SAVE Subcommand (CATREG command)
The SAVE
subcommand
is used to add the transformed variables (category indicators replaced
with optimal quantifications), the predicted values, and the residuals
to the working data file.
Excluded cases are represented by a dot (the sysmis symbol) on every saved variable.
TRDATA. Transformed variables.
PRED. Predicted values.
RES. Residuals.
- A variable rootname can be specified with each of
the keywords. Only one rootname can be specified with each keyword,
and it can contain up to five characters (if more than one rootname
is specified with a keyword, the first rootname is used; if a rootname
contains more than five characters, the first five characters are
used at most). If a rootname is not specified, the default rootnames
(
TRA
,PRE
, andRES
) are used. -
CATREG
adds two numbers separated by an underscore (_) to the rootname. The formula is ROOTNAMEk_n, where k increments from 1 to identify the source variable names by using the source variables' position numbers in theANALYSIS
subcommand (that is, the dependent variable has the position number 1, and the independent variables have the position numbers 2, 3, ..., etc., as they are listed), and n increments from 1 to identify theCATREG
procedures with the successfully executedSAVE
subcommands for a given data file in a continuous session. For example, with two predictor variables specified onANALYSIS
, the first set of default names for the transformed data, if they do not exist in the data file, would be TRA1_1 for the dependent variable, and TRA2_1, TRA3_1 for the predictor variables. The next set of default names, if they do not exist in the data file, would be TRA1_2, TRA2_2, TRA3_2. However, if, for example, TRA1_2 already exists in the data file, then the default names should be attempted as TRA1_3, TRA2_3, TRA3_3—that is, the last number increments to the next available integer. - Variable labels are created automatically. (They are shown in the Procedure Information Table (the Notes table) and can also be displayed in the Data Editor window.)