Providing software solutions since 1976
SAS/ETS Software, Release 8.2
What's New Highlights
SAS/ETS software provides very powerful and extensive tools for time series, econometric and financial analysis. A full range of forecasting and econometric methods, from simple to complex, are supported. The software also includes a point-and-click Time-Series Forecasting System that offers automated model fitting and forecasting, and interactive model development. An Investment Analysis system provides time-value-of-money analysis for a variety of investments, including loans, bonds, depreciation and generic cash flows.
Release 8.2 offers enhancements that increase the already powerful forecasting capabilities of SAS/ETS software. Read the highlights:
- The Multinomial Discrete Choice procedure (PROC MDC) enables you to analyze models where the choices consist of multiple independent alternatives (choices and nested choices). Such models often arise in a variety of areas, including economics, finance, marketing, political science, psychology and sociology. Production for 8.2, PROC MDC supports conditional logit, mixed logit, heteroscedastic extreme value, nested logit and multinomial probit models. The procedure uses the maximum likelihood (ML) or simulated maximum likelihood method for model estimation.
- The VARMAX procedure for vector time series analysis, modeling, and forecasting is now production and adds new demand planning capabilities to SAS/ETS software. This procedure enables you to jointly model the dynamic relationships between different series of events to produce more accurate forecasts for all.
- Interface engines that provide direct and seamless access to both CRSP and FAME data via a LIBNAME statement are now production.
- The X12 procedure, an adaptation of the U.S. Bureau of the Census' X-12-ARIMA Seasonal Adjustment program for seasonally adjusting monthly or quarterly time series, has been enhanced with new statements as well as some new predefined regression variables and tables.
- The ARIMA procedure has been enhanced with the new OUTLIER statement (experimental with this release). The ARIMA procedure is a popular procedure for modeling time series data using the Box-Jenkins methodology. The OUTLIER statement can be used to detect shifts in the mean level of the response series that are not accounted for by the estimated model in PROC ARIMA. Such shifts in the mean level are common phenomena, occurring due to events such as sales promotions, labor strikes, new discoveries and so on. Detecting significant shifts in the mean level using OUTLIER statements allows users to identify where and how their models can be improved.
- Other SAS/ETS features that are enhanced with this release include: the interactive Investment Analysis System for financial analysis and reporting, the Time Series Forecasting System, and the MODEL procedure.
