SAS/ETS^®

Procedures

• The ARIMA Procedure
  Analyzes and forecasts equally spaced univariate time series data, transfer function data, and intervention data by using the autoregressive integrated moving-average (ARIMA) or autoregressive moving-average (ARMA) model.
• The AUTOREG Procedure
  Estimates and forecasts linear regression models for time series data when the errors are autocorrelated or heteroscedastic.
• The COMPUTAB Procedure
  Produces tabular reports generated using a programmable data table.
• The COPULA Procedure
  Enables the user to fit multivariate distributions or copulas from a given sample data set.
• The COUNTREG Procedure
  Analyzes regression models in which the dependent variable takes nonnegative integer or count values.
• The DATASOURCE Procedure
  Extracts time series and event data from many different kinds of data files distributed by various data vendors and stores them in a SAS data set.
• The ENTROPY Procedure (Experimental)
  Implements a parametric method of linear estimation based on generalized maximum entropy.
• The ESM Procedure
  Generates forecasts by using exponential smoothing models with optimized smoothing weights for many time series or transactional data.
• The EXPAND Procedure
  Converts time series from one sampling interval or frequency to another and interpolates missing values in time series.
• The FORECAST Procedure
  Provides a quick and automatic way to generate forecasts for many time series in one step.
• The HPCDM Procedure
  Estimates a compound distribution model (CDM) by modeling the severity (magnitude) of loss and frequency (count) of loss while aggregating them into one estimate.
• The HPCOPULA Procedure
  Enables you to simulate realizations of multivariate distributions by using the copula approach.
• The HPCOUNTREG Procedure
  Fits regression models in which the dependent variable takes on nonnegative integer or count values.
• The HPPANEL Procedure
  Fits a class of linear econometric models that commonly arise when time series and cross-sectional data are combined.
• The HPQLIM Procedure
  Analyzes univariate limited dependent variable models in which dependent variables are observed only in a limited range of values
• The HPSEVERITY Procedure
  Fits models for statistical distributions of the severity (magnitude) of events.
• The LOAN Procedure
  Analyzes and compares fixed rate, adjustable rate, buydown, and balloon payment loans.
• The MDC Procedure
  Analyzes models in which the choice set consists of multiple alternatives.
• The MODEL Procedure
  Analyzes models in which the relationships among the variables comprise a system of one or more nonlinear equations.
• The PANEL Procedure
  Analyzes a class of linear econometric models that commonly arise when time series and cross-sectional data are combined.
• The PDLREG Procedure
  Estimates regression models for time series data in which the effects of some of the regressor variables are distributed across time.
• The QLIM Procedure
  Analyzes univariate and multivariate limited dependent variable models in which dependent variables take discrete values or dependent variables are observed only in a limited range of values.
• The SEVERITY Procedure
  Estimates parameters of any arbitrary continuous probability distribution that is used to model the magnitude (severity) of a continuous-valued event of interest.
• The SIMILARITY Procedure
  Computes similarity measures associated with time-stamped data, time series, and other sequentially ordered numeric data.
• The SIMLIN Procedure
  Reads the coefficients for a set of linear structural equations, which are usually produced by the SYSLIN procedure.
• The SPATIALREG Procedure
  Analyzes spatial econometric models for cross-sectional data in which observations in the data are spatially referenced or georeferenced.
• The SPECTRA Procedure
  Performs spectral and cross-spectral analysis of time series.
• The SSM Procedure
  Performs state space modeling of univariate and multivariate time series and longitudinal data.
• The STATESPACE Procedure
  Uses the state space model to analyze and forecast multivariate time series.
• The SYSLIN Procedure
  Estimates parameters in an interdependent system of linear regression equations.
• The TIMEDATA Procedure
  Analyzes time-stamped transactional data with respect to time and accumulates the data into a time series format.
• The TIMEID Procedure
  Evaluates a variable in an input data set for its suitability as a time ID variable in SAS procedures and solutions that are used for time series analysis.
• The TMODEL Procedure
  Incorporates high-performance computational techniques and offers new features that enhance the functionality of PROC MODEL
• The TIMESERIES Procedure
  Analyzes time-stamped transactional data with respect to time and accumulates the data into a time series format.
• The TSCSREG Procedure
  Analyzes a class of linear econometric models that commonly arise when time series and cross-sectional data are combined.
• The UCM Procedure
  Analyzes and forecasts equally spaced univariate time series data by using an unobserved components model (UCM).
• The VARMAX Procedure
  Estimates the model parameters and generates forecasts associated with vector autoregressive moving-average processes with exogenous regressors (VARMAX) models.
• The X11 Procedure
  Makes additive or multiplicative adjustments and creates an output data set containing the adjusted time series and intermediate calculations.
• The X12 Procedure
  Makes additive or multiplicative adjustments and creates an output data set containing the adjusted time series and intermediate calculations.
• The X13 Procedure
  Makes additive or multiplicative adjustments and creates an output data set that contains the adjusted time series and intermediate calculations.

Interface Engines

• The SASECRSP Interface Engine
  Enables SAS users to access and process time series, events, portfolios, and group data that reside in Center for Research in Security Prices databases (CRSPAccess data).
• The SASEFAME Interface Engine
  Provides a seamless interface between Fame and SAS data to enable SAS users to access and process time series, case series, and formulas that reside in a Fame database.
• The SASEFRED Interface Engine
  Enables SAS users to retrieve economic data from the FRED website, which is hosted by the Economic Research Division of the Federal Reserve Bank of St. Louis. FRED stands for Federal Reserve Economic Data.
• The SASEHAVR Interface Engine
  Enables SAS users to read economic and financial time series data that reside in a Haver Analytics DLX (Data Link Express) database.
• The SASENOAA Interface Engine
  Enables SAS programmers to retrieve severe weather data from the National Oceanic and Atmospheric Administration (NOAA) Severe Weather Data Inventory (SWDI) web service.
• The SASEOECD Interface Engine New Interface Engine!
  Enables SAS programmers to retrieve time series data from the Organisation for Economic Co-operation and Development (OECD) website.
• The SASEQUAN Interface Engine
  Enables SAS users to retrieve economic and other time series data from the Quandl website, which is hosted by Quandl.
• The SASERAIN Interface Engine
  Enables SAS users to retrieve weather data from the World Weather Online website.
• The SASEXCCM Interface Engine
  Enables SAS users to access the CRSP/Compustat Merged (CCM) Database
• The SASEXFSD Interface Engine
  Enables SAS users to access both FactSet data and FactSet-sourced data that are provided by the FactSet OnDemand service (formerly known as FASTFetch).

Topics

• Econometrics and Systems Modeling
• Time Series Analysis
• Automatic Forecasting
• Time Series Forecasting System
• Data Manipulation
• Economic & Financial Databases
• Financial Analysis & Reporting

SAS/ETS Documentation Examples

For examples in the documentation, go to SAS/ETS software documentation examples.

---

SAS/ETS Software Examples

The following SAS/ETS software examples are not included in the SAS/ETS documentation and are available only on the Web.

• Accounting for Missing Observations in Time Series Data
• Analysis of Unobserved Component Models Using PROC UCM
• Bivariate Granger Causality Test
• Bootstrapping Correct Critical Values in Tests for Structural Change
• Calculating Economic Indices
• Calculating Elasticities from a Translog Cost Function
• Calculating Elasticites in an Almost Ideal Demand System
• Calculating Price Elasticity of Demand
• Chow Test for Structural Breaks
• Computing Marginal Effects for Discrete Dependent Variable Models
• Efficiency Test for Estimators by Simulation
• Efficient Method of Moments Estimation of a Stochastic Volatility Model
• Estimating a Derived Demand System from a Translog Cost Function
• Estimating an Almost Ideal Demand System Model
• Estimating a Consumption-Based Asset Pricing Model
• Estimating GARCH Models
• Fitting a Capital Asset Pricing Model
• Forecasting a Seasonal ARMA Process
• Heteroscedastic Modeling of the Fed Funds Rate
• Heteroscedastic Two-Stage Least Squares Regression with PROC MODEL
• Multiple Imputation for a GARCH(1,1) Model
• Overlaying Multiple Forecast Methods in Time Series Plots
• Plotting Time Series Data
• Regression Model with Correction of Heteroscedasticity
• Specification Test for Non-Nested Models
• Testing for Returns to Scale in a Cobb-Douglas Production Function
• Tourism Demand Modeling and Forecasting with PROC VARMAX
• Transforming the Frequency of Time Series Data

SAS/ETS software provides extensive facilities for analyzing time series and performing financial analysis.

Econometrics and Systems Modeling

Systems modeling for econometric data is done in three parts: econometric modeling, simulation, and forecasting. Often, these tasks are performed sequentially. A model is fitted to the data, then simulated with historical data, and finally used for forecasting. Models for estimation can consist of a single equation or a system of equations; they can be linear, nonlinear, or ordinary differential equations; they can require restrictions on parameters. SAS/ETS software enables you to estimate and test hypotheses for all these types of models.

Time Series Analysis

Time series are any univariate or multivariate data collected over time. SAS/ETS software includes a wide range of tools for analyzing time series data. You can estimate relationships and produce forecasts that make use of information in past values, independent or explanatory variables, and indicator or dummy variables. In addition, you can model and predict the autoregressive conditional heteroscedastic (ARCH) model or its generalizations (GARCH). Additional tools provide regression analysis for linear models with distributed lags and time series cross-sectional regression analysis for panel data.

You can perform multiple regression in the presence of serially correlated error terms, fit models that allow for an error term generated by an autoregressive integrated moving-average (ARIMA) process, or use spectral analysis to decompose a series into cyclical components or to perform frequency domain tests.

Automatic Forecasting

Forecasting is the combining of knowledge from the past and future expectations with an estimated model to produce likely outcomes for the future. It enables more accurate predictions of the future to be made, reducing the uncertainty inherent in the decision-making process.

Many of the SAS/ETS procedures have options that facilitate the forecasting of time series variables.

The Time Series Forecasting System

SAS/ETS software includes a point-and-click application for exploring and analyzing univariate time series data. You can use the automatic model selection facility to select the best-fitting model for each time series, or you can use the system's diagnostic features and time series modeling tools interactively to develop forecasting models customized to best predict your time series. The system provides both graphical and statistical features to help you choose the best forecasting method for each series.

Data Manipulation

SAS/ETS software contains tools that can be used to convert irregularly spaced data to equally spaced data, interpolate missing values, or convert time series data from one frequency to another (such as from weekly to monthly or vice versa).

Seasonal time series can be adjusted using the U.S. Bureau of the Census X11 or X13 Seasonal Adjustment algorithms, and the X11-ARIMA or X13-ARIMA methods developed by Statistics Canada.

Access to Economic and Financial Databases

SAS/ETS software makes it easy to access directly many of the most popular commercially available economic and financial time series databases. Data can be extracted from files supplied by government and commercial data vendors and then converted into SAS data sets.

Financial Analysis and Reporting

Widely varying credit market conditions in the past few decades have given rise to many new types of financing arrangements. SAS/ETS software provides the means to compare quickly and easily different loans, to analyze fixed and variable rate loans, to analyze buydown and balloon loans, to perform calculations, and to generate financial reports.