Regression Action Set

Provides actions for fitting linear, generalized linear, and logistic models

glm Action

Fits linear regression models using the method of least squares.

CASL Syntax
Summary: Input and Output Tables
Parameter Descriptions

CASL Syntax

regression.glm <result=results> <status=rc> /

alpha=double,

attributes={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}},

byLimit=64-bit-integer,

class={{

countMissing=TRUE | FALSE,

descending=TRUE | FALSE,

ignoreMissing=TRUE | FALSE,

levelizeRaw=TRUE | FALSE,

maxLev=integer,

order="FORMATTED" | "FREQ" | "FREQFORMATTED" | "FREQINTERNAL" | "INTERNAL",

ref="FIRST" | "LAST" | double | "string",

split=TRUE | FALSE,

vars={"variable-name-1" <, "variable-name-2", ...>}

}, {...}},

classGlobalOpts={

countMissing=TRUE | FALSE,

descending=TRUE | FALSE,

ignoreMissing=TRUE | FALSE,

levelizeRaw=TRUE | FALSE,

maxLev=integer,

order="FORMATTED" | "FREQ" | "FREQFORMATTED" | "FREQINTERNAL" | "INTERNAL",

ref="FIRST" | "LAST" | double | "string",

split=TRUE | FALSE

classLevelsPrint=TRUE | FALSE,

clb=TRUE | FALSE,

code={

casOut={

caslib="string"

compress=TRUE | FALSE

indexVars={"variable-name-1" <, "variable-name-2", ...>}

label="string"

lifetime=64-bit-integer

maxMemSize=64-bit-integer

memoryFormat="DVR" | "INHERIT" | "STANDARD"

name="table-name"

onDemand=TRUE | FALSE

promote=TRUE | FALSE

replace=TRUE | FALSE

replication=integer

tableRedistUpPolicy="DEFER" | "NOREDIST" | "REBALANCE"

threadBlockSize=64-bit-integer

timeStamp="string"

where={"string-1" <, "string-2", ...>}

comment=TRUE | FALSE,

fmtWdth=integer,

indentSize=integer,

intoCutPt=double,

iProb=TRUE | FALSE,

labelId=integer,

lineSize=integer,

noTrim=TRUE | FALSE,

pCatAll=TRUE | FALSE,

tabForm=TRUE | FALSE

collection={{

details=TRUE | FALSE,

name="string",

vars={"variable-name-1" <, "variable-name-2", ...>}

}, {...}},

display={

caseSensitive=TRUE | FALSE,

exclude=TRUE | FALSE,

excludeAll=TRUE | FALSE,

keyIsPath=TRUE | FALSE,

names={"string-1" <, "string-2", ...>},

pathType="LABEL" | "NAME",

traceNames=TRUE | FALSE

freq="variable-name",

inputs={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}},

maxParameters=integer,

model={

addlaststopstep=TRUE | FALSE,

clb=TRUE | FALSE,

depVars={{

name="variable-name"

}, {...}},

effects={{

interaction="BAR" | "CROSS" | "NONE",

maxInteract=integer,

nest={"string-1" <, "string-2", ...>},

vars={"string-1" <, "string-2", ...>}

}, {...}},

entry="variable-name",

include=integer | {{effect-1} <, {effect-2}, ...>},

informative=TRUE | FALSE,

noint=TRUE | FALSE,

ridge={double-1 <, double-2, ...>},

ss3=TRUE | FALSE,

start=integer | {{effect-1} <, {effect-2}, ...>},

stb=TRUE | FALSE,

tol=TRUE | FALSE,

vif=TRUE | FALSE,

xpx=TRUE | FALSE,

xpxScaled=TRUE | FALSE,

xpxUnscaled=TRUE | FALSE

multimember={{

details=TRUE | FALSE,

name="string",

noEffect=TRUE | FALSE,

stdize=TRUE | FALSE,

vars={"variable-name-1" <, "variable-name-2", ...>},

weight={"variable-name-1" <, "variable-name-2", ...>}

}, {...}},

nClassLevelsPrint=integer,

nominals={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}},

output={

casOut={

caslib="string"

compress=TRUE | FALSE

indexVars={"variable-name-1" <, "variable-name-2", ...>}

label="string"

lifetime=64-bit-integer

maxMemSize=64-bit-integer

memoryFormat="DVR" | "INHERIT" | "STANDARD"

name="table-name"

promote=TRUE | FALSE

replace=TRUE | FALSE

replication=integer

tableRedistUpPolicy="DEFER" | "NOREDIST" | "REBALANCE"

threadBlockSize=64-bit-integer

timeStamp="string"

where={"string-1" <, "string-2", ...>}

cooksD="string",

copyVars="ALL" | "ALL_MODEL" | "ALL_NUMERIC" | {"variable-name-1" <, "variable-name-2", ...>},

covRatio="string",

dffits="string",

h="string",

lcl="string",

lclm="string",

likeDist="string",

pred="string",

press="string",

resid="string",

role="string",

rStudent="string",

stdi="string",

stdp="string",

stdr="string",

student="string",

ucl="string",

uclm="string"

outputTables={

groupByVarsRaw=TRUE | FALSE,

includeAll=TRUE | FALSE,

names={"string-1" <, "string-2", ...>} | {key-1={casouttable-1} <, key-2={casouttable-2}, ...>},

repeated=TRUE | FALSE,

replace=TRUE | FALSE

parmEstLevDetails="NONE" | "RAW" | "RAW_AND_FORMATTED",

partByFrac={

seed=integer,

test=double,

validate=double

partByVar={

name="variable-name",

test="string",

train="string",

validate="string"

polynomial={{

degree=integer,

details=TRUE | FALSE,

labelStyle={

expand=TRUE | FALSE

exponent="string"

includeName=TRUE | FALSE

productSymbol="NONE" | "string"

mDegree=integer,

name="string",

noSeparate=TRUE | FALSE,

standardize={

method="MOMENTS" | "MRANGE" | "WMOMENTS"

options="CENTER" | "CENTERSCALE" | "NONE" | "SCALE"

prefix="NONE" | "string"

vars={"variable-name-1" <, "variable-name-2", ...>}

}, {...}},

selection={

adaptive=TRUE | FALSE,

bestSubsetOptions={

best=integer

computeBeta=TRUE | FALSE

displayAIC=TRUE | FALSE

displayBIC=TRUE | FALSE

displayGMSEP=TRUE | FALSE

displayJP=TRUE | FALSE

displayMSE=TRUE | FALSE

displayPC=TRUE | FALSE

displayRMSE=TRUE | FALSE

displaySBC=TRUE | FALSE

displaySP=TRUE | FALSE

displaySSE=TRUE | FALSE

sigma=double

candidates=integer | "ALL",

competitive=TRUE | FALSE,

details="ALL" | "NONE" | "STEPS" | "SUMMARY",

elasticNetOptions={

absFConv=double

fConv=double

gConv=double

lambda={double-1 <, double-2, ...>}

mixing={double-1 <, double-2, ...>}

numLambda=integer

rho=double

solver="ADMM" | "BFGS" | "LBFGS" | "NLP"

enscale=TRUE | FALSE,

ensteps=integer,

fcpSelectionOptions={

alpha=double

bigM=double

coefTol=double

intTol=double

lambda=double

lambdaGrid="DEFAULT" | "LINSPACE" | "LOGSPACE"

maxAlpha=double

maxIterAlpha=integer

maxIterLambda=integer

maxLambda=double

maxTime=double

minAlpha=double

minLambda=double

scale=TRUE | FALSE

solver="DEFAULT" | "MILP" | "NLP"

gamma=double,

hierarchy="DEFAULT" | "NONE" | "SINGLE" | "SINGLECLASS",

kappa={double-1 <, double-2, ...>},

L2=double,

L2HIGH=double,

L2LOW=double,

lsCoeffs=TRUE | FALSE,

maxEffects=integer,

maxSteps=integer,

minEffects=integer,

orderSelect=TRUE | FALSE,

plots=TRUE | FALSE,

relaxed=TRUE | FALSE,

select="ADJRSQ" | "AIC" | "AICC" | "CP" | "DEFAULT" | "RSQUARE" | "SBC" | "SL",

slEntry=double,

slStay=double,

stop="ADJRSQ" | "AIC" | "AICC" | "CP" | "CV" | "DEFAULT" | "NONE" | "PRESS" | "RSQUARE" | "SBC" | "SL" | "VALIDATE",

stopHorizon=integer

spline={{

basis="BSPLINE" | "TPF_DEFAULT" | "TPF_NOINT" | "TPF_NOINTANDNOPOWERS" | "TPF_NOPOWERS",

dataBoundary=TRUE | FALSE,

degree=integer,

details=TRUE | FALSE,

knotMax=double,

knotMethod={

equal=integer

list={double-1 <, double-2, ...>}

listWithBoundary={double-1 <, double-2, ...>}

multiscale={

endScale=integer

startScale=integer

}

rangeFractions={double-1 <, double-2, ...>}

knotMin=double,

name="string",

naturalCubic=TRUE | FALSE,

separate=TRUE | FALSE,

split=TRUE | FALSE,

vars={"variable-name-1" <, "variable-name-2", ...>}

}, {...}},

ss3=TRUE | FALSE,

store={

caslib="string",

compress=TRUE | FALSE,

indexVars={"variable-name-1" <, "variable-name-2", ...>},

label="string",

lifetime=64-bit-integer,

maxMemSize=64-bit-integer,

memoryFormat="DVR" | "INHERIT" | "STANDARD",

name="table-name",

promote=TRUE | FALSE,

replace=TRUE | FALSE,

replication=integer,

tableRedistUpPolicy="DEFER" | "NOREDIST" | "REBALANCE",

threadBlockSize=64-bit-integer,

timeStamp="string",

where={"string-1" <, "string-2", ...>}

table={

caslib="string",

computedOnDemand=TRUE | FALSE,

computedVars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}},

computedVarsProgram="string",

dataSourceOptions={key-1=any-list-or-data-type-1 <, key-2=any-list-or-data-type-2, ...>},

groupBy={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}},

groupByMode="NOSORT" | "REDISTRIBUTE",

importOptions={fileType="ANY" | "AUDIO" | "AUTO" | "BASESAS" | "CSV" | "DELIMITED" | "DOCUMENT" | "DTA" | "ESP" | "EXCEL" | "FMT" | "HDAT" | "IMAGE" | "JMP" | "LASR" | "PARQUET" | "SOUND" | "SPSS" | "VIDEO" | "XLS", fileType-specific-parameters},

name="table-name",

orderBy={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}},

singlePass=TRUE | FALSE,

vars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}},

where="where-expression",

whereTable={

casLib="string"

dataSourceOptions={adls_noreq-parameters | bigquery-parameters | cas_noreq-parameters | clouddex-parameters | db2-parameters | dnfs-parameters | esp-parameters | fedsvr-parameters | gcs_noreq-parameters | hadoop-parameters | hana-parameters | impala-parameters | informix-parameters | jdbc-parameters | mongodb-parameters | mysql-parameters | odbc-parameters | oracle-parameters | path-parameters | postgres-parameters | redshift-parameters | s3-parameters | sapiq-parameters | sforce-parameters | singlestore_standard-parameters | snowflake-parameters | spark-parameters | spde-parameters | sqlserver-parameters | ss_noreq-parameters | teradata-parameters | vertica-parameters | yellowbrick-parameters}

name="table-name"

vars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

where="where-expression"

}

target="string",

weight="variable-name"

;

indicates a required parameter

Summary: Input and Output Tables

If a row includes a subparameter, you can specify the name, caslib, and so on in the subparameter. Otherwise, you can specify the name, caslib, and so on in the parameter.

Parameters for Reading Input Tables
Parameter	Subparameter	Description
required parametertable	—	specifies the input data table.

Parameters for Creating Output Tables
Parameter	Subparameter	Description
code	casOut	writes SAS DATA step code for computing predicted values of the fitted model
output	required parametercasOut	creates a table on the server that contains observationwise statistics, which are computed after fitting the model.
outputTables	names	lists the names of results tables to save as CAS tables on the server.
store	—	stores regression models to a binary large object (BLOB).

Parameter Descriptions

alpha=double

specifies the significance level to use for the construction of all confidence intervals.

Default	0.05
Range	(0, 1)

attributes={{casinvardesc-1} <, {casinvardesc-2}, ...>}

changes the attributes of variables used in this action. Currently, attributes specified on the inputs and nominals parameter are ignored.

For more information about specifying the attributes parameter, see the common casinvardesc parameter (Appendix A: Common Parameters).

Alias	attribute

byLimit=64-bit-integer

specifies that the analysis not be performed if the number of BY groups exceeds the specified value.

Minimum value	1

class={{classStatement-1} <, {classStatement-2}, ...>}

names the classification variables to be used as explanatory variables in the analysis.

For more information about class subparameters, see class Parameter (Shared Concepts).

For more information about specifying the class parameter, see the common classStatement parameter (Appendix A: Common Parameters).

Alias	classVars

classGlobalOpts={classopts}

lists options that apply to all classification variables.

For more information about specifying the classGlobalOpts parameter, see the common classopts parameter (Appendix A: Common Parameters).

classLevelsPrint=TRUE | FALSE

when set to False, suppresses the display of class levels.

Default	TRUE

clb=TRUE | FALSE

when set to True, displays upper and lower confidence limits for the parameter estimates.

Default	FALSE

code={aircodegen}

writes SAS DATA step code for computing predicted values of the fitted model

For more information about specifying the code parameter, see the common aircodegen parameter (Appendix A: Common Parameters).

collection={{collection-1} <, {collection-2}, ...>}

defines a set of variables that are treated as a single effect that has multiple degrees of freedom.

For more information, see Collection Effects (Shared Concepts).

The collection value can be one or more of the following:

details=TRUE | FALSE

when set to True, requests a table that shows additional details that are related to this effect.

Default	FALSE

* name="string"

specifies the name of the effect.

* vars={"variable-name-1" <, "variable-name-2", ...>}

specifies a set of variables that are treated as a single effect that has multiple degrees of freedom. The columns in the design matrix that are contributed by a collection effect are the design columns of its constituent variables in the order in which they appear in the definition of the collection effect.

display={displayTables}

specifies a list of results tables to send to the client for display.

For more information about display subparameters, see display Parameter (Shared Concepts).

For more information about specifying the display parameter, see the common displayTables parameter (Appendix A: Common Parameters).

freq="variable-name"

names the numeric variable that contains the frequency of occurrence of each observation.

inputs={{casinvardesc-1} <, {casinvardesc-2}, ...>}

specifies variables to use for analysis.

For more information about specifying the inputs parameter, see the common casinvardesc parameter (Appendix A: Common Parameters).

Alias	input

maxParameters=integer

specifies that models not be fit if the number of parameters exceeds the specified value.

Minimum value	0

model={glmmodel}

names the dependent variable, explanatory effects, and model options.

For information about model specification, see Introduction (Specifying Linear Models for SAS Viya Analytical Actions).

The glmmodel value can be one or more of the following:

addlaststopstep=TRUE | FALSE

when set to FALSE, ignores the information from the last stop step.

Default	TRUE

clb=TRUE | FALSE

when set to True, displays upper and lower confidence limits for the parameter estimates.

Default	FALSE

depVars={{responsevar-1} <, {responsevar-2}, ...>}

specifies one or more variables to use as response variables in the model. Not all models support more than one response variable.

Aliases	depVar
Aliases	target

name="variable-name"

names the response variable.

effects={{effect-1} <, {effect-2}, ...>}

specifies a list of effects that define the model. Each term in this list is made up of variables specified in the vars parameter and their interaction (which can be NONE, CROSS, or BAR). When the interaction is BAR, it can be limited by the maxInteract parameter.

For more information, see Introduction (Specifying Linear Models for SAS Viya Analytical Actions).

The effect value can be one or more of the following:

interaction="BAR" | "CROSS" | "NONE"

specifies the type of interaction for the variables.

Alias	interact
Default	NONE

maxInteract=integer

eliminates interaction effects whose order is higher than the specified integer value when used in conjunction with the BAR interaction.

nest={"string-1" <, "string-2", ...>}

specifies the variables to be nested within the term that is defined by the vars parameter. For terms with a BAR or CROSS interaction, the nest corresponds to the last variable in the vars parameter. For terms with no interaction, the nest is distributed across all variables that are listed in the vars parameter.

* vars={"string-1" <, "string-2", ...>}

specifies the variables to use in defining a term of the effect. You must specify at least one variable.

entry="variable-name"

specifies the entry variable.

include=integer | {{effect-1} <, {effect-2}, ...>}

specifies effects to include at the start of the selection process for the specified selection method. Included effects are never dropped during the selection process. If you specify n, where n is a positive integer, then the included effects consist of the first n effects of the model specification.

The effect value is specified as follows:

interaction="BAR" | "CROSS" | "NONE"

specifies the type of interaction for the variables.

Alias	interact
Default	NONE

maxInteract=integer

eliminates interaction effects whose order is higher than the specified integer value when used in conjunction with the BAR interaction.

nest={"string-1" <, "string-2", ...>}

* vars={"string-1" <, "string-2", ...>}

specifies the variables to use in defining a term of the effect. You must specify at least one variable.

informative=TRUE | FALSE

when set to True, models missing values by using extra model effects. These effects consist of dummy variables that take the value 1 when the value of a continuous model variable involved in the effect is missing, and take the value 0 otherwise. The missing value in the original model effect is replaced by the average value of the effect for the nonmissing values. For classification variables, missing values are treated as valid levels.

For more information, see Informative Missingness (Shared Concepts).

Default	FALSE

noint=TRUE | FALSE

when set to True, does not include the intercept term in the model.

Default	FALSE

ridge={double-1 <, double-2, ...>}

specifies the ridge constant values for ridge regression.

ss3=TRUE | FALSE

when set to True, performs a model analysis of variance based on type III sums of squares.

Default	FALSE

start=integer | {{effect-1} <, {effect-2}, ...>}

specifies effects to use to begin the selection process in the FORWARD, FORWARDSWAP, and STEPWISE selection methods. If you specify n, where n is a positive integer, then the starting model consists of the first n effects of the model specification.

The effect value is specified as follows:

interaction="BAR" | "CROSS" | "NONE"

specifies the type of interaction for the variables.

Alias	interact
Default	NONE

maxInteract=integer

eliminates interaction effects whose order is higher than the specified integer value when used in conjunction with the BAR interaction.

nest={"string-1" <, "string-2", ...>}

* vars={"string-1" <, "string-2", ...>}

specifies the variables to use in defining a term of the effect. You must specify at least one variable.

stb=TRUE | FALSE

when set to True, produces standardized regression coefficients. A standardized regression coefficient is computed by dividing a parameter estimate by the ratio of the sample standard deviation of the dependent variable to the sample standard deviation of the regressor.

Default	FALSE

tol=TRUE | FALSE

when set to True, produces tolerance values for the estimates. Tolerance for a variable is defined as 1 - R-square, where R-square is obtained from the regression of the variable on all other regressors in the model.

Default	FALSE

vif=TRUE | FALSE

when set to True, produces variance inflation factors with the parameter estimates. Variance inflation is the reciprocal of tolerance.

Default	FALSE

xpx=TRUE | FALSE

Crossproducts

Default	FALSE

xpxScaled=TRUE | FALSE

Scaled Crossproducts

Default	FALSE

xpxUnscaled=TRUE | FALSE

Unscaled Crossproducts

Default	FALSE

multimember={{multimember-1} <, {multimember-2}, ...>}

uses one or more classification variables specified in the vars parameter in such a way that each observation can be associated with one or more levels of the union of the levels of the classification variables.

For more information, see Multimember Effects (Shared Concepts).

For more information about specifying the multimember parameter, see the common multimember parameter (Appendix A: Common Parameters).

nClassLevelsPrint=integer

limits the display of class levels. The value 0 suppresses all levels.

Minimum value	0

nominals={{casinvardesc-1} <, {casinvardesc-2}, ...>}

specifies nominal variables to use for analysis.

For more information about specifying the nominals parameter, see the common casinvardesc parameter (Appendix A: Common Parameters).

Alias	nominal

output={glmOutputStatement}

creates a table on the server that contains observationwise statistics, which are computed after fitting the model.

For more information about the available statistics, see Predicted Values and Regression Diagnostics (GENSELECT Procedure in SAS Visual Statistics: Procedures).

For more information, see OUTPUT Statement (GENSELECT Procedure in SAS Visual Statistics: Procedures).

The glmOutputStatement value can be one or more of the following:

* casOut={casouttable}

specifies the settings for an output table.

For more information about specifying the casOut parameter, see the common casouttable (Form 1) parameter (Appendix A: Common Parameters).

cooksD="string"

names the Cook's D influence statistic.

copyVars="ALL" | "ALL_MODEL" | "ALL_NUMERIC" | {"variable-name-1" <, "variable-name-2", ...>}

specifies a list of one or more variables to be copied from the input table to the output table. You can alternatively specify the value ALL, ALL_MODEL, or ALL_NUMERIC, which respectively copies all variables, all variables used in the modeling, or all numeric variables from the input table to the output table.

covRatio="string"

names the standard influence of the observation on covariance of betas. The COVRATIO statistic measures the change in the determinant of the covariance matrix of the estimates by deleting the ith observation.

dffits="string"

names the scaled measure of the change in the predicted value for the ith observation and is calculated by deleting the ith observation. A large value indicates that the observation is very influential in its neighborhood of the X space.

h="string"

names the leverage of the observation.

lcl="string"

names the lower bound of a confidence interval for an individual prediction.

lclm="string"

names the lower bound of a confidence interval for the expected value of the dependent variable.

likeDist="string"

names the likelihood displacement.

pred="string"

names the predicted value. If you do not specify any output statistics, then by default the predicted value is named Pred.

press="string"

names the ith residual divided by 1 - h, where h is the leverage, and where the model has been refit without the ith observation.

resid="string"

names the residual, calculated as ACTUAL minus PREDICTED.

role="string"

identifies the training, validation, and test roles for the observations.

rStudent="string"

names the studentized residual with the current observation deleted.

stdi="string"

names the standard error of the individual predicted value.

stdp="string"

names the standard error of the mean predicted value.

stdr="string"

names the standard error of the residual.

student="string"

names the studentized residuals, which are the residuals divided by their standard errors.

ucl="string"

names the upper bound of a confidence interval for an individual prediction.

uclm="string"

names the upper bound of a confidence interval for the expected value of the dependent variable.

outputTables={outputTables}

lists the names of results tables to save as CAS tables on the server.

For more information about specifying the outputTables parameter, see the common outputTables parameter (Appendix A: Common Parameters).

Alias	displayOut

parmEstLevDetails="NONE" | "RAW" | "RAW_AND_FORMATTED"

specifies whether to add raw and formatted values of classification variables in the ParameterEstimates table.

Default	RAW

partByFrac={partByFracStatement}

specifies the fractions of the data to be used for validation and testing.

For more information, see partByFrac and partByVar Partitioning Parameters (Shared Concepts).

The partByFracStatement value can be one or more of the following:

seed=integer

specifies the seed to use in the random number generator that is used for partitioning the data.

Default	0

test=double

randomly assigns the specified proportion of observations in the input table to the testing role. The sum of the fractions that are specified in the test and validate parameters must be less than 1.

Range	0–1

validate=double

randomly assigns the specified proportion of observations in the input table to the validation role. The sum of the fractions that are specified in the test and validate parameters must be less than 1.

Alias	valid
Range	0–1

partByVar={partByVarStatement}

names the variable and its values used to partition the data into training, validation, and testing roles.

For more information, see partByFrac and partByVar Partitioning Parameters (Shared Concepts).

Long form	partByVar={name="variable-name"}
Shortcut form	partByVar="variable-name"

The partByVarStatement value can be one or more of the following:

* name="variable-name"

names the variable in the input table whose values are used to assign roles to each observation.

test="string"

specifies the formatted value of the variable that is used to assign observations to the testing role.

train="string"

specifies the formatted value of the variable that is used to assign observations to the training role. If you do not specify the train parameter, then all observations whose roles are not determined by the test and validate parameters are assigned to training.

validate="string"

specifies the formatted value of the variable that is used to assign observations to the validation role.

Alias	valid

polynomial={{polynomial-1} <, {polynomial-2}, ...>}

specifies a polynomial effect. All specified variables must be numeric. A design matrix column is generated for each term of the specified polynomial. By default, each of these terms is treated as a separate effect for the purpose of model building.

For more information, see Polynomial Effects (Shared Concepts).

For more information about specifying the polynomial parameter, see the common polynomial parameter (Appendix A: Common Parameters).

Alias	poly

selection={selectionStatement}

specifies the method and options for performing model selection.

For more information, see selection Parameter (Shared Concepts).

Long form	selection={method="BACKWARD" \| "BESTSUBSET" \| "ELASTICNET" \| "FORWARD" \| "FORWARDSWAP" \| "LAR" \| "LASSO" \| "MCP" \| "NONE" \| "SCAD" \| "STEPWISE"}
Shortcut form	selection="BACKWARD" \| "BESTSUBSET" \| "ELASTICNET" \| "FORWARD" \| "FORWARDSWAP" \| "LAR" \| "LASSO" \| "MCP" \| "NONE" \| "SCAD" \| "STEPWISE"

The selectionStatement value can be one or more of the following:

adaptive=TRUE | FALSE

when set to True, applies adaptive weights to each of the coefficients in the LASSO method.

Default	FALSE

bestSubsetOptions={bestOptions}

specifies options to perform best-subset selection.

The bestOptions value can be one or more of the following:

best=integer

specifies the maximum number of subset models to display.

Minimum value	0

computeBeta=TRUE | FALSE

when set to True, requests estimated regression coefficients for each subset model.

Alias	beta
Default	FALSE

displayAIC=TRUE | FALSE

when set to True, adds Akaike's information criterion to the selection summary.

Alias	aic
Default	FALSE

displayBIC=TRUE | FALSE

when set to True, adds the Bayesian information criterion to the selection summary.

Alias	bic
Default	FALSE

displayGMSEP=TRUE | FALSE

when set to True, adds estimated mean square error of prediction to the selection summary.

Alias	gmsep
Default	FALSE

displayJP=TRUE | FALSE

when set to True, adds final prediction error to the selection summary.

Alias	jp
Default	FALSE

displayMSE=TRUE | FALSE

when set to True, adds mean square error to the selection summary.

Alias	mse
Default	FALSE

displayPC=TRUE | FALSE

when set to True, adds Amemiya's prediction criterion to the selection summary.

Alias	pc
Default	FALSE

displayRMSE=TRUE | FALSE

when set to True, adds root mean square error to the selection summary.

Alias	rmse
Default	FALSE

displaySBC=TRUE | FALSE

when set to True, adds the Schwarz Bayesian criterion to the selection summary.

Alias	sbc
Default	FALSE

displaySP=TRUE | FALSE

when set to True, adds SP to the selection summary.

Alias	sp
Default	FALSE

displaySSE=TRUE | FALSE

when set to True, adds error sum of squares to the selection summary.

Alias	sse
Default	FALSE

sigma=double

specifies the true standard deviation of the error term to use in computing the CP and BIC statistics.

Default	0

candidates=integer | "ALL"

specifies the maximum number of candidates to display at each step of the selection process, when the detail level ALL is specified.

choose="ADJRSQ" | "AIC" | "AICC" | "CP" | "CV" | "DEFAULT" | "NONE" | "PRESS" | "RSQUARE" | "SBC" | "VALIDATE"

specifies the criterion for choosing the model. The specified criterion is evaluated at each step of the selection process, and the model that yields the best value of the criterion is chosen.

For more information, see the discussion of the choose subparameter (Shared Concepts).

competitive=TRUE | FALSE

when set to True, evaluates (during stepwise selection) the selection criterion for all models in which an effect currently in the model is dropped or an effect not yet in the model is added. The effect whose removal from or addition to the model yields the maximum improvement to the selection criterion is dropped or added.

Default	FALSE

details="ALL" | "NONE" | "STEPS" | "SUMMARY"

specifies the level of detail to produce about the selection process.

For more information, see the description of the details subparameter (Shared Concepts).

Default	SUMMARY

elasticNetOptions={enOptions}

specifies options to use in performing elastic net selection methods.

The enOptions value can be one or more of the following:

absFConv=double

specifies the absolute function difference convergence criterion.

Alias	abstol
Default	1E-08
Minimum value	0

fConv=double

specifies the relative function difference convergence criterion.

Alias	fTol
Minimum value	0

gConv=double

specifies the relative gradient convergence criterion.

Alias	gTol
Minimum value	0

lambda={double-1 <, double-2, ...>}

specifies the regularization parameters in the elastic net selection method.

mixing={double-1 <, double-2, ...>}

specifies the elastic net mixing parameter.

numLambda=integer

specifies the number of regularization parameters in the elastic net selection method.

Alias	nLambda
Default	0
Minimum value	0

rho=double

specifies the scaling factor to use in computing minimum regularization parameter.

Range	(0, 1)

solver="ADMM" | "BFGS" | "LBFGS" | "NLP"

specifies a solver for elastic net selection.

enscale=TRUE | FALSE

when set to True, applies scaling to beta in the elastic net selection method.

Default	FALSE

ensteps=integer

specifies the number of iterations to use in the elastic net selection method.

Default	50

fcpSelectionOptions={fcpOptions}

specifies options to use in performing the folded concave penalized (FCP) selection methods.

The fcpOptions value can be one or more of the following:

alpha=double

specifies the alpha value in the SCAD and MCP selection methods.

Minimum value (exclusive)	0

bigM=double

specifies the big M constant in the mixed integer linear programming (MILP) solver.

Minimum value (exclusive)	0

coefTol=double

specifies the tolerance for truncating estimated coefficients.

Alias	coefficientTolerance
Minimum value (exclusive)	0

intTol=double

specifies the tolerance for integer variables in the mixed integer linear programming (MILP) solver.

Alias	integerTolerance
Minimum value (exclusive)	0

lambda=double

specifies the fixed lambda value in the SCAD and MCP selection methods.

Minimum value (exclusive)	0

lambdaGrid="DEFAULT" | "LINSPACE" | "LOGSPACE"

specifies the lambda searching grid in the SCAD and MCP selection methods.

maxAlpha=double

specifies the upper bound to use in searching for alpha in the SCAD and MCP selection methods.

Minimum value (exclusive)	0

maxIterAlpha=integer

specifies the number of iterations to use in searching for the best alpha value in the SCAD and MCP selection methods.

Minimum value	2

maxIterLambda=integer

specifies the maximum number of iterations to use in searching for the best lambda value in the SCAD and MCP selection methods.

Minimum value	2

maxLambda=double

specifies the maximum lambda value in the SCAD and MCP selection methods.

Minimum value (exclusive)	0

maxTime=double

specifies the time limit allowed for the optimization solver.

Minimum value (exclusive)	0

minAlpha=double

specifies the lower bound to use in searching for alpha in the SCAD and MCP selection methods.

Minimum value (exclusive)	0

minLambda=double

specifies the minimum lambda value in the SCAD and MCP selection methods.

Minimum value (exclusive)	0

scale=TRUE | FALSE

when set to True, applies normalization in computing the crossproducts matrix.

Default	TRUE

solver="DEFAULT" | "MILP" | "NLP"

specifies the solver to use in the SCAD and MCP selection methods.

gamma=double

specifies the exponent of the power transformation that is applied to the parameters in forming the adaptive weights.

Default	1

hierarchy="DEFAULT" | "NONE" | "SINGLE" | "SINGLECLASS"

specifies whether and how to apply the model hierarchy requirement. Model hierarchy refers to the requirement that, for any term to be in the model, all model effects that are contained in the term must be present in the model.

For more information, see the description of the hierarchy subparameter (Shared Concepts).

Default	DEFAULT

kappa={double-1 <, double-2, ...>}

specifies the coefficients in the relaxed LASSO method.

L2=double

specifies the L2 parameter in the elastic net selection method.

Default	0

L2HIGH=double

specifies the upper bound to use in searching for the L2 parameter in the elastic net selection method.

Alias	maxL2
Default	1

L2LOW=double

specifies the lower bound to use in searching for the L2 parameter in the elastic net selection method.

Alias	minL2
Default	0

lsCoeffs=TRUE | FALSE

when set to True, specifies a hybrid version of the LAR or LASSO method, in which the sequence of models is determined by the LAR or LASSO method but the coefficients of the parameters for the model at any step are determined by using ordinary least squares.

Default	FALSE

maxEffects=integer

specifies the maximum number of effects in any model to consider during the selection process. This parameter is ignored for backward selection.

maxSteps=integer

specifies the maximum number of selection steps to perform.

method="BACKWARD" | "BESTSUBSET" | "ELASTICNET" | "FORWARD" | "FORWARDSWAP" | "LAR" | "LASSO" | "MCP" | "NONE" | "SCAD" | "STEPWISE"

specifies the model selection method.

For more information, see Model Selection Methods (Shared Concepts).

Default	STEPWISE

minEffects=integer

specifies the minimum number of effects in any model to consider during backward selection.

orderSelect=TRUE | FALSE

when set to True, shows effects in parameter estimates tables in the order in which they were added to the model.

Default	FALSE

plots=TRUE | FALSE

when set to True, produces coefficientProgression and selectionSummaryForPlots tables that you can use to produce selection diagnostic plots.

For more information about the plots you can create, see Model Selection Plots (Shared Concepts in SAS Visual Statistics: Procedures).

Default	FALSE

relaxed=TRUE | FALSE

when set to True, applies the relaxed LASSO method.

Default	FALSE

select="ADJRSQ" | "AIC" | "AICC" | "CP" | "DEFAULT" | "RSQUARE" | "SBC" | "SL"

specifies the criterion to use in determining the order in which effects enter or leave at each step of the selection method. This parameter does not apply to LAR or LASSO selection.

For more information, see the discussion of the select subparameter (Shared Concepts).

slEntry=double

specifies the significance level for entry when the significance level is used as the select or stop criterion.

Alias	sle
Default	0.05
Range	(0, 1)

slStay=double

specifies the significance level for removal when the significance level is used as the select or stop criterion.

Alias	sls
Default	0.05
Range	(0, 1)

stop="ADJRSQ" | "AIC" | "AICC" | "CP" | "CV" | "DEFAULT" | "NONE" | "PRESS" | "RSQUARE" | "SBC" | "SL" | "VALIDATE"

specifies a criterion that to use for stopping the selection process. If you do not specify a stop criterion, then the criterion that is used to select the model is also used as the stop criterion.

For more information, see the discussion of the stop subparameter (Shared Concepts).

stopHorizon=integer

specifies the number of consecutive steps at which the stop criterion must worsen in order for a local extremum to be detected.

For more information, see the description of the stopHorizon subparameter (Shared Concepts).

Default	3

spline={{spline-1} <, {spline-2}, ...>}

expands variables into spline bases whose form depends on the specified parameters.

For more information, see Spline Effects (Shared Concepts).

For more information about specifying the spline parameter, see the common spline parameter (Appendix A: Common Parameters).

ss3=TRUE | FALSE

when set to True, performs a model analysis of variance based on type III sums of squares.

Default	FALSE

store={casouttable}

stores regression models to a binary large object (BLOB).

For more information about specifying the store parameter, see the common casouttable (Form 1) parameter (Appendix A: Common Parameters).

Alias	savestate

* table={castable}

specifies the input data table.

For more information about specifying the table parameter, see the common castable (Form 1) parameter (Appendix A: Common Parameters).

target="string"

specifies the target variable to use for analysis.

weight="variable-name"

names the numeric variable to use to perform a weighted analysis of the data.

glm Action

Fits linear regression models using the method of least squares.

Lua Syntax
Summary: Input and Output Tables
Parameter Descriptions

Lua Syntax

results, info = s:regression_glm{

alpha=double,

attributes={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}},

byLimit=64-bit-integer,

class={{

countMissing=true | false,

descending=true | false,

ignoreMissing=true | false,

levelizeRaw=true | false,

maxLev=integer,

order="FORMATTED" | "FREQ" | "FREQFORMATTED" | "FREQINTERNAL" | "INTERNAL",

ref="FIRST" | "LAST" | double | "string",

split=true | false,

vars={"variable-name-1" <, "variable-name-2", ...>}

}, {...}},

classGlobalOpts={

countMissing=true | false,

descending=true | false,

ignoreMissing=true | false,

levelizeRaw=true | false,

maxLev=integer,

order="FORMATTED" | "FREQ" | "FREQFORMATTED" | "FREQINTERNAL" | "INTERNAL",

ref="FIRST" | "LAST" | double | "string",

split=true | false

classLevelsPrint=true | false,

clb=true | false,

code={

casOut={

caslib="string"

compress=true | false

indexVars={"variable-name-1" <, "variable-name-2", ...>}

label="string"

lifetime=64-bit-integer

maxMemSize=64-bit-integer

memoryFormat="DVR" | "INHERIT" | "STANDARD"

name="table-name"

onDemand=true | false

promote=true | false

replace=true | false

replication=integer

tableRedistUpPolicy="DEFER" | "NOREDIST" | "REBALANCE"

threadBlockSize=64-bit-integer

timeStamp="string"

where={"string-1" <, "string-2", ...>}

comment=true | false,

fmtWdth=integer,

indentSize=integer,

intoCutPt=double,

iProb=true | false,

labelId=integer,

lineSize=integer,

noTrim=true | false,

pCatAll=true | false,

tabForm=true | false

collection={{

details=true | false,

name="string",

vars={"variable-name-1" <, "variable-name-2", ...>}

}, {...}},

display={

caseSensitive=true | false,

exclude=true | false,

excludeAll=true | false,

keyIsPath=true | false,

names={"string-1" <, "string-2", ...>},

pathType="LABEL" | "NAME",

traceNames=true | false

freq="variable-name",

inputs={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}},

maxParameters=integer,

model={

addlaststopstep=true | false,

clb=true | false,

depVars={{

name="variable-name"

}, {...}},

effects={{

interaction="BAR" | "CROSS" | "NONE",

maxInteract=integer,

nest={"string-1" <, "string-2", ...>},

vars={"string-1" <, "string-2", ...>}

}, {...}},

entry="variable-name",

include=integer | {{effect-1} <, {effect-2}, ...>},

informative=true | false,

noint=true | false,

ridge={double-1 <, double-2, ...>},

ss3=true | false,

start=integer | {{effect-1} <, {effect-2}, ...>},

stb=true | false,

tol=true | false,

vif=true | false,

xpx=true | false,

xpxScaled=true | false,

xpxUnscaled=true | false

multimember={{

details=true | false,

name="string",

noEffect=true | false,

stdize=true | false,

vars={"variable-name-1" <, "variable-name-2", ...>},

weight={"variable-name-1" <, "variable-name-2", ...>}

}, {...}},

nClassLevelsPrint=integer,

nominals={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}},

output={

casOut={

caslib="string"

compress=true | false

indexVars={"variable-name-1" <, "variable-name-2", ...>}

label="string"

lifetime=64-bit-integer

maxMemSize=64-bit-integer

memoryFormat="DVR" | "INHERIT" | "STANDARD"

name="table-name"

promote=true | false

replace=true | false

replication=integer

tableRedistUpPolicy="DEFER" | "NOREDIST" | "REBALANCE"

threadBlockSize=64-bit-integer

timeStamp="string"

where={"string-1" <, "string-2", ...>}

cooksD="string",

copyVars="ALL" | "ALL_MODEL" | "ALL_NUMERIC" | {"variable-name-1" <, "variable-name-2", ...>},

covRatio="string",

dffits="string",

h="string",

lcl="string",

lclm="string",

likeDist="string",

pred="string",

press="string",

resid="string",

role="string",

rStudent="string",

stdi="string",

stdp="string",

stdr="string",

student="string",

ucl="string",

uclm="string"

outputTables={

groupByVarsRaw=true | false,

includeAll=true | false,

names={"string-1" <, "string-2", ...>} | {key-1={casouttable-1} <, key-2={casouttable-2}, ...>},

repeated=true | false,

replace=true | false

parmEstLevDetails="NONE" | "RAW" | "RAW_AND_FORMATTED",

partByFrac={

seed=integer,

test=double,

validate=double

partByVar={

name="variable-name",

test="string",

train="string",

validate="string"

polynomial={{

degree=integer,

details=true | false,

labelStyle={

expand=true | false

exponent="string"

includeName=true | false

productSymbol="NONE" | "string"

mDegree=integer,

name="string",

noSeparate=true | false,

standardize={

method="MOMENTS" | "MRANGE" | "WMOMENTS"

options="CENTER" | "CENTERSCALE" | "NONE" | "SCALE"

prefix="NONE" | "string"

vars={"variable-name-1" <, "variable-name-2", ...>}

}, {...}},

selection={

adaptive=true | false,

bestSubsetOptions={

best=integer

computeBeta=true | false

displayAIC=true | false

displayBIC=true | false

displayGMSEP=true | false

displayJP=true | false

displayMSE=true | false

displayPC=true | false

displayRMSE=true | false

displaySBC=true | false

displaySP=true | false

displaySSE=true | false

sigma=double

candidates=integer | "ALL",

competitive=true | false,

details="ALL" | "NONE" | "STEPS" | "SUMMARY",

elasticNetOptions={

absFConv=double

fConv=double

gConv=double

lambda={double-1 <, double-2, ...>}

mixing={double-1 <, double-2, ...>}

numLambda=integer

rho=double

solver="ADMM" | "BFGS" | "LBFGS" | "NLP"

enscale=true | false,

ensteps=integer,

fcpSelectionOptions={

alpha=double

bigM=double

coefTol=double

intTol=double

lambda=double

lambdaGrid="DEFAULT" | "LINSPACE" | "LOGSPACE"

maxAlpha=double

maxIterAlpha=integer

maxIterLambda=integer

maxLambda=double

maxTime=double

minAlpha=double

minLambda=double

scale=true | false

solver="DEFAULT" | "MILP" | "NLP"

gamma=double,

hierarchy="DEFAULT" | "NONE" | "SINGLE" | "SINGLECLASS",

kappa={double-1 <, double-2, ...>},

L2=double,

L2HIGH=double,

L2LOW=double,

lsCoeffs=true | false,

maxEffects=integer,

maxSteps=integer,

minEffects=integer,

orderSelect=true | false,

plots=true | false,

relaxed=true | false,

select="ADJRSQ" | "AIC" | "AICC" | "CP" | "DEFAULT" | "RSQUARE" | "SBC" | "SL",

slEntry=double,

slStay=double,

stop="ADJRSQ" | "AIC" | "AICC" | "CP" | "CV" | "DEFAULT" | "NONE" | "PRESS" | "RSQUARE" | "SBC" | "SL" | "VALIDATE",

stopHorizon=integer

spline={{

basis="BSPLINE" | "TPF_DEFAULT" | "TPF_NOINT" | "TPF_NOINTANDNOPOWERS" | "TPF_NOPOWERS",

dataBoundary=true | false,

degree=integer,

details=true | false,

knotMax=double,

knotMethod={

equal=integer

list={double-1 <, double-2, ...>}

listWithBoundary={double-1 <, double-2, ...>}

multiscale={

endScale=integer

startScale=integer

}

rangeFractions={double-1 <, double-2, ...>}

knotMin=double,

name="string",

naturalCubic=true | false,

separate=true | false,

split=true | false,

vars={"variable-name-1" <, "variable-name-2", ...>}

}, {...}},

ss3=true | false,

store={

caslib="string",

compress=true | false,

indexVars={"variable-name-1" <, "variable-name-2", ...>},

label="string",

lifetime=64-bit-integer,

maxMemSize=64-bit-integer,

memoryFormat="DVR" | "INHERIT" | "STANDARD",

name="table-name",

promote=true | false,

replace=true | false,

replication=integer,

tableRedistUpPolicy="DEFER" | "NOREDIST" | "REBALANCE",

threadBlockSize=64-bit-integer,

timeStamp="string",

where={"string-1" <, "string-2", ...>}

table={

caslib="string",

computedOnDemand=true | false,

computedVars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}},

computedVarsProgram="string",

dataSourceOptions={key-1=any-list-or-data-type-1 <, key-2=any-list-or-data-type-2, ...>},

groupBy={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}},

groupByMode="NOSORT" | "REDISTRIBUTE",

name="table-name",

orderBy={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}},

singlePass=true | false,

vars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}},

where="where-expression",

whereTable={

casLib="string"

name="table-name"

vars={{

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

}, {...}}

where="where-expression"

}

target="string",

weight="variable-name"

}

indicates a required parameter

Summary: Input and Output Tables

If a row includes a subparameter, you can specify the name, caslib, and so on in the subparameter. Otherwise, you can specify the name, caslib, and so on in the parameter.

Parameters for Reading Input Tables
Parameter	Subparameter	Description
required parametertable	—	specifies the input data table.

Parameters for Creating Output Tables
Parameter	Subparameter	Description
code	casOut	writes SAS DATA step code for computing predicted values of the fitted model
output	required parametercasOut	creates a table on the server that contains observationwise statistics, which are computed after fitting the model.
outputTables	names	lists the names of results tables to save as CAS tables on the server.
store	—	stores regression models to a binary large object (BLOB).

Parameter Descriptions

alpha=double

specifies the significance level to use for the construction of all confidence intervals.

Default	0.05
Range	(0, 1)

attributes={{casinvardesc-1} <, {casinvardesc-2}, ...>}

changes the attributes of variables used in this action. Currently, attributes specified on the inputs and nominals parameter are ignored.

For more information about specifying the attributes parameter, see the common casinvardesc parameter (Appendix A: Common Parameters).

Alias	attribute

byLimit=64-bit-integer

specifies that the analysis not be performed if the number of BY groups exceeds the specified value.

Minimum value	1

class={{classStatement-1} <, {classStatement-2}, ...>}

names the classification variables to be used as explanatory variables in the analysis.

For more information about class subparameters, see class Parameter (Shared Concepts).

For more information about specifying the class parameter, see the common classStatement parameter (Appendix A: Common Parameters).

Alias	classVars

classGlobalOpts={classopts}

lists options that apply to all classification variables.

For more information about specifying the classGlobalOpts parameter, see the common classopts parameter (Appendix A: Common Parameters).

classLevelsPrint=true | false

when set to False, suppresses the display of class levels.

Default	true

clb=true | false

when set to True, displays upper and lower confidence limits for the parameter estimates.

Default	false

code={aircodegen}

writes SAS DATA step code for computing predicted values of the fitted model

For more information about specifying the code parameter, see the common aircodegen parameter (Appendix A: Common Parameters).

collection={{collection-1} <, {collection-2}, ...>}

defines a set of variables that are treated as a single effect that has multiple degrees of freedom.

For more information, see Collection Effects (Shared Concepts).

The collection value can be one or more of the following:

details=true | false

when set to True, requests a table that shows additional details that are related to this effect.

Default	false

* name="string"

specifies the name of the effect.

* vars={"variable-name-1" <, "variable-name-2", ...>}

display={displayTables}

specifies a list of results tables to send to the client for display.

For more information about display subparameters, see display Parameter (Shared Concepts).

For more information about specifying the display parameter, see the common displayTables parameter (Appendix A: Common Parameters).

freq="variable-name"

names the numeric variable that contains the frequency of occurrence of each observation.

inputs={{casinvardesc-1} <, {casinvardesc-2}, ...>}

specifies variables to use for analysis.

For more information about specifying the inputs parameter, see the common casinvardesc parameter (Appendix A: Common Parameters).

Alias	input

maxParameters=integer

specifies that models not be fit if the number of parameters exceeds the specified value.

Minimum value	0

model={glmmodel}

names the dependent variable, explanatory effects, and model options.

For information about model specification, see Introduction (Specifying Linear Models for SAS Viya Analytical Actions).

The glmmodel value can be one or more of the following:

addlaststopstep=true | false

when set to FALSE, ignores the information from the last stop step.

Default	true

clb=true | false

when set to True, displays upper and lower confidence limits for the parameter estimates.

Default	false

depVars={{responsevar-1} <, {responsevar-2}, ...>}

specifies one or more variables to use as response variables in the model. Not all models support more than one response variable.

Aliases	depVar
Aliases	target

name="variable-name"

names the response variable.

effects={{effect-1} <, {effect-2}, ...>}

For more information, see Introduction (Specifying Linear Models for SAS Viya Analytical Actions).

The effect value can be one or more of the following:

interaction="BAR" | "CROSS" | "NONE"

specifies the type of interaction for the variables.

Alias	interact
Default	NONE

maxInteract=integer

eliminates interaction effects whose order is higher than the specified integer value when used in conjunction with the BAR interaction.

nest={"string-1" <, "string-2", ...>}

* vars={"string-1" <, "string-2", ...>}

specifies the variables to use in defining a term of the effect. You must specify at least one variable.

entry="variable-name"

specifies the entry variable.

include=integer | {{effect-1} <, {effect-2}, ...>}

The effect value is specified as follows:

interaction="BAR" | "CROSS" | "NONE"

specifies the type of interaction for the variables.

Alias	interact
Default	NONE

maxInteract=integer

eliminates interaction effects whose order is higher than the specified integer value when used in conjunction with the BAR interaction.

nest={"string-1" <, "string-2", ...>}

* vars={"string-1" <, "string-2", ...>}

specifies the variables to use in defining a term of the effect. You must specify at least one variable.

informative=true | false

For more information, see Informative Missingness (Shared Concepts).

Default	false

noint=true | false

when set to True, does not include the intercept term in the model.

Default	false

ridge={double-1 <, double-2, ...>}

specifies the ridge constant values for ridge regression.

ss3=true | false

when set to True, performs a model analysis of variance based on type III sums of squares.

Default	false

start=integer | {{effect-1} <, {effect-2}, ...>}

The effect value is specified as follows:

interaction="BAR" | "CROSS" | "NONE"

specifies the type of interaction for the variables.

Alias	interact
Default	NONE

maxInteract=integer

eliminates interaction effects whose order is higher than the specified integer value when used in conjunction with the BAR interaction.

nest={"string-1" <, "string-2", ...>}

* vars={"string-1" <, "string-2", ...>}

specifies the variables to use in defining a term of the effect. You must specify at least one variable.

stb=true | false

Default	false

tol=true | false

Default	false

vif=true | false

when set to True, produces variance inflation factors with the parameter estimates. Variance inflation is the reciprocal of tolerance.

Default	false

xpx=true | false

Crossproducts

Default	false

xpxScaled=true | false

Scaled Crossproducts

Default	false

xpxUnscaled=true | false

Unscaled Crossproducts

Default	false

multimember={{multimember-1} <, {multimember-2}, ...>}

For more information, see Multimember Effects (Shared Concepts).

For more information about specifying the multimember parameter, see the common multimember parameter (Appendix A: Common Parameters).

nClassLevelsPrint=integer

limits the display of class levels. The value 0 suppresses all levels.

Minimum value	0

nominals={{casinvardesc-1} <, {casinvardesc-2}, ...>}

specifies nominal variables to use for analysis.

For more information about specifying the nominals parameter, see the common casinvardesc parameter (Appendix A: Common Parameters).

Alias	nominal

output={glmOutputStatement}

creates a table on the server that contains observationwise statistics, which are computed after fitting the model.

For more information about the available statistics, see Predicted Values and Regression Diagnostics (GENSELECT Procedure in SAS Visual Statistics: Procedures).

For more information, see OUTPUT Statement (GENSELECT Procedure in SAS Visual Statistics: Procedures).

The glmOutputStatement value can be one or more of the following:

* casOut={casouttable}

specifies the settings for an output table.

For more information about specifying the casOut parameter, see the common casouttable (Form 1) parameter (Appendix A: Common Parameters).

cooksD="string"

names the Cook's D influence statistic.

copyVars="ALL" | "ALL_MODEL" | "ALL_NUMERIC" | {"variable-name-1" <, "variable-name-2", ...>}

covRatio="string"

dffits="string"

h="string"

names the leverage of the observation.

lcl="string"

names the lower bound of a confidence interval for an individual prediction.

lclm="string"

names the lower bound of a confidence interval for the expected value of the dependent variable.

likeDist="string"

names the likelihood displacement.

pred="string"

names the predicted value. If you do not specify any output statistics, then by default the predicted value is named Pred.

press="string"

names the ith residual divided by 1 - h, where h is the leverage, and where the model has been refit without the ith observation.

resid="string"

names the residual, calculated as ACTUAL minus PREDICTED.

role="string"

identifies the training, validation, and test roles for the observations.

rStudent="string"

names the studentized residual with the current observation deleted.

stdi="string"

names the standard error of the individual predicted value.

stdp="string"

names the standard error of the mean predicted value.

stdr="string"

names the standard error of the residual.

student="string"

names the studentized residuals, which are the residuals divided by their standard errors.

ucl="string"

names the upper bound of a confidence interval for an individual prediction.

uclm="string"

names the upper bound of a confidence interval for the expected value of the dependent variable.

outputTables={outputTables}

lists the names of results tables to save as CAS tables on the server.

For more information about specifying the outputTables parameter, see the common outputTables parameter (Appendix A: Common Parameters).

Alias	displayOut

parmEstLevDetails="NONE" | "RAW" | "RAW_AND_FORMATTED"

specifies whether to add raw and formatted values of classification variables in the ParameterEstimates table.

Default	RAW

partByFrac={partByFracStatement}

specifies the fractions of the data to be used for validation and testing.

For more information, see partByFrac and partByVar Partitioning Parameters (Shared Concepts).

The partByFracStatement value can be one or more of the following:

seed=integer

specifies the seed to use in the random number generator that is used for partitioning the data.

Default	0

test=double

randomly assigns the specified proportion of observations in the input table to the testing role. The sum of the fractions that are specified in the test and validate parameters must be less than 1.

Range	0–1

validate=double

Alias	valid
Range	0–1

partByVar={partByVarStatement}

names the variable and its values used to partition the data into training, validation, and testing roles.

For more information, see partByFrac and partByVar Partitioning Parameters (Shared Concepts).

Long form	partByVar={name="variable-name"}
Shortcut form	partByVar="variable-name"

The partByVarStatement value can be one or more of the following:

* name="variable-name"

names the variable in the input table whose values are used to assign roles to each observation.

test="string"

specifies the formatted value of the variable that is used to assign observations to the testing role.

train="string"

validate="string"

specifies the formatted value of the variable that is used to assign observations to the validation role.

Alias	valid

polynomial={{polynomial-1} <, {polynomial-2}, ...>}

For more information, see Polynomial Effects (Shared Concepts).

For more information about specifying the polynomial parameter, see the common polynomial parameter (Appendix A: Common Parameters).

Alias	poly

selection={selectionStatement}

specifies the method and options for performing model selection.

For more information, see selection Parameter (Shared Concepts).

Long form	selection={method="BACKWARD" \| "BESTSUBSET" \| "ELASTICNET" \| "FORWARD" \| "FORWARDSWAP" \| "LAR" \| "LASSO" \| "MCP" \| "NONE" \| "SCAD" \| "STEPWISE"}
Shortcut form	selection="BACKWARD" \| "BESTSUBSET" \| "ELASTICNET" \| "FORWARD" \| "FORWARDSWAP" \| "LAR" \| "LASSO" \| "MCP" \| "NONE" \| "SCAD" \| "STEPWISE"

The selectionStatement value can be one or more of the following:

adaptive=true | false

when set to True, applies adaptive weights to each of the coefficients in the LASSO method.

Default	false

bestSubsetOptions={bestOptions}

specifies options to perform best-subset selection.

The bestOptions value can be one or more of the following:

best=integer

specifies the maximum number of subset models to display.

Minimum value	0

computeBeta=true | false

when set to True, requests estimated regression coefficients for each subset model.

Alias	beta
Default	false

displayAIC=true | false

when set to True, adds Akaike's information criterion to the selection summary.

Alias	aic
Default	false

displayBIC=true | false

when set to True, adds the Bayesian information criterion to the selection summary.

Alias	bic
Default	false

displayGMSEP=true | false

when set to True, adds estimated mean square error of prediction to the selection summary.

Alias	gmsep
Default	false

displayJP=true | false

when set to True, adds final prediction error to the selection summary.

Alias	jp
Default	false

displayMSE=true | false

when set to True, adds mean square error to the selection summary.

Alias	mse
Default	false

displayPC=true | false

when set to True, adds Amemiya's prediction criterion to the selection summary.

Alias	pc
Default	false

displayRMSE=true | false

when set to True, adds root mean square error to the selection summary.

Alias	rmse
Default	false

displaySBC=true | false

when set to True, adds the Schwarz Bayesian criterion to the selection summary.

Alias	sbc
Default	false

displaySP=true | false

when set to True, adds SP to the selection summary.

Alias	sp
Default	false

displaySSE=true | false

when set to True, adds error sum of squares to the selection summary.

Alias	sse
Default	false

sigma=double

specifies the true standard deviation of the error term to use in computing the CP and BIC statistics.

Default	0

candidates=integer | "ALL"

specifies the maximum number of candidates to display at each step of the selection process, when the detail level ALL is specified.

choose="ADJRSQ" | "AIC" | "AICC" | "CP" | "CV" | "DEFAULT" | "NONE" | "PRESS" | "RSQUARE" | "SBC" | "VALIDATE"

specifies the criterion for choosing the model. The specified criterion is evaluated at each step of the selection process, and the model that yields the best value of the criterion is chosen.

For more information, see the discussion of the choose subparameter (Shared Concepts).

competitive=true | false

Default	false

details="ALL" | "NONE" | "STEPS" | "SUMMARY"

specifies the level of detail to produce about the selection process.

For more information, see the description of the details subparameter (Shared Concepts).

Default	SUMMARY

elasticNetOptions={enOptions}

specifies options to use in performing elastic net selection methods.

The enOptions value can be one or more of the following:

absFConv=double

specifies the absolute function difference convergence criterion.

Alias	abstol
Default	1E-08
Minimum value	0

fConv=double

specifies the relative function difference convergence criterion.

Alias	fTol
Minimum value	0

gConv=double

specifies the relative gradient convergence criterion.

Alias	gTol
Minimum value	0

lambda={double-1 <, double-2, ...>}

specifies the regularization parameters in the elastic net selection method.

mixing={double-1 <, double-2, ...>}

specifies the elastic net mixing parameter.

numLambda=integer

specifies the number of regularization parameters in the elastic net selection method.

Alias	nLambda
Default	0
Minimum value	0

rho=double

specifies the scaling factor to use in computing minimum regularization parameter.

Range	(0, 1)

solver="ADMM" | "BFGS" | "LBFGS" | "NLP"

specifies a solver for elastic net selection.

enscale=true | false

when set to True, applies scaling to beta in the elastic net selection method.

Default	false

ensteps=integer

specifies the number of iterations to use in the elastic net selection method.

Default	50

fcpSelectionOptions={fcpOptions}

specifies options to use in performing the folded concave penalized (FCP) selection methods.

The fcpOptions value can be one or more of the following:

alpha=double

specifies the alpha value in the SCAD and MCP selection methods.

Minimum value (exclusive)	0

bigM=double

specifies the big M constant in the mixed integer linear programming (MILP) solver.

Minimum value (exclusive)	0

coefTol=double

specifies the tolerance for truncating estimated coefficients.

Alias	coefficientTolerance
Minimum value (exclusive)	0

intTol=double

specifies the tolerance for integer variables in the mixed integer linear programming (MILP) solver.

Alias	integerTolerance
Minimum value (exclusive)	0

lambda=double

specifies the fixed lambda value in the SCAD and MCP selection methods.

Minimum value (exclusive)	0

lambdaGrid="DEFAULT" | "LINSPACE" | "LOGSPACE"

specifies the lambda searching grid in the SCAD and MCP selection methods.

maxAlpha=double

specifies the upper bound to use in searching for alpha in the SCAD and MCP selection methods.

Minimum value (exclusive)	0

maxIterAlpha=integer

specifies the number of iterations to use in searching for the best alpha value in the SCAD and MCP selection methods.

Minimum value	2

maxIterLambda=integer

specifies the maximum number of iterations to use in searching for the best lambda value in the SCAD and MCP selection methods.

Minimum value	2

maxLambda=double

specifies the maximum lambda value in the SCAD and MCP selection methods.

Minimum value (exclusive)	0

maxTime=double

specifies the time limit allowed for the optimization solver.

Minimum value (exclusive)	0

minAlpha=double

specifies the lower bound to use in searching for alpha in the SCAD and MCP selection methods.

Minimum value (exclusive)	0

minLambda=double

specifies the minimum lambda value in the SCAD and MCP selection methods.

Minimum value (exclusive)	0

scale=true | false

when set to True, applies normalization in computing the crossproducts matrix.

Default	true

solver="DEFAULT" | "MILP" | "NLP"

specifies the solver to use in the SCAD and MCP selection methods.

gamma=double

specifies the exponent of the power transformation that is applied to the parameters in forming the adaptive weights.

Default	1

hierarchy="DEFAULT" | "NONE" | "SINGLE" | "SINGLECLASS"

For more information, see the description of the hierarchy subparameter (Shared Concepts).

Default	DEFAULT

kappa={double-1 <, double-2, ...>}

specifies the coefficients in the relaxed LASSO method.

L2=double

specifies the L2 parameter in the elastic net selection method.

Default	0

L2HIGH=double

specifies the upper bound to use in searching for the L2 parameter in the elastic net selection method.

Alias	maxL2
Default	1

L2LOW=double

specifies the lower bound to use in searching for the L2 parameter in the elastic net selection method.

Alias	minL2
Default	0

lsCoeffs=true | false

Default	false

maxEffects=integer

specifies the maximum number of effects in any model to consider during the selection process. This parameter is ignored for backward selection.

maxSteps=integer

specifies the maximum number of selection steps to perform.

method="BACKWARD" | "BESTSUBSET" | "ELASTICNET" | "FORWARD" | "FORWARDSWAP" | "LAR" | "LASSO" | "MCP" | "NONE" | "SCAD" | "STEPWISE"

specifies the model selection method.

For more information, see Model Selection Methods (Shared Concepts).

Default	STEPWISE

minEffects=integer

specifies the minimum number of effects in any model to consider during backward selection.

orderSelect=true | false

when set to True, shows effects in parameter estimates tables in the order in which they were added to the model.

Default	false

plots=true | false

when set to True, produces coefficientProgression and selectionSummaryForPlots tables that you can use to produce selection diagnostic plots.

For more information about the plots you can create, see Model Selection Plots (Shared Concepts in SAS Visual Statistics: Procedures).

Default	false

relaxed=true | false

when set to True, applies the relaxed LASSO method.

Default	false

select="ADJRSQ" | "AIC" | "AICC" | "CP" | "DEFAULT" | "RSQUARE" | "SBC" | "SL"

specifies the criterion to use in determining the order in which effects enter or leave at each step of the selection method. This parameter does not apply to LAR or LASSO selection.

For more information, see the discussion of the select subparameter (Shared Concepts).

slEntry=double

specifies the significance level for entry when the significance level is used as the select or stop criterion.

Alias	sle
Default	0.05
Range	(0, 1)

slStay=double

specifies the significance level for removal when the significance level is used as the select or stop criterion.

Alias	sls
Default	0.05
Range	(0, 1)

stop="ADJRSQ" | "AIC" | "AICC" | "CP" | "CV" | "DEFAULT" | "NONE" | "PRESS" | "RSQUARE" | "SBC" | "SL" | "VALIDATE"

specifies a criterion that to use for stopping the selection process. If you do not specify a stop criterion, then the criterion that is used to select the model is also used as the stop criterion.

For more information, see the discussion of the stop subparameter (Shared Concepts).

stopHorizon=integer

specifies the number of consecutive steps at which the stop criterion must worsen in order for a local extremum to be detected.

For more information, see the description of the stopHorizon subparameter (Shared Concepts).

Default	3

spline={{spline-1} <, {spline-2}, ...>}

expands variables into spline bases whose form depends on the specified parameters.

For more information, see Spline Effects (Shared Concepts).

For more information about specifying the spline parameter, see the common spline parameter (Appendix A: Common Parameters).

ss3=true | false

when set to True, performs a model analysis of variance based on type III sums of squares.

Default	false

store={casouttable}

stores regression models to a binary large object (BLOB).

For more information about specifying the store parameter, see the common casouttable (Form 1) parameter (Appendix A: Common Parameters).

Alias	savestate

* table={castable}

specifies the input data table.

For more information about specifying the table parameter, see the common castable (Form 1) parameter (Appendix A: Common Parameters).

target="string"

specifies the target variable to use for analysis.

weight="variable-name"

names the numeric variable to use to perform a weighted analysis of the data.

glm Action

Fits linear regression models using the method of least squares.

Python Syntax
Summary: Input and Output Tables
Parameter Descriptions

Python Syntax

results=s.regression.glm(

alpha=double,

attributes=[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>],

byLimit=64-bit-integer,

class_=[{

"countMissing":True | False,

"descending":True | False,

"ignoreMissing":True | False,

"levelizeRaw":True | False,

"maxLev":integer,

"order":"FORMATTED" | "FREQ" | "FREQFORMATTED" | "FREQINTERNAL" | "INTERNAL",

"ref":"FIRST" | "LAST" | double | "string",

"split":True | False,

"vars":["variable-name-1" <, "variable-name-2", ...>]

}<, {...}>],

classGlobalOpts={

"countMissing":True | False,

"descending":True | False,

"ignoreMissing":True | False,

"levelizeRaw":True | False,

"maxLev":integer,

"order":"FORMATTED" | "FREQ" | "FREQFORMATTED" | "FREQINTERNAL" | "INTERNAL",

"ref":"FIRST" | "LAST" | double | "string",

"split":True | False

classLevelsPrint=True | False,

clb=True | False,

code={

"casOut":{

"caslib":"string"

"compress":True | False

"indexVars":["variable-name-1" <, "variable-name-2", ...>]

"label":"string"

"lifetime":64-bit-integer

"maxMemSize":64-bit-integer

"memoryFormat":"DVR" | "INHERIT" | "STANDARD"

"name":"table-name"

"onDemand":True | False

"promote":True | False

"replace":True | False

"replication":integer

"tableRedistUpPolicy":"DEFER" | "NOREDIST" | "REBALANCE"

"threadBlockSize":64-bit-integer

"timeStamp":"string"

"where":["string-1" <, "string-2", ...>]

"comment":True | False,

"fmtWdth":integer,

"indentSize":integer,

"intoCutPt":double,

"iProb":True | False,

"labelId":integer,

"lineSize":integer,

"noTrim":True | False,

"pCatAll":True | False,

"tabForm":True | False

collection=[{

"details":True | False,

"name":"string",

"vars":["variable-name-1" <, "variable-name-2", ...>]

}<, {...}>],

display={

"caseSensitive":True | False,

"exclude":True | False,

"excludeAll":True | False,

"keyIsPath":True | False,

"names":["string-1" <, "string-2", ...>],

"pathType":"LABEL" | "NAME",

"traceNames":True | False

freq="variable-name",

inputs=[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>],

maxParameters=integer,

model={

"addlaststopstep":True | False,

"clb":True | False,

"depVars":[{

"name":"variable-name"

}<, {...}>],

"effects":[{

"interaction":"BAR" | "CROSS" | "NONE",

"maxInteract":integer,

"nest":["string-1" <, "string-2", ...>],

"vars":["string-1" <, "string-2", ...>]

}<, {...}>],

"entry":"variable-name",

"include":integer | [{effect-1} <, {effect-2}, ...>],

"informative":True | False,

"noint":True | False,

"ridge":[double-1 <, double-2, ...>],

"ss3":True | False,

"start":integer | [{effect-1} <, {effect-2}, ...>],

"stb":True | False,

"tol":True | False,

"vif":True | False,

"xpx":True | False,

"xpxScaled":True | False,

"xpxUnscaled":True | False

multimember=[{

"details":True | False,

"name":"string",

"noEffect":True | False,

"stdize":True | False,

"vars":["variable-name-1" <, "variable-name-2", ...>],

"weight":["variable-name-1" <, "variable-name-2", ...>]

}<, {...}>],

nClassLevelsPrint=integer,

nominals=[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>],

output={

"casOut":{

"caslib":"string"

"compress":True | False

"indexVars":["variable-name-1" <, "variable-name-2", ...>]

"label":"string"

"lifetime":64-bit-integer

"maxMemSize":64-bit-integer

"memoryFormat":"DVR" | "INHERIT" | "STANDARD"

"name":"table-name"

"promote":True | False

"replace":True | False

"replication":integer

"tableRedistUpPolicy":"DEFER" | "NOREDIST" | "REBALANCE"

"threadBlockSize":64-bit-integer

"timeStamp":"string"

"where":["string-1" <, "string-2", ...>]

"cooksD":"string",

"copyVars":"ALL" | "ALL_MODEL" | "ALL_NUMERIC" | ["variable-name-1" <, "variable-name-2", ...>],

"covRatio":"string",

"dffits":"string",

"h":"string",

"lcl":"string",

"lclm":"string",

"likeDist":"string",

"pred":"string",

"press":"string",

"resid":"string",

"role":"string",

"rStudent":"string",

"stdi":"string",

"stdp":"string",

"stdr":"string",

"student":"string",

"ucl":"string",

"uclm":"string"

outputTables={

"groupByVarsRaw":True | False,

"includeAll":True | False,

"names":["string-1" <, "string-2", ...>] | {"key-1":{casouttable-1} <, "key-2":{casouttable-2}, ...>},

"repeated":True | False,

"replace":True | False

parmEstLevDetails="NONE" | "RAW" | "RAW_AND_FORMATTED",

partByFrac={

"seed":integer,

"test":double,

"validate":double

partByVar={

"name":"variable-name",

"test":"string",

"train":"string",

"validate":"string"

polynomial=[{

"degree":integer,

"details":True | False,

"labelStyle":{

"expand":True | False

"exponent":"string"

"includeName":True | False

"productSymbol":"NONE" | "string"

"mDegree":integer,

"name":"string",

"noSeparate":True | False,

"standardize":{

"method":"MOMENTS" | "MRANGE" | "WMOMENTS"

"options":"CENTER" | "CENTERSCALE" | "NONE" | "SCALE"

"prefix":"NONE" | "string"

"vars":["variable-name-1" <, "variable-name-2", ...>]

}<, {...}>],

selection={

"adaptive":True | False,

"bestSubsetOptions":{

"best":integer

"computeBeta":True | False

"displayAIC":True | False

"displayBIC":True | False

"displayGMSEP":True | False

"displayJP":True | False

"displayMSE":True | False

"displayPC":True | False

"displayRMSE":True | False

"displaySBC":True | False

"displaySP":True | False

"displaySSE":True | False

"sigma":double

"candidates":integer | "ALL",

"competitive":True | False,

"details":"ALL" | "NONE" | "STEPS" | "SUMMARY",

"elasticNetOptions":{

"absFConv":double

"fConv":double

"gConv":double

"lambda_":[double-1 <, double-2, ...>]

"mixing":[double-1 <, double-2, ...>]

"numLambda":integer

"rho":double

"solver":"ADMM" | "BFGS" | "LBFGS" | "NLP"

"enscale":True | False,

"ensteps":integer,

"fcpSelectionOptions":{

"alpha":double

"bigM":double

"coefTol":double

"intTol":double

"lambda_":double

"lambdaGrid":"DEFAULT" | "LINSPACE" | "LOGSPACE"

"maxAlpha":double

"maxIterAlpha":integer

"maxIterLambda":integer

"maxLambda":double

"maxTime":double

"minAlpha":double

"minLambda":double

"scale":True | False

"solver":"DEFAULT" | "MILP" | "NLP"

"gamma":double,

"hierarchy":"DEFAULT" | "NONE" | "SINGLE" | "SINGLECLASS",

"kappa":[double-1 <, double-2, ...>],

"L2":double,

"L2HIGH":double,

"L2LOW":double,

"lsCoeffs":True | False,

"maxEffects":integer,

"maxSteps":integer,

"minEffects":integer,

"orderSelect":True | False,

"plots":True | False,

"relaxed":True | False,

"select":"ADJRSQ" | "AIC" | "AICC" | "CP" | "DEFAULT" | "RSQUARE" | "SBC" | "SL",

"slEntry":double,

"slStay":double,

"stop":"ADJRSQ" | "AIC" | "AICC" | "CP" | "CV" | "DEFAULT" | "NONE" | "PRESS" | "RSQUARE" | "SBC" | "SL" | "VALIDATE",

"stopHorizon":integer

spline=[{

"basis":"BSPLINE" | "TPF_DEFAULT" | "TPF_NOINT" | "TPF_NOINTANDNOPOWERS" | "TPF_NOPOWERS",

"dataBoundary":True | False,

"degree":integer,

"details":True | False,

"knotMax":double,

"knotMethod":{

"equal":integer

"list":[double-1 <, double-2, ...>]

"listWithBoundary":[double-1 <, double-2, ...>]

"multiscale":{

"endScale":integer

"startScale":integer

}

"rangeFractions":[double-1 <, double-2, ...>]

"knotMin":double,

"name":"string",

"naturalCubic":True | False,

"separate":True | False,

"split":True | False,

"vars":["variable-name-1" <, "variable-name-2", ...>]

}<, {...}>],

ss3=True | False,

store={

"caslib":"string",

"compress":True | False,

"indexVars":["variable-name-1" <, "variable-name-2", ...>],

"label":"string",

"lifetime":64-bit-integer,

"maxMemSize":64-bit-integer,

"memoryFormat":"DVR" | "INHERIT" | "STANDARD",

"name":"table-name",

"promote":True | False,

"replace":True | False,

"replication":integer,

"tableRedistUpPolicy":"DEFER" | "NOREDIST" | "REBALANCE",

"threadBlockSize":64-bit-integer,

"timeStamp":"string",

"where":["string-1" <, "string-2", ...>]

table={

"caslib":"string",

"computedOnDemand":True | False,

"computedVars":[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>],

"computedVarsProgram":"string",

"dataSourceOptions":{"key-1":{any-list-or-data-type-1} <, "key-2":{any-list-or-data-type-2}, ...>},

"groupBy":[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>],

"groupByMode":"NOSORT" | "REDISTRIBUTE",

"importOptions":{"fileType":"ANY" | "AUDIO" | "AUTO" | "BASESAS" | "CSV" | "DELIMITED" | "DOCUMENT" | "DTA" | "ESP" | "EXCEL" | "FMT" | "HDAT" | "IMAGE" | "JMP" | "LASR" | "PARQUET" | "SOUND" | "SPSS" | "VIDEO" | "XLS", fileType-specific-parameters},

"name":"table-name",

"orderBy":[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>],

"singlePass":True | False,

"vars":[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>],

"where":"where-expression",

"whereTable":{

"casLib":"string"

"dataSourceOptions":{adls_noreq-parameters | bigquery-parameters | cas_noreq-parameters | clouddex-parameters | db2-parameters | dnfs-parameters | esp-parameters | fedsvr-parameters | gcs_noreq-parameters | hadoop-parameters | hana-parameters | impala-parameters | informix-parameters | jdbc-parameters | mongodb-parameters | mysql-parameters | odbc-parameters | oracle-parameters | path-parameters | postgres-parameters | redshift-parameters | s3-parameters | sapiq-parameters | sforce-parameters | singlestore_standard-parameters | snowflake-parameters | spark-parameters | spde-parameters | sqlserver-parameters | ss_noreq-parameters | teradata-parameters | vertica-parameters | yellowbrick-parameters}

"name":"table-name"

"vars":[{

"format":"string",

"formattedLength":integer,

"label":"string",

"name":"variable-name",

"nfd":integer,

"nfl":integer

}<, {...}>]

"where":"where-expression"

}

target="string",

weight="variable-name"

)

indicates a required parameter

Summary: Input and Output Tables

If a row includes a subparameter, you can specify the name, caslib, and so on in the subparameter. Otherwise, you can specify the name, caslib, and so on in the parameter.

Parameters for Reading Input Tables
Parameter	Subparameter	Description
required parametertable	—	specifies the input data table.

Parameters for Creating Output Tables
Parameter	Subparameter	Description
code	casOut	writes SAS DATA step code for computing predicted values of the fitted model
output	required parametercasOut	creates a table on the server that contains observationwise statistics, which are computed after fitting the model.
outputTables	names	lists the names of results tables to save as CAS tables on the server.
store	—	stores regression models to a binary large object (BLOB).

Parameter Descriptions

alpha=double

specifies the significance level to use for the construction of all confidence intervals.

Default	0.05
Range	(0, 1)

attributes=[{casinvardesc-1} <, {casinvardesc-2}, ...>]

changes the attributes of variables used in this action. Currently, attributes specified on the inputs and nominals parameter are ignored.

For more information about specifying the attributes parameter, see the common casinvardesc parameter (Appendix A: Common Parameters).

Alias	attribute

byLimit=64-bit-integer

specifies that the analysis not be performed if the number of BY groups exceeds the specified value.

Minimum value	1

class_=[{classStatement-1} <, {classStatement-2}, ...>]

names the classification variables to be used as explanatory variables in the analysis.

For more information about class subparameters, see class Parameter (Shared Concepts).

For more information about specifying the class parameter, see the common classStatement parameter (Appendix A: Common Parameters).

Alias	classVars

classGlobalOpts={classopts}

lists options that apply to all classification variables.

For more information about specifying the classGlobalOpts parameter, see the common classopts parameter (Appendix A: Common Parameters).

classLevelsPrint=True | False

when set to False, suppresses the display of class levels.

Default	True

clb=True | False

when set to True, displays upper and lower confidence limits for the parameter estimates.

Default	False

code={aircodegen}

writes SAS DATA step code for computing predicted values of the fitted model

For more information about specifying the code parameter, see the common aircodegen parameter (Appendix A: Common Parameters).

collection=[{collection-1} <, {collection-2}, ...>]

defines a set of variables that are treated as a single effect that has multiple degrees of freedom.

For more information, see Collection Effects (Shared Concepts).

The collection value can be one or more of the following:

"details":True | False

when set to True, requests a table that shows additional details that are related to this effect.

Default	False

* "name":"string"

specifies the name of the effect.

* "vars":["variable-name-1" <, "variable-name-2", ...>]

display={displayTables}

specifies a list of results tables to send to the client for display.

For more information about display subparameters, see display Parameter (Shared Concepts).

For more information about specifying the display parameter, see the common displayTables parameter (Appendix A: Common Parameters).

freq="variable-name"

names the numeric variable that contains the frequency of occurrence of each observation.

inputs=[{casinvardesc-1} <, {casinvardesc-2}, ...>]

specifies variables to use for analysis.

For more information about specifying the inputs parameter, see the common casinvardesc parameter (Appendix A: Common Parameters).

Alias	input

maxParameters=integer

specifies that models not be fit if the number of parameters exceeds the specified value.

Minimum value	0

model={glmmodel}

names the dependent variable, explanatory effects, and model options.

For information about model specification, see Introduction (Specifying Linear Models for SAS Viya Analytical Actions).

The glmmodel value can be one or more of the following:

"addlaststopstep":True | False

when set to FALSE, ignores the information from the last stop step.

Default	True

"clb":True | False

when set to True, displays upper and lower confidence limits for the parameter estimates.

Default	False

"depVars":[{responsevar-1} <, {responsevar-2}, ...>]

specifies one or more variables to use as response variables in the model. Not all models support more than one response variable.

Aliases	depVar
Aliases	target

"name":"variable-name"

names the response variable.

"effects":[{effect-1} <, {effect-2}, ...>]

For more information, see Introduction (Specifying Linear Models for SAS Viya Analytical Actions).

The effect value can be one or more of the following:

"interaction":"BAR" | "CROSS" | "NONE"

specifies the type of interaction for the variables.

Alias	interact
Default	NONE

"maxInteract":integer

eliminates interaction effects whose order is higher than the specified integer value when used in conjunction with the BAR interaction.

"nest":["string-1" <, "string-2", ...>]

* "vars":["string-1" <, "string-2", ...>]

specifies the variables to use in defining a term of the effect. You must specify at least one variable.

"entry":"variable-name"

specifies the entry variable.

"include":integer | [{effect-1} <, {effect-2}, ...>]

The effect value is specified as follows:

"interaction":"BAR" | "CROSS" | "NONE"

specifies the type of interaction for the variables.

Alias	interact
Default	NONE

"maxInteract":integer

eliminates interaction effects whose order is higher than the specified integer value when used in conjunction with the BAR interaction.

"nest":["string-1" <, "string-2", ...>]

* "vars":["string-1" <, "string-2", ...>]

specifies the variables to use in defining a term of the effect. You must specify at least one variable.

"informative":True | False

For more information, see Informative Missingness (Shared Concepts).

Default	False

"noint":True | False

when set to True, does not include the intercept term in the model.

Default	False

"ridge":[double-1 <, double-2, ...>]

specifies the ridge constant values for ridge regression.

"ss3":True | False

when set to True, performs a model analysis of variance based on type III sums of squares.

Default	False

"start":integer | [{effect-1} <, {effect-2}, ...>]

The effect value is specified as follows:

"interaction":"BAR" | "CROSS" | "NONE"

specifies the type of interaction for the variables.

Alias	interact
Default	NONE

"maxInteract":integer

eliminates interaction effects whose order is higher than the specified integer value when used in conjunction with the BAR interaction.

"nest":["string-1" <, "string-2", ...>]

* "vars":["string-1" <, "string-2", ...>]

specifies the variables to use in defining a term of the effect. You must specify at least one variable.

"stb":True | False

Default	False

"tol":True | False

Default	False

"vif":True | False

when set to True, produces variance inflation factors with the parameter estimates. Variance inflation is the reciprocal of tolerance.

Default	False

"xpx":True | False

Crossproducts

Default	False

"xpxScaled":True | False

Scaled Crossproducts

Default	False

"xpxUnscaled":True | False

Unscaled Crossproducts

Default	False

multimember=[{multimember-1} <, {multimember-2}, ...>]

For more information, see Multimember Effects (Shared Concepts).

For more information about specifying the multimember parameter, see the common multimember parameter (Appendix A: Common Parameters).

nClassLevelsPrint=integer

limits the display of class levels. The value 0 suppresses all levels.

Minimum value	0

nominals=[{casinvardesc-1} <, {casinvardesc-2}, ...>]

specifies nominal variables to use for analysis.

For more information about specifying the nominals parameter, see the common casinvardesc parameter (Appendix A: Common Parameters).

Alias	nominal

output={glmOutputStatement}

creates a table on the server that contains observationwise statistics, which are computed after fitting the model.

For more information about the available statistics, see Predicted Values and Regression Diagnostics (GENSELECT Procedure in SAS Visual Statistics: Procedures).

For more information, see OUTPUT Statement (GENSELECT Procedure in SAS Visual Statistics: Procedures).

The glmOutputStatement value can be one or more of the following:

* "casOut":{casouttable}

specifies the settings for an output table.

For more information about specifying the casOut parameter, see the common casouttable (Form 1) parameter (Appendix A: Common Parameters).

"cooksD":"string"

names the Cook's D influence statistic.

"copyVars":"ALL" | "ALL_MODEL" | "ALL_NUMERIC" | ["variable-name-1" <, "variable-name-2", ...>]

"covRatio":"string"

"dffits":"string"

"h":"string"

names the leverage of the observation.

"lcl":"string"

names the lower bound of a confidence interval for an individual prediction.

"lclm":"string"

names the lower bound of a confidence interval for the expected value of the dependent variable.

"likeDist":"string"

names the likelihood displacement.

"pred":"string"

names the predicted value. If you do not specify any output statistics, then by default the predicted value is named Pred.

"press":"string"

names the ith residual divided by 1 - h, where h is the leverage, and where the model has been refit without the ith observation.

"resid":"string"

names the residual, calculated as ACTUAL minus PREDICTED.

"role":"string"

identifies the training, validation, and test roles for the observations.

"rStudent":"string"

names the studentized residual with the current observation deleted.

"stdi":"string"

names the standard error of the individual predicted value.

"stdp":"string"

names the standard error of the mean predicted value.

"stdr":"string"

names the standard error of the residual.

"student":"string"

names the studentized residuals, which are the residuals divided by their standard errors.

"ucl":"string"

names the upper bound of a confidence interval for an individual prediction.

"uclm":"string"

names the upper bound of a confidence interval for the expected value of the dependent variable.

outputTables={outputTables}

lists the names of results tables to save as CAS tables on the server.

For more information about specifying the outputTables parameter, see the common outputTables parameter (Appendix A: Common Parameters).

Alias	displayOut

parmEstLevDetails="NONE" | "RAW" | "RAW_AND_FORMATTED"

specifies whether to add raw and formatted values of classification variables in the ParameterEstimates table.

Default	RAW

partByFrac={partByFracStatement}

specifies the fractions of the data to be used for validation and testing.

For more information, see partByFrac and partByVar Partitioning Parameters (Shared Concepts).

The partByFracStatement value can be one or more of the following:

"seed":integer

specifies the seed to use in the random number generator that is used for partitioning the data.

Default	0

"test":double

randomly assigns the specified proportion of observations in the input table to the testing role. The sum of the fractions that are specified in the test and validate parameters must be less than 1.

Range	0–1

"validate":double

Alias	valid
Range	0–1

partByVar={partByVarStatement}

names the variable and its values used to partition the data into training, validation, and testing roles.

For more information, see partByFrac and partByVar Partitioning Parameters (Shared Concepts).

Long form	partByVar={"name":"variable-name"}
Shortcut form	partByVar="variable-name"

The partByVarStatement value can be one or more of the following:

* "name":"variable-name"

names the variable in the input table whose values are used to assign roles to each observation.

"test":"string"

specifies the formatted value of the variable that is used to assign observations to the testing role.

"train":"string"

"validate":"string"

specifies the formatted value of the variable that is used to assign observations to the validation role.

Alias	valid

polynomial=[{polynomial-1} <, {polynomial-2}, ...>]

For more information, see Polynomial Effects (Shared Concepts).

For more information about specifying the polynomial parameter, see the common polynomial parameter (Appendix A: Common Parameters).

Alias	poly

selection={selectionStatement}

specifies the method and options for performing model selection.

For more information, see selection Parameter (Shared Concepts).

Long form	selection={"method":"BACKWARD" \| "BESTSUBSET" \| "ELASTICNET" \| "FORWARD" \| "FORWARDSWAP" \| "LAR" \| "LASSO" \| "MCP" \| "NONE" \| "SCAD" \| "STEPWISE"}
Shortcut form	selection="BACKWARD" \| "BESTSUBSET" \| "ELASTICNET" \| "FORWARD" \| "FORWARDSWAP" \| "LAR" \| "LASSO" \| "MCP" \| "NONE" \| "SCAD" \| "STEPWISE"

The selectionStatement value can be one or more of the following:

"adaptive":True | False

when set to True, applies adaptive weights to each of the coefficients in the LASSO method.

Default	False

"bestSubsetOptions":{bestOptions}

specifies options to perform best-subset selection.

The bestOptions value can be one or more of the following:

"best":integer

specifies the maximum number of subset models to display.

Minimum value	0

"computeBeta":True | False

when set to True, requests estimated regression coefficients for each subset model.

Alias	beta
Default	False

"displayAIC":True | False

when set to True, adds Akaike's information criterion to the selection summary.

Alias	aic
Default	False

"displayBIC":True | False

when set to True, adds the Bayesian information criterion to the selection summary.

Alias	bic
Default	False

"displayGMSEP":True | False

when set to True, adds estimated mean square error of prediction to the selection summary.

Alias	gmsep
Default	False

"displayJP":True | False

when set to True, adds final prediction error to the selection summary.

Alias	jp
Default	False

"displayMSE":True | False

when set to True, adds mean square error to the selection summary.

Alias	mse
Default	False

"displayPC":True | False

when set to True, adds Amemiya's prediction criterion to the selection summary.

Alias	pc
Default	False

"displayRMSE":True | False

when set to True, adds root mean square error to the selection summary.

Alias	rmse
Default	False

"displaySBC":True | False

when set to True, adds the Schwarz Bayesian criterion to the selection summary.

Alias	sbc
Default	False

"displaySP":True | False

when set to True, adds SP to the selection summary.

Alias	sp
Default	False

"displaySSE":True | False

when set to True, adds error sum of squares to the selection summary.

Alias	sse
Default	False

"sigma":double

specifies the true standard deviation of the error term to use in computing the CP and BIC statistics.

Default	0

"candidates":integer | "ALL"

specifies the maximum number of candidates to display at each step of the selection process, when the detail level ALL is specified.

"choose":"ADJRSQ" | "AIC" | "AICC" | "CP" | "CV" | "DEFAULT" | "NONE" | "PRESS" | "RSQUARE" | "SBC" | "VALIDATE"

specifies the criterion for choosing the model. The specified criterion is evaluated at each step of the selection process, and the model that yields the best value of the criterion is chosen.

For more information, see the discussion of the choose subparameter (Shared Concepts).

"competitive":True | False

Default	False

"details":"ALL" | "NONE" | "STEPS" | "SUMMARY"

specifies the level of detail to produce about the selection process.

For more information, see the description of the details subparameter (Shared Concepts).

Default	SUMMARY

"elasticNetOptions":{enOptions}

specifies options to use in performing elastic net selection methods.

The enOptions value can be one or more of the following:

"absFConv":double

specifies the absolute function difference convergence criterion.

Alias	abstol
Default	1E-08
Minimum value	0

"fConv":double

specifies the relative function difference convergence criterion.

Alias	fTol
Minimum value	0

"gConv":double

specifies the relative gradient convergence criterion.

Alias	gTol
Minimum value	0

"lambda_":[double-1 <, double-2, ...>]

specifies the regularization parameters in the elastic net selection method.

"mixing":[double-1 <, double-2, ...>]

specifies the elastic net mixing parameter.

"numLambda":integer

specifies the number of regularization parameters in the elastic net selection method.

Alias	nLambda
Default	0
Minimum value	0

"rho":double

specifies the scaling factor to use in computing minimum regularization parameter.

Range	(0, 1)

"solver":"ADMM" | "BFGS" | "LBFGS" | "NLP"

specifies a solver for elastic net selection.

"enscale":True | False

when set to True, applies scaling to beta in the elastic net selection method.

Default	False

"ensteps":integer

specifies the number of iterations to use in the elastic net selection method.

Default	50

"fcpSelectionOptions":{fcpOptions}

specifies options to use in performing the folded concave penalized (FCP) selection methods.

The fcpOptions value can be one or more of the following:

"alpha":double

specifies the alpha value in the SCAD and MCP selection methods.

Minimum value (exclusive)	0

"bigM":double

specifies the big M constant in the mixed integer linear programming (MILP) solver.

Minimum value (exclusive)	0

"coefTol":double

specifies the tolerance for truncating estimated coefficients.

Alias	coefficientTolerance
Minimum value (exclusive)	0

"intTol":double

specifies the tolerance for integer variables in the mixed integer linear programming (MILP) solver.

Alias	integerTolerance
Minimum value (exclusive)	0

"lambda_":double

specifies the fixed lambda value in the SCAD and MCP selection methods.

Minimum value (exclusive)	0

"lambdaGrid":"DEFAULT" | "LINSPACE" | "LOGSPACE"

specifies the lambda searching grid in the SCAD and MCP selection methods.

"maxAlpha":double

specifies the upper bound to use in searching for alpha in the SCAD and MCP selection methods.

Minimum value (exclusive)	0

"maxIterAlpha":integer

specifies the number of iterations to use in searching for the best alpha value in the SCAD and MCP selection methods.

Minimum value	2

"maxIterLambda":integer

specifies the maximum number of iterations to use in searching for the best lambda value in the SCAD and MCP selection methods.

Minimum value	2

"maxLambda":double

specifies the maximum lambda value in the SCAD and MCP selection methods.

Minimum value (exclusive)	0

"maxTime":double

specifies the time limit allowed for the optimization solver.

Minimum value (exclusive)	0

"minAlpha":double

specifies the lower bound to use in searching for alpha in the SCAD and MCP selection methods.

Minimum value (exclusive)	0

"minLambda":double

specifies the minimum lambda value in the SCAD and MCP selection methods.

Minimum value (exclusive)	0

"scale":True | False

when set to True, applies normalization in computing the crossproducts matrix.

Default	True

"solver":"DEFAULT" | "MILP" | "NLP"

specifies the solver to use in the SCAD and MCP selection methods.

"gamma":double

specifies the exponent of the power transformation that is applied to the parameters in forming the adaptive weights.

Default	1

"hierarchy":"DEFAULT" | "NONE" | "SINGLE" | "SINGLECLASS"

For more information, see the description of the hierarchy subparameter (Shared Concepts).

Default	DEFAULT

"kappa":[double-1 <, double-2, ...>]

specifies the coefficients in the relaxed LASSO method.

"L2":double

specifies the L2 parameter in the elastic net selection method.

Default	0

"L2HIGH":double

specifies the upper bound to use in searching for the L2 parameter in the elastic net selection method.

Alias	maxL2
Default	1

"L2LOW":double

specifies the lower bound to use in searching for the L2 parameter in the elastic net selection method.

Alias	minL2
Default	0

"lsCoeffs":True | False

Default	False

"maxEffects":integer

specifies the maximum number of effects in any model to consider during the selection process. This parameter is ignored for backward selection.

"maxSteps":integer

specifies the maximum number of selection steps to perform.

"method":"BACKWARD" | "BESTSUBSET" | "ELASTICNET" | "FORWARD" | "FORWARDSWAP" | "LAR" | "LASSO" | "MCP" | "NONE" | "SCAD" | "STEPWISE"

specifies the model selection method.

For more information, see Model Selection Methods (Shared Concepts).

Default	STEPWISE

"minEffects":integer

specifies the minimum number of effects in any model to consider during backward selection.

"orderSelect":True | False

when set to True, shows effects in parameter estimates tables in the order in which they were added to the model.

Default	False

"plots":True | False

when set to True, produces coefficientProgression and selectionSummaryForPlots tables that you can use to produce selection diagnostic plots.

For more information about the plots you can create, see Model Selection Plots (Shared Concepts in SAS Visual Statistics: Procedures).

Default	False

"relaxed":True | False

when set to True, applies the relaxed LASSO method.

Default	False

"select":"ADJRSQ" | "AIC" | "AICC" | "CP" | "DEFAULT" | "RSQUARE" | "SBC" | "SL"

specifies the criterion to use in determining the order in which effects enter or leave at each step of the selection method. This parameter does not apply to LAR or LASSO selection.

For more information, see the discussion of the select subparameter (Shared Concepts).

"slEntry":double

specifies the significance level for entry when the significance level is used as the select or stop criterion.

Alias	sle
Default	0.05
Range	(0, 1)

"slStay":double

specifies the significance level for removal when the significance level is used as the select or stop criterion.

Alias	sls
Default	0.05
Range	(0, 1)

"stop":"ADJRSQ" | "AIC" | "AICC" | "CP" | "CV" | "DEFAULT" | "NONE" | "PRESS" | "RSQUARE" | "SBC" | "SL" | "VALIDATE"

specifies a criterion that to use for stopping the selection process. If you do not specify a stop criterion, then the criterion that is used to select the model is also used as the stop criterion.

For more information, see the discussion of the stop subparameter (Shared Concepts).

"stopHorizon":integer

specifies the number of consecutive steps at which the stop criterion must worsen in order for a local extremum to be detected.

For more information, see the description of the stopHorizon subparameter (Shared Concepts).

Default	3

spline=[{spline-1} <, {spline-2}, ...>]

expands variables into spline bases whose form depends on the specified parameters.

For more information, see Spline Effects (Shared Concepts).

For more information about specifying the spline parameter, see the common spline parameter (Appendix A: Common Parameters).

ss3=True | False

when set to True, performs a model analysis of variance based on type III sums of squares.

Default	False

store={casouttable}

stores regression models to a binary large object (BLOB).

For more information about specifying the store parameter, see the common casouttable (Form 1) parameter (Appendix A: Common Parameters).

Alias	savestate

* table={castable}

specifies the input data table.

For more information about specifying the table parameter, see the common castable (Form 1) parameter (Appendix A: Common Parameters).

target="string"

specifies the target variable to use for analysis.

weight="variable-name"

names the numeric variable to use to perform a weighted analysis of the data.

glm Action

Fits linear regression models using the method of least squares.

R Syntax
Summary: Input and Output Tables
Parameter Descriptions

R Syntax

results <– cas.regression.glm(s,

alpha=double,

attributes=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>),

byLimit=64-bit-integer,

class=list( list(

countMissing=TRUE | FALSE,

descending=TRUE | FALSE,

ignoreMissing=TRUE | FALSE,

levelizeRaw=TRUE | FALSE,

maxLev=integer,

order="FORMATTED" | "FREQ" | "FREQFORMATTED" | "FREQINTERNAL" | "INTERNAL",

ref="FIRST" | "LAST" | double | "string",

split=TRUE | FALSE,

vars=list("variable-name-1" <, "variable-name-2", ...>)

) <, list(...)>),

classGlobalOpts=list(

countMissing=TRUE | FALSE,

descending=TRUE | FALSE,

ignoreMissing=TRUE | FALSE,

levelizeRaw=TRUE | FALSE,

maxLev=integer,

order="FORMATTED" | "FREQ" | "FREQFORMATTED" | "FREQINTERNAL" | "INTERNAL",

ref="FIRST" | "LAST" | double | "string",

split=TRUE | FALSE

classLevelsPrint=TRUE | FALSE,

clb=TRUE | FALSE,

code=list(

casOut=list(

caslib="string"

compress=TRUE | FALSE

indexVars=list("variable-name-1" <, "variable-name-2", ...>)

label="string"

lifetime=64-bit-integer

maxMemSize=64-bit-integer

memoryFormat="DVR" | "INHERIT" | "STANDARD"

name="table-name"

onDemand=TRUE | FALSE

promote=TRUE | FALSE

replace=TRUE | FALSE

replication=integer

tableRedistUpPolicy="DEFER" | "NOREDIST" | "REBALANCE"

threadBlockSize=64-bit-integer

timeStamp="string"

where=list("string-1" <, "string-2", ...>)

comment=TRUE | FALSE,

fmtWdth=integer,

indentSize=integer,

intoCutPt=double,

iProb=TRUE | FALSE,

labelId=integer,

lineSize=integer,

noTrim=TRUE | FALSE,

pCatAll=TRUE | FALSE,

tabForm=TRUE | FALSE

collection=list( list(

details=TRUE | FALSE,

name="string",

vars=list("variable-name-1" <, "variable-name-2", ...>)

) <, list(...)>),

display=list(

caseSensitive=TRUE | FALSE,

exclude=TRUE | FALSE,

excludeAll=TRUE | FALSE,

keyIsPath=TRUE | FALSE,

names=list("string-1" <, "string-2", ...>),

pathType="LABEL" | "NAME",

traceNames=TRUE | FALSE

freq="variable-name",

inputs=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>),

maxParameters=integer,

model=list(

addlaststopstep=TRUE | FALSE,

clb=TRUE | FALSE,

depVars=list( list(

name="variable-name"

) <, list(...)>),

effects=list( list(

interaction="BAR" | "CROSS" | "NONE",

maxInteract=integer,

nest=list("string-1" <, "string-2", ...>),

vars=list("string-1" <, "string-2", ...>)

) <, list(...)>),

entry="variable-name",

include=integer | list( list(effect-1) <, list(effect-2), ...>),

informative=TRUE | FALSE,

noint=TRUE | FALSE,

ridge=list(double-1 <, double-2, ...>),

ss3=TRUE | FALSE,

start=integer | list( list(effect-1) <, list(effect-2), ...>),

stb=TRUE | FALSE,

tol=TRUE | FALSE,

vif=TRUE | FALSE,

xpx=TRUE | FALSE,

xpxScaled=TRUE | FALSE,

xpxUnscaled=TRUE | FALSE

multimember=list( list(

details=TRUE | FALSE,

name="string",

noEffect=TRUE | FALSE,

stdize=TRUE | FALSE,

vars=list("variable-name-1" <, "variable-name-2", ...>),

weight=list("variable-name-1" <, "variable-name-2", ...>)

) <, list(...)>),

nClassLevelsPrint=integer,

nominals=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>),

output=list(

casOut=list(

caslib="string"

compress=TRUE | FALSE

indexVars=list("variable-name-1" <, "variable-name-2", ...>)

label="string"

lifetime=64-bit-integer

maxMemSize=64-bit-integer

memoryFormat="DVR" | "INHERIT" | "STANDARD"

name="table-name"

promote=TRUE | FALSE

replace=TRUE | FALSE

replication=integer

tableRedistUpPolicy="DEFER" | "NOREDIST" | "REBALANCE"

threadBlockSize=64-bit-integer

timeStamp="string"

where=list("string-1" <, "string-2", ...>)

cooksD="string",

copyVars="ALL" | "ALL_MODEL" | "ALL_NUMERIC" | list("variable-name-1" <, "variable-name-2", ...>),

covRatio="string",

dffits="string",

h="string",

lcl="string",

lclm="string",

likeDist="string",

pred="string",

press="string",

resid="string",

role="string",

rStudent="string",

stdi="string",

stdp="string",

stdr="string",

student="string",

ucl="string",

uclm="string"

outputTables=list(

groupByVarsRaw=TRUE | FALSE,

includeAll=TRUE | FALSE,

names=list("string-1" <, "string-2", ...>) | list(key-1=list(casouttable-1) <, key-2=list(casouttable-2), ...>),

repeated=TRUE | FALSE,

replace=TRUE | FALSE

parmEstLevDetails="NONE" | "RAW" | "RAW_AND_FORMATTED",

partByFrac=list(

seed=integer,

test=double,

validate=double

partByVar=list(

name="variable-name",

test="string",

train="string",

validate="string"

polynomial=list( list(

degree=integer,

details=TRUE | FALSE,

labelStyle=list(

expand=TRUE | FALSE

exponent="string"

includeName=TRUE | FALSE

productSymbol="NONE" | "string"

mDegree=integer,

name="string",

noSeparate=TRUE | FALSE,

standardize=list(

method="MOMENTS" | "MRANGE" | "WMOMENTS"

options="CENTER" | "CENTERSCALE" | "NONE" | "SCALE"

prefix="NONE" | "string"

vars=list("variable-name-1" <, "variable-name-2", ...>)

) <, list(...)>),

selection=list(

adaptive=TRUE | FALSE,

bestSubsetOptions=list(

best=integer

computeBeta=TRUE | FALSE

displayAIC=TRUE | FALSE

displayBIC=TRUE | FALSE

displayGMSEP=TRUE | FALSE

displayJP=TRUE | FALSE

displayMSE=TRUE | FALSE

displayPC=TRUE | FALSE

displayRMSE=TRUE | FALSE

displaySBC=TRUE | FALSE

displaySP=TRUE | FALSE

displaySSE=TRUE | FALSE

sigma=double

candidates=integer | "ALL",

competitive=TRUE | FALSE,

details="ALL" | "NONE" | "STEPS" | "SUMMARY",

elasticNetOptions=list(

absFConv=double

fConv=double

gConv=double

lambda=list(double-1 <, double-2, ...>)

mixing=list(double-1 <, double-2, ...>)

numLambda=integer

rho=double

solver="ADMM" | "BFGS" | "LBFGS" | "NLP"

enscale=TRUE | FALSE,

ensteps=integer,

fcpSelectionOptions=list(

alpha=double

bigM=double

coefTol=double

intTol=double

lambda=double

lambdaGrid="DEFAULT" | "LINSPACE" | "LOGSPACE"

maxAlpha=double

maxIterAlpha=integer

maxIterLambda=integer

maxLambda=double

maxTime=double

minAlpha=double

minLambda=double

scale=TRUE | FALSE

solver="DEFAULT" | "MILP" | "NLP"

gamma=double,

hierarchy="DEFAULT" | "NONE" | "SINGLE" | "SINGLECLASS",

kappa=list(double-1 <, double-2, ...>),

L2=double,

L2HIGH=double,

L2LOW=double,

lsCoeffs=TRUE | FALSE,

maxEffects=integer,

maxSteps=integer,

minEffects=integer,

orderSelect=TRUE | FALSE,

plots=TRUE | FALSE,

relaxed=TRUE | FALSE,

select="ADJRSQ" | "AIC" | "AICC" | "CP" | "DEFAULT" | "RSQUARE" | "SBC" | "SL",

slEntry=double,

slStay=double,

stop="ADJRSQ" | "AIC" | "AICC" | "CP" | "CV" | "DEFAULT" | "NONE" | "PRESS" | "RSQUARE" | "SBC" | "SL" | "VALIDATE",

stopHorizon=integer

spline=list( list(

basis="BSPLINE" | "TPF_DEFAULT" | "TPF_NOINT" | "TPF_NOINTANDNOPOWERS" | "TPF_NOPOWERS",

dataBoundary=TRUE | FALSE,

degree=integer,

details=TRUE | FALSE,

knotMax=double,

knotMethod=list(

equal=integer

list=list(double-1 <, double-2, ...>)

listWithBoundary=list(double-1 <, double-2, ...>)

multiscale=list(

endScale=integer

startScale=integer

)

rangeFractions=list(double-1 <, double-2, ...>)

knotMin=double,

name="string",

naturalCubic=TRUE | FALSE,

separate=TRUE | FALSE,

split=TRUE | FALSE,

vars=list("variable-name-1" <, "variable-name-2", ...>)

) <, list(...)>),

ss3=TRUE | FALSE,

store=list(

caslib="string",

compress=TRUE | FALSE,

indexVars=list("variable-name-1" <, "variable-name-2", ...>),

label="string",

lifetime=64-bit-integer,

maxMemSize=64-bit-integer,

memoryFormat="DVR" | "INHERIT" | "STANDARD",

name="table-name",

promote=TRUE | FALSE,

replace=TRUE | FALSE,

replication=integer,

tableRedistUpPolicy="DEFER" | "NOREDIST" | "REBALANCE",

threadBlockSize=64-bit-integer,

timeStamp="string",

where=list("string-1" <, "string-2", ...>)

table=list(

caslib="string",

computedOnDemand=TRUE | FALSE,

computedVars=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>),

computedVarsProgram="string",

dataSourceOptions=list(key-1=list(any-list-or-data-type-1) <, key-2=list(any-list-or-data-type-2), ...>),

groupBy=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>),

groupByMode="NOSORT" | "REDISTRIBUTE",

name="table-name",

orderBy=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>),

singlePass=TRUE | FALSE,

vars=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>),

where="where-expression",

whereTable=list(

casLib="string"

name="table-name"

vars=list( list(

format="string",

formattedLength=integer,

label="string",

name="variable-name",

nfd=integer,

nfl=integer

) <, list(...)>)

where="where-expression"

)

target="string",

weight="variable-name"

)

indicates a required parameter

Summary: Input and Output Tables

If a row includes a subparameter, you can specify the name, caslib, and so on in the subparameter. Otherwise, you can specify the name, caslib, and so on in the parameter.

Parameters for Reading Input Tables
Parameter	Subparameter	Description
required parametertable	—	specifies the input data table.

Parameters for Creating Output Tables
Parameter	Subparameter	Description
code	casOut	writes SAS DATA step code for computing predicted values of the fitted model
output	required parametercasOut	creates a table on the server that contains observationwise statistics, which are computed after fitting the model.
outputTables	names	lists the names of results tables to save as CAS tables on the server.
store	—	stores regression models to a binary large object (BLOB).

Parameter Descriptions

alpha=double

specifies the significance level to use for the construction of all confidence intervals.

Default	0.05
Range	(0, 1)

attributes=list( list(casinvardesc-1) <, list(casinvardesc-2), ...>)

changes the attributes of variables used in this action. Currently, attributes specified on the inputs and nominals parameter are ignored.

For more information about specifying the attributes parameter, see the common casinvardesc parameter (Appendix A: Common Parameters).

Alias	attribute

byLimit=64-bit-integer

specifies that the analysis not be performed if the number of BY groups exceeds the specified value.

Minimum value	1

class=list( list(classStatement-1) <, list(classStatement-2), ...>)

names the classification variables to be used as explanatory variables in the analysis.

For more information about class subparameters, see class Parameter (Shared Concepts).

For more information about specifying the class parameter, see the common classStatement parameter (Appendix A: Common Parameters).

Alias	classVars

classGlobalOpts=list(classopts)

lists options that apply to all classification variables.

For more information about specifying the classGlobalOpts parameter, see the common classopts parameter (Appendix A: Common Parameters).

classLevelsPrint=TRUE | FALSE

when set to False, suppresses the display of class levels.

Default	TRUE

clb=TRUE | FALSE

when set to True, displays upper and lower confidence limits for the parameter estimates.

Default	FALSE

code=list(aircodegen)

writes SAS DATA step code for computing predicted values of the fitted model

For more information about specifying the code parameter, see the common aircodegen parameter (Appendix A: Common Parameters).

collection=list( list(collection-1) <, list(collection-2), ...>)

defines a set of variables that are treated as a single effect that has multiple degrees of freedom.

For more information, see Collection Effects (Shared Concepts).

The collection value can be one or more of the following:

details=TRUE | FALSE

when set to True, requests a table that shows additional details that are related to this effect.

Default	FALSE

* name="string"

specifies the name of the effect.

* vars=list("variable-name-1" <, "variable-name-2", ...>)

display=list(displayTables)

specifies a list of results tables to send to the client for display.

For more information about display subparameters, see display Parameter (Shared Concepts).

For more information about specifying the display parameter, see the common displayTables parameter (Appendix A: Common Parameters).

freq="variable-name"

names the numeric variable that contains the frequency of occurrence of each observation.

inputs=list( list(casinvardesc-1) <, list(casinvardesc-2), ...>)

specifies variables to use for analysis.

For more information about specifying the inputs parameter, see the common casinvardesc parameter (Appendix A: Common Parameters).

Alias	input

maxParameters=integer

specifies that models not be fit if the number of parameters exceeds the specified value.

Minimum value	0

model=list(glmmodel)

names the dependent variable, explanatory effects, and model options.

For information about model specification, see Introduction (Specifying Linear Models for SAS Viya Analytical Actions).

The glmmodel value can be one or more of the following:

addlaststopstep=TRUE | FALSE

when set to FALSE, ignores the information from the last stop step.

Default	TRUE

clb=TRUE | FALSE

when set to True, displays upper and lower confidence limits for the parameter estimates.

Default	FALSE

depVars=list( list(responsevar-1) <, list(responsevar-2), ...>)

specifies one or more variables to use as response variables in the model. Not all models support more than one response variable.

Aliases	depVar
Aliases	target

name="variable-name"

names the response variable.

effects=list( list(effect-1) <, list(effect-2), ...>)

For more information, see Introduction (Specifying Linear Models for SAS Viya Analytical Actions).

The effect value can be one or more of the following:

interaction="BAR" | "CROSS" | "NONE"

specifies the type of interaction for the variables.

Alias	interact
Default	NONE

maxInteract=integer

eliminates interaction effects whose order is higher than the specified integer value when used in conjunction with the BAR interaction.

nest=list("string-1" <, "string-2", ...>)

* vars=list("string-1" <, "string-2", ...>)

specifies the variables to use in defining a term of the effect. You must specify at least one variable.

entry="variable-name"

specifies the entry variable.

include=integer | list( list(effect-1) <, list(effect-2), ...>)

The effect value is specified as follows:

interaction="BAR" | "CROSS" | "NONE"

specifies the type of interaction for the variables.

Alias	interact
Default	NONE

maxInteract=integer

eliminates interaction effects whose order is higher than the specified integer value when used in conjunction with the BAR interaction.

nest=list("string-1" <, "string-2", ...>)

* vars=list("string-1" <, "string-2", ...>)

specifies the variables to use in defining a term of the effect. You must specify at least one variable.

informative=TRUE | FALSE

For more information, see Informative Missingness (Shared Concepts).

Default	FALSE

noint=TRUE | FALSE

when set to True, does not include the intercept term in the model.

Default	FALSE

ridge=list(double-1 <, double-2, ...>)

specifies the ridge constant values for ridge regression.

ss3=TRUE | FALSE

when set to True, performs a model analysis of variance based on type III sums of squares.

Default	FALSE

start=integer | list( list(effect-1) <, list(effect-2), ...>)

The effect value is specified as follows:

interaction="BAR" | "CROSS" | "NONE"

specifies the type of interaction for the variables.

Alias	interact
Default	NONE

maxInteract=integer

eliminates interaction effects whose order is higher than the specified integer value when used in conjunction with the BAR interaction.

nest=list("string-1" <, "string-2", ...>)

* vars=list("string-1" <, "string-2", ...>)

specifies the variables to use in defining a term of the effect. You must specify at least one variable.

stb=TRUE | FALSE

Default	FALSE

tol=TRUE | FALSE

Default	FALSE

vif=TRUE | FALSE

when set to True, produces variance inflation factors with the parameter estimates. Variance inflation is the reciprocal of tolerance.

Default	FALSE

xpx=TRUE | FALSE

Crossproducts

Default	FALSE

xpxScaled=TRUE | FALSE

Scaled Crossproducts

Default	FALSE

xpxUnscaled=TRUE | FALSE

Unscaled Crossproducts

Default	FALSE

multimember=list( list(multimember-1) <, list(multimember-2), ...>)

For more information, see Multimember Effects (Shared Concepts).

For more information about specifying the multimember parameter, see the common multimember parameter (Appendix A: Common Parameters).

nClassLevelsPrint=integer

limits the display of class levels. The value 0 suppresses all levels.

Minimum value	0

nominals=list( list(casinvardesc-1) <, list(casinvardesc-2), ...>)

specifies nominal variables to use for analysis.

For more information about specifying the nominals parameter, see the common casinvardesc parameter (Appendix A: Common Parameters).

Alias	nominal

output=list(glmOutputStatement)

creates a table on the server that contains observationwise statistics, which are computed after fitting the model.

For more information about the available statistics, see Predicted Values and Regression Diagnostics (GENSELECT Procedure in SAS Visual Statistics: Procedures).

For more information, see OUTPUT Statement (GENSELECT Procedure in SAS Visual Statistics: Procedures).

The glmOutputStatement value can be one or more of the following:

* casOut=list(casouttable)

specifies the settings for an output table.

For more information about specifying the casOut parameter, see the common casouttable (Form 1) parameter (Appendix A: Common Parameters).

cooksD="string"

names the Cook's D influence statistic.

copyVars="ALL" | "ALL_MODEL" | "ALL_NUMERIC" | list("variable-name-1" <, "variable-name-2", ...>)

covRatio="string"

dffits="string"

h="string"

names the leverage of the observation.

lcl="string"

names the lower bound of a confidence interval for an individual prediction.

lclm="string"

names the lower bound of a confidence interval for the expected value of the dependent variable.

likeDist="string"

names the likelihood displacement.

pred="string"

names the predicted value. If you do not specify any output statistics, then by default the predicted value is named Pred.

press="string"

names the ith residual divided by 1 - h, where h is the leverage, and where the model has been refit without the ith observation.

resid="string"

names the residual, calculated as ACTUAL minus PREDICTED.

role="string"

identifies the training, validation, and test roles for the observations.

rStudent="string"

names the studentized residual with the current observation deleted.

stdi="string"

names the standard error of the individual predicted value.

stdp="string"

names the standard error of the mean predicted value.

stdr="string"

names the standard error of the residual.

student="string"

names the studentized residuals, which are the residuals divided by their standard errors.

ucl="string"

names the upper bound of a confidence interval for an individual prediction.

uclm="string"

names the upper bound of a confidence interval for the expected value of the dependent variable.

outputTables=list(outputTables)

lists the names of results tables to save as CAS tables on the server.

For more information about specifying the outputTables parameter, see the common outputTables parameter (Appendix A: Common Parameters).

Alias	displayOut

parmEstLevDetails="NONE" | "RAW" | "RAW_AND_FORMATTED"

specifies whether to add raw and formatted values of classification variables in the ParameterEstimates table.

Default	RAW

partByFrac=list(partByFracStatement)

specifies the fractions of the data to be used for validation and testing.

For more information, see partByFrac and partByVar Partitioning Parameters (Shared Concepts).

The partByFracStatement value can be one or more of the following:

seed=integer

specifies the seed to use in the random number generator that is used for partitioning the data.

Default	0

test=double

randomly assigns the specified proportion of observations in the input table to the testing role. The sum of the fractions that are specified in the test and validate parameters must be less than 1.

Range	0–1

validate=double

Alias	valid
Range	0–1

partByVar=list(partByVarStatement)

names the variable and its values used to partition the data into training, validation, and testing roles.

For more information, see partByFrac and partByVar Partitioning Parameters (Shared Concepts).

Long form	partByVar=list(name="variable-name")
Shortcut form	partByVar="variable-name"

The partByVarStatement value can be one or more of the following:

* name="variable-name"

names the variable in the input table whose values are used to assign roles to each observation.

test="string"

specifies the formatted value of the variable that is used to assign observations to the testing role.

train="string"

validate="string"

specifies the formatted value of the variable that is used to assign observations to the validation role.

Alias	valid

polynomial=list( list(polynomial-1) <, list(polynomial-2), ...>)

For more information, see Polynomial Effects (Shared Concepts).

For more information about specifying the polynomial parameter, see the common polynomial parameter (Appendix A: Common Parameters).

Alias	poly

selection=list(selectionStatement)

specifies the method and options for performing model selection.

For more information, see selection Parameter (Shared Concepts).

Long form	selection=list(method="BACKWARD" \| "BESTSUBSET" \| "ELASTICNET" \| "FORWARD" \| "FORWARDSWAP" \| "LAR" \| "LASSO" \| "MCP" \| "NONE" \| "SCAD" \| "STEPWISE")
Shortcut form	selection="BACKWARD" \| "BESTSUBSET" \| "ELASTICNET" \| "FORWARD" \| "FORWARDSWAP" \| "LAR" \| "LASSO" \| "MCP" \| "NONE" \| "SCAD" \| "STEPWISE"

The selectionStatement value can be one or more of the following:

adaptive=TRUE | FALSE

when set to True, applies adaptive weights to each of the coefficients in the LASSO method.

Default	FALSE

bestSubsetOptions=list(bestOptions)

specifies options to perform best-subset selection.

The bestOptions value can be one or more of the following:

best=integer

specifies the maximum number of subset models to display.

Minimum value	0

computeBeta=TRUE | FALSE

when set to True, requests estimated regression coefficients for each subset model.

Alias	beta
Default	FALSE

displayAIC=TRUE | FALSE

when set to True, adds Akaike's information criterion to the selection summary.

Alias	aic
Default	FALSE

displayBIC=TRUE | FALSE

when set to True, adds the Bayesian information criterion to the selection summary.

Alias	bic
Default	FALSE

displayGMSEP=TRUE | FALSE

when set to True, adds estimated mean square error of prediction to the selection summary.

Alias	gmsep
Default	FALSE

displayJP=TRUE | FALSE

when set to True, adds final prediction error to the selection summary.

Alias	jp
Default	FALSE

displayMSE=TRUE | FALSE

when set to True, adds mean square error to the selection summary.

Alias	mse
Default	FALSE

displayPC=TRUE | FALSE

when set to True, adds Amemiya's prediction criterion to the selection summary.

Alias	pc
Default	FALSE

displayRMSE=TRUE | FALSE

when set to True, adds root mean square error to the selection summary.

Alias	rmse
Default	FALSE

displaySBC=TRUE | FALSE

when set to True, adds the Schwarz Bayesian criterion to the selection summary.

Alias	sbc
Default	FALSE

displaySP=TRUE | FALSE

when set to True, adds SP to the selection summary.

Alias	sp
Default	FALSE

displaySSE=TRUE | FALSE

when set to True, adds error sum of squares to the selection summary.

Alias	sse
Default	FALSE

sigma=double

specifies the true standard deviation of the error term to use in computing the CP and BIC statistics.

Default	0

candidates=integer | "ALL"

specifies the maximum number of candidates to display at each step of the selection process, when the detail level ALL is specified.

choose="ADJRSQ" | "AIC" | "AICC" | "CP" | "CV" | "DEFAULT" | "NONE" | "PRESS" | "RSQUARE" | "SBC" | "VALIDATE"

specifies the criterion for choosing the model. The specified criterion is evaluated at each step of the selection process, and the model that yields the best value of the criterion is chosen.

For more information, see the discussion of the choose subparameter (Shared Concepts).

competitive=TRUE | FALSE

Default	FALSE

details="ALL" | "NONE" | "STEPS" | "SUMMARY"

specifies the level of detail to produce about the selection process.

For more information, see the description of the details subparameter (Shared Concepts).

Default	SUMMARY

elasticNetOptions=list(enOptions)

specifies options to use in performing elastic net selection methods.

The enOptions value can be one or more of the following:

absFConv=double

specifies the absolute function difference convergence criterion.

Alias	abstol
Default	1E-08
Minimum value	0

fConv=double

specifies the relative function difference convergence criterion.

Alias	fTol
Minimum value	0

gConv=double

specifies the relative gradient convergence criterion.

Alias	gTol
Minimum value	0

lambda=list(double-1 <, double-2, ...>)

specifies the regularization parameters in the elastic net selection method.

mixing=list(double-1 <, double-2, ...>)

specifies the elastic net mixing parameter.

numLambda=integer

specifies the number of regularization parameters in the elastic net selection method.

Alias	nLambda
Default	0
Minimum value	0

rho=double

specifies the scaling factor to use in computing minimum regularization parameter.

Range	(0, 1)

solver="ADMM" | "BFGS" | "LBFGS" | "NLP"

specifies a solver for elastic net selection.

enscale=TRUE | FALSE

when set to True, applies scaling to beta in the elastic net selection method.

Default	FALSE

ensteps=integer

specifies the number of iterations to use in the elastic net selection method.

Default	50

fcpSelectionOptions=list(fcpOptions)

specifies options to use in performing the folded concave penalized (FCP) selection methods.

The fcpOptions value can be one or more of the following:

alpha=double

specifies the alpha value in the SCAD and MCP selection methods.

Minimum value (exclusive)	0

bigM=double

specifies the big M constant in the mixed integer linear programming (MILP) solver.

Minimum value (exclusive)	0

coefTol=double

specifies the tolerance for truncating estimated coefficients.

Alias	coefficientTolerance
Minimum value (exclusive)	0

intTol=double

specifies the tolerance for integer variables in the mixed integer linear programming (MILP) solver.

Alias	integerTolerance
Minimum value (exclusive)	0

lambda=double

specifies the fixed lambda value in the SCAD and MCP selection methods.

Minimum value (exclusive)	0

lambdaGrid="DEFAULT" | "LINSPACE" | "LOGSPACE"

specifies the lambda searching grid in the SCAD and MCP selection methods.

maxAlpha=double

specifies the upper bound to use in searching for alpha in the SCAD and MCP selection methods.

Minimum value (exclusive)	0

maxIterAlpha=integer

specifies the number of iterations to use in searching for the best alpha value in the SCAD and MCP selection methods.

Minimum value	2

maxIterLambda=integer

specifies the maximum number of iterations to use in searching for the best lambda value in the SCAD and MCP selection methods.

Minimum value	2

maxLambda=double

specifies the maximum lambda value in the SCAD and MCP selection methods.

Minimum value (exclusive)	0

maxTime=double

specifies the time limit allowed for the optimization solver.

Minimum value (exclusive)	0

minAlpha=double

specifies the lower bound to use in searching for alpha in the SCAD and MCP selection methods.

Minimum value (exclusive)	0

minLambda=double

specifies the minimum lambda value in the SCAD and MCP selection methods.

Minimum value (exclusive)	0

scale=TRUE | FALSE

when set to True, applies normalization in computing the crossproducts matrix.

Default	TRUE

solver="DEFAULT" | "MILP" | "NLP"

specifies the solver to use in the SCAD and MCP selection methods.

gamma=double

specifies the exponent of the power transformation that is applied to the parameters in forming the adaptive weights.

Default	1

hierarchy="DEFAULT" | "NONE" | "SINGLE" | "SINGLECLASS"

For more information, see the description of the hierarchy subparameter (Shared Concepts).

Default	DEFAULT

kappa=list(double-1 <, double-2, ...>)

specifies the coefficients in the relaxed LASSO method.

L2=double

specifies the L2 parameter in the elastic net selection method.

Default	0

L2HIGH=double

specifies the upper bound to use in searching for the L2 parameter in the elastic net selection method.

Alias	maxL2
Default	1

L2LOW=double

specifies the lower bound to use in searching for the L2 parameter in the elastic net selection method.

Alias	minL2
Default	0

lsCoeffs=TRUE | FALSE

Default	FALSE

maxEffects=integer

specifies the maximum number of effects in any model to consider during the selection process. This parameter is ignored for backward selection.

maxSteps=integer

specifies the maximum number of selection steps to perform.

method="BACKWARD" | "BESTSUBSET" | "ELASTICNET" | "FORWARD" | "FORWARDSWAP" | "LAR" | "LASSO" | "MCP" | "NONE" | "SCAD" | "STEPWISE"

specifies the model selection method.

For more information, see Model Selection Methods (Shared Concepts).

Default	STEPWISE

minEffects=integer

specifies the minimum number of effects in any model to consider during backward selection.

orderSelect=TRUE | FALSE

when set to True, shows effects in parameter estimates tables in the order in which they were added to the model.

Default	FALSE

plots=TRUE | FALSE

when set to True, produces coefficientProgression and selectionSummaryForPlots tables that you can use to produce selection diagnostic plots.

For more information about the plots you can create, see Model Selection Plots (Shared Concepts in SAS Visual Statistics: Procedures).

Default	FALSE

relaxed=TRUE | FALSE

when set to True, applies the relaxed LASSO method.

Default	FALSE

select="ADJRSQ" | "AIC" | "AICC" | "CP" | "DEFAULT" | "RSQUARE" | "SBC" | "SL"

specifies the criterion to use in determining the order in which effects enter or leave at each step of the selection method. This parameter does not apply to LAR or LASSO selection.

For more information, see the discussion of the select subparameter (Shared Concepts).

slEntry=double

specifies the significance level for entry when the significance level is used as the select or stop criterion.

Alias	sle
Default	0.05
Range	(0, 1)

slStay=double

specifies the significance level for removal when the significance level is used as the select or stop criterion.

Alias	sls
Default	0.05
Range	(0, 1)

stop="ADJRSQ" | "AIC" | "AICC" | "CP" | "CV" | "DEFAULT" | "NONE" | "PRESS" | "RSQUARE" | "SBC" | "SL" | "VALIDATE"

specifies a criterion that to use for stopping the selection process. If you do not specify a stop criterion, then the criterion that is used to select the model is also used as the stop criterion.

For more information, see the discussion of the stop subparameter (Shared Concepts).

stopHorizon=integer

specifies the number of consecutive steps at which the stop criterion must worsen in order for a local extremum to be detected.

For more information, see the description of the stopHorizon subparameter (Shared Concepts).

Default	3

spline=list( list(spline-1) <, list(spline-2), ...>)

expands variables into spline bases whose form depends on the specified parameters.

For more information, see Spline Effects (Shared Concepts).

For more information about specifying the spline parameter, see the common spline parameter (Appendix A: Common Parameters).

ss3=TRUE | FALSE

when set to True, performs a model analysis of variance based on type III sums of squares.

Default	FALSE

store=list(casouttable)

stores regression models to a binary large object (BLOB).

For more information about specifying the store parameter, see the common casouttable (Form 1) parameter (Appendix A: Common Parameters).

Alias	savestate

* table=list(castable)

specifies the input data table.

For more information about specifying the table parameter, see the common castable (Form 1) parameter (Appendix A: Common Parameters).

target="string"

specifies the target variable to use for analysis.

weight="variable-name"

names the numeric variable to use to perform a weighted analysis of the data.

Last updated: March 05, 2026