st: Multinomial Logistic - ordinal variables and Odds Ratios

[Imogen Jones <Imogen.Jones@utas.edu.au>]

Hi Everybody

 

I was hoping somebody could shed some light on the differences between using an ordinal and nominal variable in multinomial logistic regression in Stata.

 

I understand the processes are different, but I’m more concerned about the model fitting.  My interpretation of Hosmer and Lemeshow (2000) was that there isn’t a reliable test to estimate model fit.  Is this still correct?

 

Also, when using an ordinal variable as a dependent variable in multinomial logistic, are there any assumptions specific to this analysis that need to be met or parameter estimates that may vary from binary logistic?

 

Another question – Stata only seems to produce a coefficient or relative risk ratio for multinomial logistic.  Is there a specific reason why it won’t produce an odds ratio or is it just not a function of Stata?  I assumed it was the former since Stata is so comprehensive it probably wouldn’t leave something like that out.

 

Thanks in anticipation

 

Imogen Jones