The ARIMA Procedure
- Overview
-
Getting Started
The Three Stages of ARIMA ModelingIdentification StageEstimation and Diagnostic Checking StageForecasting StageUsing ARIMA Procedure StatementsGeneral Notation for ARIMA ModelsStationarityDifferencingSubset, Seasonal, and Factored ARMA ModelsInput Variables and Regression with ARMA ErrorsIntervention Models and Interrupted Time SeriesRational Transfer Functions and Distributed Lag ModelsForecasting with Input VariablesData Requirements -
Syntax
-
DetailsThe Inverse Autocorrelation FunctionThe Partial Autocorrelation FunctionThe Cross-Correlation FunctionThe ESACF MethodThe MINIC MethodThe SCAN MethodStationarity TestsPrewhiteningIdentifying Transfer Function ModelsMissing Values and AutocorrelationsEstimation DetailsSpecifying Inputs and Transfer FunctionsInitial ValuesStationarity and InvertibilityNaming of Model ParametersMissing Values and Estimation and ForecastingForecasting DetailsForecasting Log Transformed DataSpecifying Series PeriodicityDetecting OutliersOUT= Data SetOUTCOV= Data SetOUTEST= Data SetOUTMODEL= SAS Data SetOUTSTAT= Data SetPrinted OutputODS Table NamesStatistical Graphics
-
Examples
- References
The output data set produced by the OUTCOV= option of the IDENTIFY statement contains the following variables:
-
LAG, a numeric variable that contains the lags that correspond to the values of the covariance variables. The values of LAG range from 0 to N for covariance functions and from –N to N for cross-covariance functions, where N is the value of the NLAG= option.
-
VAR, a character variable that contains the name of the variable specified by the VAR= option.
-
CROSSVAR, a character variable that contains the name of the variable specified in the CROSSCORR= option, which labels the different cross-covariance functions. The CROSSVAR variable is blank for the autocovariance observations. When there is no CROSSCORR= option, this variable is not created.
-
N, a numeric variable that contains the number of observations used to calculate the current value of the covariance or cross-covariance function.
-
COV, a numeric variable that contains the autocovariance or cross-covariance function values. COV contains the autocovariances of the VAR= variable when the value of the CROSSVAR variable is blank. Otherwise COV contains the cross covariances between the VAR= variable and the variable named by the CROSSVAR variable.
-
CORR, a numeric variable that contains the autocorrelation or cross-correlation function values. CORR contains the autocorrelations of the VAR= variable when the value of the CROSSVAR variable is blank. Otherwise CORR contains the cross-correlations between the VAR= variable and the variable named by the CROSSVAR variable.
-
STDERR, a numeric variable that contains the standard errors of the autocorrelations. The standard error estimate is based on the hypothesis that the process that generates the time series is a pure moving-average process of order LAG–1. For the cross-correlations, STDERR contains the value
, which approximates the standard error under the hypothesis that the two series are uncorrelated.
-
INVCORR, a numeric variable that contains the inverse autocorrelation function values of the VAR= variable. For cross-correlation observations (that is, when the value of the CROSSVAR variable is not blank), INVCORR contains missing values.
-
PARTCORR, a numeric variable that contains the partial autocorrelation function values of the VAR= variable. For cross-correlation observations (that is, when the value of the CROSSVAR variable is not blank), PARTCORR contains missing values.