proc autoreg and a logistic regression equation

[MaryA_Marion]

I have been asked to use proc autoreg to compute the durbin watson statistic for a logistic regression problem. How to do?

Thank you.  Mary

proc autoreg data=silica;
model y = exp(-(A B C)) / nlag=?;

[PGStats]

proc autoreg doesn't do logistic regression. What is the model that you wish to fit?

[PeterClemmensen]

Use Proc GENMOD or Proc LOGISTIC instead 🙂

[StatDave · Accepted solution]

There is no Durbin-Watson test for binomial data.  However, you could consider fitting a GEE model in PROC GENMOD and using TYPE=AR or MDEP(1) to examine the estimated correlation between adjacent observations.

[MaryA_Marion]

thank you for your reply. will the autocorrelation between observations be the same as that between residuals?

mary