Multinominal Regression (NOMREG) Subpopulation Error

Moderators: statman, Analyst Techy, andris, Fierce, GerineL, Smash

Posts: 1
Joined: Mon Jan 21, 2008 5:18 pm

Multinominal Regression (NOMREG) Subpopulation Error

Postby davis1163 » Mon Jan 21, 2008 5:42 pm


I am trying to run a Multinominal Regression with 12 predictors, predicting 1 of 3 groups. However, everytime I run it I get an error warning me that
"There are 344 (66.7%) cells (i.e., dependent variable levels by subpopulations) with zero frequencies."

Can anybody please tell me what this error means, and what the implications might be, and possible suggestions??

Please let me know if you need additional info to help me out

Thanks in advance!

Who is online

Users browsing this forum: No registered users and 1 guest