A question on multinomial logistic regression in stata

[Xiaochi]

Dear listers:

I ran a multinomial logistic model (it was an assignment). I used command mlogit. But I didn't not find any command to report the goodness of fit statistics (pearson X squared and deviance X squared). Also, there was no command to make classification table for mlogit in stata. The command estat gof and estat classification could only work for logit or probit. It's kind of weird since both SAS and SPSS could make it. Although I can use SAS to finis thin assignment but I really want to use stata since I mainly use stata so far.

I am not sure if it is a matter of software or mathematics. I am study multinomial model. If you need, I will send you the data or SAS and SPSS output. Thank you very much for your time.

Xiaochi

[Joseph Coveney]

In SAS, are you using PROC LOGISTIC or PROC CATMOD? You can attach your output files if they're plain text to your posts. Why don't you do that--it might help others see what you're looking for.

[Xiaochi]

I used PRO LOGISTIC. I want Pearson and Deviance goodness of fit after multinomial logistic regression (mlogit). SAS output is like this: There is no corresponding stata command.