Tell me more ×
Cross Validated is a question and answer site for statisticians, data analysts, data miners and data visualization experts. It's 100% free, no registration required.
up vote 0 down vote favorite

Why would I get 0 estimates of coefficients in logistic regression? And the coefficients are exactly 0. These are for variables of different levels of a categorical variable.

share|improve this question
1  
Context please? Coefficients that are exactly zero? Or, just close to zero? Classical logistic regression or some regularized version? – cardinal Nov 13 '11 at 23:14
4  
Friendly reminder: The more effort you put into stating your question clearly and completely, the more easily others can provide clear and complete answers. :) – cardinal Nov 13 '11 at 23:15
1  
If it's a categorical predictor then this probably just means the mean within that level (the one that gives a $\hat{\beta}$ of 0) of the categorical predictor is the same of that in the reference level. – Macro Nov 13 '11 at 23:35
@Macro: (+1) This is true if there is only a single categorical predictor. – cardinal Nov 13 '11 at 23:56
Might be cool if you pasted your data somehow. – Adam Nov 14 '11 at 2:12

Know someone who can answer? Share a link to this question via email, Google+, Twitter, or Facebook.

Your Answer

 
discard

By posting your answer, you agree to the privacy policy and terms of service.

Browse other questions tagged or ask your own question.