topic Re: Logistic Regression using CATMOD in Statistical Procedures

Logistic Regression using CATMOD

Proshi — Fri, 27 Apr 2018 15:11:07 GMT

Dear all,

I would like to know if I could estimate Odds ratio with a Catmod procedure?

Thank you,

Darina Proshenska

Re: Logistic Regression using CATMOD

Ksharp — Sat, 28 Apr 2018 11:18:36 GMT

I am not sure .

CONTRAST '1 vs. 4' A 2 1 1 / EXP ;

Re: Logistic Regression using CATMOD

Proshi — Sun, 29 Apr 2018 17:57:57 GMT

I will try this. Thank you for your help!

Darina

Re: Logistic Regression using CATMOD

Rick_SAS — Mon, 30 Apr 2018 12:30:21 GMT

Yes. Use the LOGLIN statement to specify the model effects and put the _RESPONSE_ keyword on the right-hand side of the MODEL statement. The parameter estimates table contains the estimates on a log scale. You will need to combine them and exponentiate them to get the odds ratios. I wasn't able to find an online example, but there is an example in the "Loglinear Models" chapter of Stokes, Davis, and Koch, "Categorical Data Analysis" book.

Re: Logistic Regression using CATMOD

Proshi — Tue, 01 May 2018 15:18:26 GMT

Okay. I'll check this.

Thanks, Rick,
Darina Proshenska

Re: Logistic Regression using CATMOD

Rick_SAS — Tue, 01 May 2018 15:24:03 GMT

@StatDave gave you some valuable advice about using PROC LOGISTIC instead of PROC CATMOD. Please consider following his advice.

Re: Logistic Regression using CATMOD

Proshi — Tue, 01 May 2018 20:44:21 GMT

Yes. Thank you!