Stepwise with categorical variables

Hi all. I would like to estimate a predictive linear regression model
with 5 predictors. One predictor is categorical (socioeconomic
status-SS) with 3 categories, so I generate 2 dummy variables: SS1 and
SS2.
The problem appears when using STEPWISE regression with the procedure
REGRESSION of SPSS, because this method of selection does not take into
account that the 2 dummy variables must go together in any candidate
model.
Does anyone how to solve this problem working with SPSS (I know other
software make the dummy decomposition automatically so there is no
problem).

Thank's in advance.
Blas Navarro.
Universitat Autònoma de Barcelona - SPAIN

.

Relevant Pages

  • Re: All possible subsets regression
    ... > models by combination of predictors, and to compare they with C_p ... > analysis, but I don't know how to do it with SPSS, or even if it is ... > subsets regression" analysis with SPSS, ... "best predictors for a predictive linear regression model". ...
    (sci.stat.edu)
  • Re: Stepwise with categorical variables
    ... I would like to estimate a predictive linear regression model ... > REGRESSION of SPSS, because this method of selection does not take into ... predictors are categorical or continuous. ...
    (sci.stat.edu)
  • All possible subsets regression
    ... In the selection of best predictors for a predictive linear regression ... The command REGRESS of BMDP 9R software does automatically this ... analysis, but I don't know how to do it with SPSS, or even if it is ...
    (sci.stat.edu)
  • Re: stepwise regression by GENSTAT
    ... My handbook considers only stepwise regression as a method to select ... leaving behind only "random variation" in the residuals (residuals = ... to which subset of these to use as predictors. ...
    (sci.stat.math)
  • Re: Questions about square errors
    ... Take a look at the 10X10 correlation coefficient matrix and the ... multicollinearities. ... least squares and/or multiple regression. ... Your model may have several unnecessary predictors. ...
    (sci.stat.math)