Hi,
I wonder whether anybody can help me. I am trying to run a small sample (n = 45) binary logistic regression, with a mixture of continuous and categorical predictors. One categorical predictor (2x2) has an empty cell, and leads to an incredibly large standard error. I would like to follow Firth (1993) and add .5 to the cells, but there seems to be no way to do it in SPSS (apart from running a multinomial regression)  any suggestions?
Many thanks,
Seb
Topic
This topic has been locked.
1 reply
Latest Post
 20121223T23:26:13Z by SystemAdmin
ACCEPTED ANSWER
Pinned topic Binary logistic regression & empty cells
20121223T21:29:42Z

Answered question
This question has been answered.
Unanswered question
This question has not been answered yet.
Updated on 20121223T23:26:13Z at 20121223T23:26:13Z by SystemAdmin

ACCEPTED ANSWER
Re: Binary logistic regression & empty cells
20121223T23:26:13Z in response to SystemAdminWhy not just run multinomial regression with two categories?