SAS/ETS software includes the following SAS procedures:
ARIMA (Box-Jenkins) and ARIMAX (Box-Tiao) modeling and forecasting
regression analysis with autocorrelated or heteroscedastic errors and ARCH and GARCH modeling
spreadsheet calculations and financial report generation
fitting and simulating multivariate distributions by using copula methods
regression modeling for dependent variables that represent counts
access to financial and economic databases
maximum entropy-based regression
forecasting by using exponential smoothing models with optimized smoothing weights
time series interpolation, frequency conversion, and transformation of time series
loan analysis and comparison
multinomial discrete choice analysis
nonlinear simultaneous equations regression and nonlinear systems modeling and simulation
panel data modeling
polynomial distributed lag regression
qualitative and limited dependent variable analysis
modeling the statistical distribution of the severity of losses and other events
similarity analysis of time series data for time series data mining
linear systems simulation
spatial econometric models for cross-sectional data
spectral and cross-spectral analysis
state space modeling of time series
state space modeling and automated forecasting of multivariate time series
linear simultaneous equations models
analyzes time-stamped transactional data with respect to time and accumulates the data into a time series format
identifying the time frequency for data sets that contain time series data
analysis of time-stamped transactional data
nonlinear simultaneous equations regression and nonlinear systems modeling and simulation
time series cross-sectional regression analysis
unobserved components analysis of time series
vector autoregressive and moving average with modeling and forecasting
seasonal adjustment (Census X-11 and X-11 ARIMA)
seasonal adjustment (Census X-12 ARIMA)
seasonal adjustment (Census X-13 ARIMA-SEATS)
High-performance (HP) procedures are adapted to perform optimally in symmetric multiprocessing (SMP) mode, providing faster performance by making multiple CPUs available to complete individual processes simultaneously.
SAS/ETS software includes the following high-performance procedures:
high-performance compound distribution models
high-performance fitting and simulation of multivariate distributions by using copula methods
high-performance regression modeling for count dependent variables
high-performance panel data modeling
high-performance qualitative and limited dependent variable analysis
high-performance modeling of the severity of losses and other events
SAS/ETS software includes the following LIBNAME statement engines to provide access to financial and economic databases:
LIBNAME engine for accessing time series and event data that reside in a CRSPAccess database
LIBNAME engine for accessing time series or case series data that reside in a FAME database
LIBNAME engine to retrieve economic data from the FRED website, which is hosted by the Economic Research Division of the Federal Reserve Bank of St. Louis
LIBNAME engine for accessing time series that reside in a Haver Analytics Data Link Express (DLX) database
LIBNAME engine for accessing time series to retrieve statistical data from the Organisation for Economic Cooperation and Development (OECD) website on topics such as agriculture and fisheries, economy, education, employment, energy, environment, finance, health, industry and entrepreneurship, innovation, insurance and pensions, international migration, internet economy, investment, OECD.Stat data warehouse, regional, rural and urban development, science and technology, social and welfare issues, tax, trade, and transport
LIBNAME engine to retrieve economic data from the Quandl website, which offers access to 8 million time series data sets from 400 sources in finance, economics, society, health, energy, demography, and more
LIBNAME engine for accessing data items that reside in the CRSP US Stock (STK) Database, the CRSP US Stock and Indices (IND) Database, the CRSP US Treasury (TRS) Database, or the CRSP/Compustat Merged (CCM) Database, which is created from data delivered via Standard & Poor’s Compustat Xpressfeed product
LIBNAME engine for accessing both FactSet data and FactSet-sourced data that are provided by the FactSet OnDemand service
LIBNAME engine for accessing time series to retrieve statistical data from the World Bank Group Open (WBGO) data website, hosted by the World Bank Group. The most popular is the World Development Indicators (WDI) database, which presents the most current and accurate global development data available, including national, regional, and global estimates. The SASEWBGO interface engine supports access to the WDI database, but it also provides access to time series in other WBGO databases, such as the Global Economic Monitor (GEM) and the Special Data Dissemination Standard (SDDS)
SAS/ETS software includes the following LIBNAME statement engines to provide access to global weather and severe weather databases:
LIBNAME engine to retrieve severe weather data such as tornado vortex signatures; mesocyclone signatures; digital mesocyclone detection algorithm; hail, storm cell structure, and preliminary local storm reports; and severe thunderstorm, tornado, flash flood, and special marine warnings from the NOAA Severe Weather Data Inventory (SWDI) web service
LIBNAME engine to retrieve global weather data such as temperature, precipitation (rainfall), weather description, weather icon, and wind speed from the World Weather Online website
SAS/ETS software includes the following SAS macros:
generates statements to define autoregressive error models for the MODEL procedure
defines autoregressive error models that are specified using general form equations for the MODEL procedure
investigates Box-Cox transformations useful for modeling and forecasting a time series
computes probabilities for Dickey-Fuller test statistics
performs Dickey-Fuller tests for unit roots in a time series process
tests to determine whether a log transformation is appropriate for modeling and forecasting a time series
generates statements to define moving-average error models for the MODEL procedure
defines moving-average error models that are specified using general form equations for the MODEL procedure
generates statements to define polynomial distributed lag models for the MODEL procedure
These macros are part of the SAS AUTOCALL facility and are automatically available for use in your SAS program. For information about the SAS macro facility, see SAS Macro Language: Reference.