topic Re: Imputation of categorical variables in Statistical Procedures

Imputation of categorical variables

deleted_user — Tue, 28 Jul 2009 13:26:18 GMT

Hi,

I need to impute a nominal categorical variable using both continuous and categorical covariates. Proc MI documentation suggests DISCRIM option for nominal variables but this procedure uses only continuous variables. Is there any other option to include both continuous and nominal covariates in the estimation ?

Thank you for your help.
Shule

Re: Imputation of categorical variables

StatDave — Tue, 28 Jul 2009 16:04:18 GMT

You could consider using a nominal logistic model. You can model a nominal (unordered) response in PROC LOGISTIC using the LINK=GLOGIT option, and you can use a mixture of categorical (CLASS) and continuous predictors. See the example titled "Nominal Response Data: Generalized Logits Model" in the LOGISTIC documentation:

9.1: http://support.sas.com/onlinedoc/913/getDoc/en/statug.hlp/logistic_index.htm
9.2: http://support.sas.com/documentation/cdl/en/statug/59654/HTML/default/logistic_toc.htm

Re: Imputation of categorical variables

deleted_user — Tue, 28 Jul 2009 16:07:35 GMT

I was looking for a method for multiple imputation but using logistic regression should also work for my purpose.

Thanks.

Re: Imputation of categorical variables

deleted_user — Thu, 24 Feb 2011 09:39:49 GMT

How to impute via MI the categorical variables in case of non-monotone pattern of missingness?

Re: Imputation of categorical variables

Dale — Thu, 24 Feb 2011 17:24:02 GMT

Over on SAS-L, there was a post just this morning regarding imputation of categorical variables. The author of the post suggested use of a product called IVEWARE for imputing categorical data. The author of that post also indicated that IVEWARE is free and can be called from SAS. Sounds like it would be worth checking into.

The SAS-L post can be found at:
http://listserv.uga.edu/cgi-bin/wa?A2=ind1102d&L=sas-l&F=&S=&P=10071

A quick Google search turned up the following page for the IVEWARE program:
http://www.isr.umich.edu/src/smp/ive/

Re: Imputation of categorical variables

deleted_user — Fri, 25 Feb 2011 15:25:23 GMT

Thanks for reply. Looks very interesting for me. Would be good to know what SAS thinks about this method (i.e. about Sequential Regression Imputation Method)