The SSM Procedure

OUTPUT Statement

OUTPUT <options> ;

The OUTPUT statement creates an optional output data set and also provides options to control certain aspects of the procedure output. If the OUT= option is specified, then an output data set is created to store estimates of the model components and series forecasts. If the OUT= option is omitted, then no data set is created by the OUTPUT statement. Other options in the OUTPUT statement produce additional information in the printed output generated by the procedure. For example, the AO and BREAK options control the search for additive outliers and structural breaks in the data, respectively.

AO(<ALPHA=number> <MAXNUM=number> <MAXPCT=number>): controls the additive outlier search (see the section Delete-One Cross Validation and the Additive Outlier Detection for more information). The ALPHA= suboption specifies the significance level for reporting the outliers. The default is ALPHA=0.05. The MAXNUM= suboption limits the number of outliers to search. The default is MAXNUM=5. The MAXPCT= suboption is similar to the MAXNUM= suboption. In the MAXPCT= option you can limit the number of outliers to search for according to a percentage of the series length. The default is MAXPCT=1. When you specify both of these options, the lesser of the two search numbers is used.
ALPHA=number: specifies the significance level of the forecast confidence intervals. For example, ALPHA=0.05, which is the default, results in a 95% confidence interval.
BREAK(<ALPHA=number> <MAXNUM=number> <MAXPCT=number>): controls the structural break search (for more information, see the section Structural Breaks in the State Evolution). In order for this option to have any effect, the CHECKBREAK option in one of the STATE or TREND statements, or the MAXSHOCK option in the OUTPUT statement, must be turned on. The ALPHA= suboption specifies the significance level for reporting the breaks. The default is ALPHA=0.05. The MAXNUM= suboption limits the number of breaks to search. The default is MAXNUM=5. The MAXPCT= suboption is similar to the MAXNUM= suboption. In the MAXPCT= option, you can limit the number of breaks to search for according to a percentage of the number of distinct time points in the data. The default is MAXPCT=1. When you specify both of these options, the lesser of the two search numbers is used.
MAXSHOCK: causes the computation of the maximal state shock chi-square statistic at each distinct time point in the input data set. These statistics are output to the data set that is specified in the OUT= option. A time series plot of these statistics is produced if the PLOTS=MAXSHOCK option is specified in the PROC SSM statement. These statistics are useful for detecting structural breaks in the state evolution process. This option can be computationally expensive for a model with large state size. See the section Structural Breaks in the State Evolution for more information.
OUT=SAS-data-set: specifies an output data set for the forecasts. The output data set contains the ID variable (if specified), the response variables, the one-step-ahead and out-of-sample response variable forecasts, the forecast confidence intervals, the smoothed values of the response series, and the one-step-ahead and smoothed estimates of the model components—including expressions that are defined by using the EVAL statement. See the section OUT= Data Set for more information.
PDV: causes the inclusion of the variables (variables in the program data vector) that are defined by using the programming statements in the SSM procedure in the OUT= data set. The parameters defined by the PARMS statement are also included. The output data set contains the values of these variables evaluated for all the rows in the input data set that is specified in the DATA= option. The parameters in the PARMS statement contain their estimated values.
PRESS: prints the prediction error sum of squares (PRESS) and the generalized cross validation error sum of squares (GCV). The PRESS table also reports the number of summands that are used in these sums of squares. See the section Delete-One Cross Validation and the Additive Outlier Detection for more information.