The X13 Procedure

INPUT Statement

  • INPUT variables < / options > ;

The INPUT statement specifies variables in the DATA= or AUXDATA= data set (which are specified in the PROC X13 statement) that are to be used as regressors in the regression portion of the regARIMA model. The variables in the data set should contain the values for each observation that define the regressor. Past values of regression variables should also be included in the DATA= or AUXDATA= data set if the time series listed in the VAR statement is to be extended with regARIMA backcasts. Similarly, future values of regression variables should also be included in the DATA= or AUXDATA= data set if the time series listed in the VAR statement is to be extended with regARIMA forecasts.

You can specify multiple INPUT statements. If you do not specify a MDLINFOIN= data set in the PROC X13 statement, then all variables listed in the INPUT statements are applied to all BY groups and all time series that are processed. If you specify a MDLINFOIN= data set, then the INPUT statements apply only if no regression information for the BY group and series is available in the MDLINFOIN= data set.

The INPUT statement provides the same functionality as the USERVAR= option in the REGRESSION statement. For more information about specifying user-defined regression variables, see the section User-Defined Regression Variables, Example 45.6, and Example 45.11.

The following options can appear in the INPUT statement:

B=(value <F> …)

specifies initial or fixed values for the regression parameters in the order in which they appear in variables. Each B= list applies to the variable list that immediately precedes the slash.

For example, the following statements set an initial value of 1 for the user-defined regressor, x: 

   input y ;
   input x / b=1 2 ;

In this example, the B= option applies only to the second INPUT statement. The value 2 is discarded because there is only one variable in the variable list.

To assign an initial value of 1 to the y regressor and 2 to the x regressor, use the following statements: 

   input y / b=1;
   input x / b=2 ;

An F immediately following the numerical value indicates that this is not an initial value, but a fixed value. See Example 45.8 for an example that uses fixed parameters. In PROC X13, individual parameters can be fixed while other parameters in the same model are estimated.

USERTYPE=(values)

enables a user-defined variable to be processed in the same manner as a US Census predefined variable. You can specify the following values: AO, CONSTANT, EASTER, HOLIDAY, LABOR, LOM, LOMSTOCK, LOQ, LPYEAR, LS, RP, SCEASTER, SEASONAL, TC, TD, TDSTOCK, THANKS, or USER. For example, the US Census Bureau EASTER(w) regression effects are included the "RegARIMA Holiday Component" table (A7). Specify USERTYPE=EASTER to include a user-defined variable that is processed exactly as the US Census predefined EASTER(w) variable, including inclusion in the A7 table. The NOAPPLY= option in the REGRESSION statement also changes the processing of variables based on the USERTYPE= value. Table 45.4 shows the regression types that are associated with each regression effects table.

Each USERTYPE= list applies to the variable list that immediately precedes the slash. The same rules for assigning B= values to regression variables apply for USERTYPE= options. For example, the following statements specify that the user-defined regressor in the variable MyEaster be processed exactly as the US Census predefined LOM variable: 

   input MyLOM;
   input MyEaster / usertype=LOM EASTER;

In this example, the USERTYPE= option applies only to the MyEaster variable in the second INPUT statement. The USERTYPE value EASTER is discarded because there is only one variable in the variable list.

To assign the USERTYPE value LOM to the MyLOM variable and EASTER to the MyEaster variable, use the following statements: 

   input MyLOM / usertype=LOM;
   input MyEaster / usertype=EASTER;

The following USERTYPE= options specify that the regression effect be removed from the seasonally adjusted series: EASTER, HOLIDAY, LABOR, LOM, LOMSTOCK, LOQ, LPYEAR, SCEASTER, SEASONAL, TD, TDSTOCK, THANKS, and USER. When a regression effect is removed from the seasonally adjusted series, the level (mean) of the seasonally adjusted series can be altered. It is often desirable to use a zero-mean (mean-adjusted) regressor for effects that are to be removed from the seasonally adjusted series. See Example 45.6 for an example that specifies a zero-mean regressor.