Common Parameter: spline

CASL Syntax

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,
required parameter name="string",
naturalCubic=TRUE | FALSE,
separate=TRUE | FALSE,
split=TRUE | FALSE,
required parameter vars={"variable-name-1" <, "variable-name-2", ...>}
}, {...}}

Parameter Descriptions

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

specifies the basis for the spline expansion.

For more information, see Splines and Spline Bases (Shared Concepts).

Default BSPLINE
BSPLINE

specifies a B-spline basis for the spline expansion.

TPF_DEFAULT

specifies a truncated power function basis for the spline expansion.

TPF_NOINT

excludes the intercept column when the basis is a truncated power function.

TPF_NOINTANDNOPOWERS

is equivalent to specifying both TPF_NOINT and TPF_NOPOWERS.

TPF_NOPOWERS

excludes the intercept column and polynomial columns when the basis is a truncated power function.

dataBoundary=TRUE | FALSE

when set to True, uses the extremes of the data as boundary knots in building a B-spline basis.

Default FALSE
degree=integer

specifies the degree of the spline transformation.

Default 3
Minimum value 0
details=TRUE | FALSE

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

Default FALSE
knotMax=double

equally spaces the right-side boundary knots for each variable, starting at the maximum of the variable and ending at the specified value.

knotMethod={knotmethodlist}

specifies how to construct the knots for spline effects.

For more information, see the knotMethod subparameter in the spline parameter (Shared Concepts).

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

equal=integer

specifies the number of equally spaced knots to be positioned between the extremes of the data. For a B-spline basis, any necessary boundary knots continue to be equally spaced unless the dataBoundary parameter is set to True. If no knotMethod is specified, the default of the equal parameter is 3.

Default 3
list={double-1 <, double-2, ...>}

specifies the list of internal knots to be used in forming the spline basis columns. For a B-spline basis, the data extremes are used as boundary knots.

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

specifies the list of all knots to be used in forming the spline basis columns. When you use a truncated power function basis, this list is interpreted as the list of internal knots. When you use a B-spline basis of degree d, then the first d entries are used as left-side boundary knots and the last MAX(d,1) entries in the list are used as right-side boundary knots.

multiscale={multiscalelist}

generates multiple B-spline bases that correspond to sets with an increasing number of internal knots. For scale i, the spline basis corresponds to 2 to the power of i equally spaced internal knots. By default, the bases for scales 0 to 7 are generated. A separate spline effect is generated for each effect.

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

endScale=integer

specifies the ending scale for a multiscale spline effect.

Default 7
startScale=integer

specifies the starting scale for a multiscale spline effect.

Default 0
rangeFractions={double-1 <, double-2, ...>}

specifies a list of fractions. For each variable that is specified in the spline effect, internal knots are placed at each specified fraction of the ranges of those variables.

knotMin=double

equally spaces the left-side boundary knots for each variable, starting at the specified value and ending at the minimum of the variable.

* name="string"

specifies the name of the effect.

naturalCubic=TRUE | FALSE

when set to True, specifies a natural cubic spline basis for the spline expansion. Natural cubic splines, also known as restricted cubic splines, are cubic splines that are constructed to be linear beyond the extreme knots.

Default FALSE
separate=TRUE | FALSE

when set to True, treats the spline basis for each variable as a separate effect when multiple variables are specified.

For more information, see the separate subparameter in the spline parameter (Shared Concepts).

Default FALSE
split=TRUE | FALSE

when set to True, treats each individual column in the design matrix that corresponds to the spline effect as a separate effect that can enter or leave the model independently.

For more information, see the split subparameter in the spline parameter (Shared Concepts).

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

specifies numeric variables for the spline effect. By default, the spline basis that is generated for each variable is a cubic B-spline basis with three equally spaced knots that are positioned between the minimum and maximum values of that variable.

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

Lua Syntax

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,
required parameter name="string",
naturalCubic=true | false,
separate=true | false,
split=true | false,
required parameter vars={"variable-name-1" <, "variable-name-2", ...>}
}, {...}}

Parameter Descriptions

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

specifies the basis for the spline expansion.

For more information, see Splines and Spline Bases (Shared Concepts).

Default BSPLINE
BSPLINE

specifies a B-spline basis for the spline expansion.

TPF_DEFAULT

specifies a truncated power function basis for the spline expansion.

TPF_NOINT

excludes the intercept column when the basis is a truncated power function.

TPF_NOINTANDNOPOWERS

is equivalent to specifying both TPF_NOINT and TPF_NOPOWERS.

TPF_NOPOWERS

excludes the intercept column and polynomial columns when the basis is a truncated power function.

dataBoundary=true | false

when set to True, uses the extremes of the data as boundary knots in building a B-spline basis.

Default false
degree=integer

specifies the degree of the spline transformation.

Default 3
Minimum value 0
details=true | false

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

Default false
knotMax=double

equally spaces the right-side boundary knots for each variable, starting at the maximum of the variable and ending at the specified value.

knotMethod={knotmethodlist}

specifies how to construct the knots for spline effects.

For more information, see the knotMethod subparameter in the spline parameter (Shared Concepts).

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

equal=integer

specifies the number of equally spaced knots to be positioned between the extremes of the data. For a B-spline basis, any necessary boundary knots continue to be equally spaced unless the dataBoundary parameter is set to True. If no knotMethod is specified, the default of the equal parameter is 3.

Default 3
list={double-1 <, double-2, ...>}

specifies the list of internal knots to be used in forming the spline basis columns. For a B-spline basis, the data extremes are used as boundary knots.

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

specifies the list of all knots to be used in forming the spline basis columns. When you use a truncated power function basis, this list is interpreted as the list of internal knots. When you use a B-spline basis of degree d, then the first d entries are used as left-side boundary knots and the last MAX(d,1) entries in the list are used as right-side boundary knots.

multiscale={multiscalelist}

generates multiple B-spline bases that correspond to sets with an increasing number of internal knots. For scale i, the spline basis corresponds to 2 to the power of i equally spaced internal knots. By default, the bases for scales 0 to 7 are generated. A separate spline effect is generated for each effect.

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

endScale=integer

specifies the ending scale for a multiscale spline effect.

Default 7
startScale=integer

specifies the starting scale for a multiscale spline effect.

Default 0
rangeFractions={double-1 <, double-2, ...>}

specifies a list of fractions. For each variable that is specified in the spline effect, internal knots are placed at each specified fraction of the ranges of those variables.

knotMin=double

equally spaces the left-side boundary knots for each variable, starting at the specified value and ending at the minimum of the variable.

* name="string"

specifies the name of the effect.

naturalCubic=true | false

when set to True, specifies a natural cubic spline basis for the spline expansion. Natural cubic splines, also known as restricted cubic splines, are cubic splines that are constructed to be linear beyond the extreme knots.

Default false
separate=true | false

when set to True, treats the spline basis for each variable as a separate effect when multiple variables are specified.

For more information, see the separate subparameter in the spline parameter (Shared Concepts).

Default false
split=true | false

when set to True, treats each individual column in the design matrix that corresponds to the spline effect as a separate effect that can enter or leave the model independently.

For more information, see the split subparameter in the spline parameter (Shared Concepts).

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

specifies numeric variables for the spline effect. By default, the spline basis that is generated for each variable is a cubic B-spline basis with three equally spaced knots that are positioned between the minimum and maximum values of that variable.

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

Python Syntax

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,
required parameter "name":"string",
"naturalCubic":True | False,
"separate":True | False,
"split":True | False,
required parameter "vars":["variable-name-1" <, "variable-name-2", ...>]
}<, {...}>]

Parameter Descriptions

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

specifies the basis for the spline expansion.

For more information, see Splines and Spline Bases (Shared Concepts).

Default BSPLINE
BSPLINE

specifies a B-spline basis for the spline expansion.

TPF_DEFAULT

specifies a truncated power function basis for the spline expansion.

TPF_NOINT

excludes the intercept column when the basis is a truncated power function.

TPF_NOINTANDNOPOWERS

is equivalent to specifying both TPF_NOINT and TPF_NOPOWERS.

TPF_NOPOWERS

excludes the intercept column and polynomial columns when the basis is a truncated power function.

"dataBoundary":True | False

when set to True, uses the extremes of the data as boundary knots in building a B-spline basis.

Default False
"degree":integer

specifies the degree of the spline transformation.

Default 3
Minimum value 0
"details":True | False

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

Default False
"knotMax":double

equally spaces the right-side boundary knots for each variable, starting at the maximum of the variable and ending at the specified value.

"knotMethod":{knotmethodlist}

specifies how to construct the knots for spline effects.

For more information, see the knotMethod subparameter in the spline parameter (Shared Concepts).

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

"equal":integer

specifies the number of equally spaced knots to be positioned between the extremes of the data. For a B-spline basis, any necessary boundary knots continue to be equally spaced unless the dataBoundary parameter is set to True. If no knotMethod is specified, the default of the equal parameter is 3.

Default 3
"list":[double-1 <, double-2, ...>]

specifies the list of internal knots to be used in forming the spline basis columns. For a B-spline basis, the data extremes are used as boundary knots.

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

specifies the list of all knots to be used in forming the spline basis columns. When you use a truncated power function basis, this list is interpreted as the list of internal knots. When you use a B-spline basis of degree d, then the first d entries are used as left-side boundary knots and the last MAX(d,1) entries in the list are used as right-side boundary knots.

"multiscale":{multiscalelist}

generates multiple B-spline bases that correspond to sets with an increasing number of internal knots. For scale i, the spline basis corresponds to 2 to the power of i equally spaced internal knots. By default, the bases for scales 0 to 7 are generated. A separate spline effect is generated for each effect.

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

"endScale":integer

specifies the ending scale for a multiscale spline effect.

Default 7
"startScale":integer

specifies the starting scale for a multiscale spline effect.

Default 0
"rangeFractions":[double-1 <, double-2, ...>]

specifies a list of fractions. For each variable that is specified in the spline effect, internal knots are placed at each specified fraction of the ranges of those variables.

"knotMin":double

equally spaces the left-side boundary knots for each variable, starting at the specified value and ending at the minimum of the variable.

* "name":"string"

specifies the name of the effect.

"naturalCubic":True | False

when set to True, specifies a natural cubic spline basis for the spline expansion. Natural cubic splines, also known as restricted cubic splines, are cubic splines that are constructed to be linear beyond the extreme knots.

Default False
"separate":True | False

when set to True, treats the spline basis for each variable as a separate effect when multiple variables are specified.

For more information, see the separate subparameter in the spline parameter (Shared Concepts).

Default False
"split":True | False

when set to True, treats each individual column in the design matrix that corresponds to the spline effect as a separate effect that can enter or leave the model independently.

For more information, see the split subparameter in the spline parameter (Shared Concepts).

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

specifies numeric variables for the spline effect. By default, the spline basis that is generated for each variable is a cubic B-spline basis with three equally spaced knots that are positioned between the minimum and maximum values of that variable.

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

R Syntax

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,
required parameter name="string",
naturalCubic=TRUE | FALSE,
separate=TRUE | FALSE,
split=TRUE | FALSE,
required parameter vars=list("variable-name-1" <, "variable-name-2", ...>)
) <, list(...)>)

Parameter Descriptions

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

specifies the basis for the spline expansion.

For more information, see Splines and Spline Bases (Shared Concepts).

Default BSPLINE
BSPLINE

specifies a B-spline basis for the spline expansion.

TPF_DEFAULT

specifies a truncated power function basis for the spline expansion.

TPF_NOINT

excludes the intercept column when the basis is a truncated power function.

TPF_NOINTANDNOPOWERS

is equivalent to specifying both TPF_NOINT and TPF_NOPOWERS.

TPF_NOPOWERS

excludes the intercept column and polynomial columns when the basis is a truncated power function.

dataBoundary=TRUE | FALSE

when set to True, uses the extremes of the data as boundary knots in building a B-spline basis.

Default FALSE
degree=integer

specifies the degree of the spline transformation.

Default 3
Minimum value 0
details=TRUE | FALSE

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

Default FALSE
knotMax=double

equally spaces the right-side boundary knots for each variable, starting at the maximum of the variable and ending at the specified value.

knotMethod=list(knotmethodlist)

specifies how to construct the knots for spline effects.

For more information, see the knotMethod subparameter in the spline parameter (Shared Concepts).

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

equal=integer

specifies the number of equally spaced knots to be positioned between the extremes of the data. For a B-spline basis, any necessary boundary knots continue to be equally spaced unless the dataBoundary parameter is set to True. If no knotMethod is specified, the default of the equal parameter is 3.

Default 3
list=list(double-1 <, double-2, ...>)

specifies the list of internal knots to be used in forming the spline basis columns. For a B-spline basis, the data extremes are used as boundary knots.

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

specifies the list of all knots to be used in forming the spline basis columns. When you use a truncated power function basis, this list is interpreted as the list of internal knots. When you use a B-spline basis of degree d, then the first d entries are used as left-side boundary knots and the last MAX(d,1) entries in the list are used as right-side boundary knots.

multiscale=list(multiscalelist)

generates multiple B-spline bases that correspond to sets with an increasing number of internal knots. For scale i, the spline basis corresponds to 2 to the power of i equally spaced internal knots. By default, the bases for scales 0 to 7 are generated. A separate spline effect is generated for each effect.

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

endScale=integer

specifies the ending scale for a multiscale spline effect.

Default 7
startScale=integer

specifies the starting scale for a multiscale spline effect.

Default 0
rangeFractions=list(double-1 <, double-2, ...>)

specifies a list of fractions. For each variable that is specified in the spline effect, internal knots are placed at each specified fraction of the ranges of those variables.

knotMin=double

equally spaces the left-side boundary knots for each variable, starting at the specified value and ending at the minimum of the variable.

* name="string"

specifies the name of the effect.

naturalCubic=TRUE | FALSE

when set to True, specifies a natural cubic spline basis for the spline expansion. Natural cubic splines, also known as restricted cubic splines, are cubic splines that are constructed to be linear beyond the extreme knots.

Default FALSE
separate=TRUE | FALSE

when set to True, treats the spline basis for each variable as a separate effect when multiple variables are specified.

For more information, see the separate subparameter in the spline parameter (Shared Concepts).

Default FALSE
split=TRUE | FALSE

when set to True, treats each individual column in the design matrix that corresponds to the spline effect as a separate effect that can enter or leave the model independently.

For more information, see the split subparameter in the spline parameter (Shared Concepts).

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

specifies numeric variables for the spline effect. By default, the spline basis that is generated for each variable is a cubic B-spline basis with three equally spaced knots that are positioned between the minimum and maximum values of that variable.

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

Last updated: March 05, 2026