Zero Degrees of Freedom Class Variable in Logistic Regression

Reply
New Contributor
Posts: 2

Zero Degrees of Freedom Class Variable in Logistic Regression

Hi All,

I have a question, when does degrees of freedom for a class variable (lets say with 5 levels) equal to zero in the logistic regressions Type III analysis of Effects?

In MLE class variable groups have very logical coefficients, but in Effects section, where you can find Wald etc., it says df = 0.

Thanks.

George

To have a better idea, output looks like this:

                     Type 3 Analysis of Effects

                                                  Wald
Effect                                DF    Chi-Square    Pr > ChiSq

VAR1                                 0         .             .

                                Analysis of Maximum Likelihood Estimates

                                                        Standard          Wald
Parameter                             DF    Estimate       Error    Chi-Square    Pr > ChiSq    Exp(Est)

VAR1                              1     1      0.2912      0.0335         75.50        <.0001       1.338
VAR1                              2     0           0           .           .           .            .                     .

Super User
Posts: 19,165

Re: Zero Degrees of Freedom Class Variable in Logistic Regression

I usually see that when the level is fully equivalent to another level in the class, ie var1 level1 is fully equal to var1 level2 OR if it is the reference level.

New Contributor
Posts: 2

Re: Zero Degrees of Freedom Class Variable in Logistic Regression

Hi Reeza,

This is not the case, level 1 and 2 completely differ with each other. It is in fact flag variable, with 0-s and 1-s (IV is equal to 0.05).

I suspect that this variable might be a linear combination of other variables, but how to check this fact?

BR,

George

Super User
Posts: 19,165

Re: Zero Degrees of Freedom Class Variable in Logistic Regression

See the last part of my answer - the reference level does not have an estimate. So for a variable that has two levels only, one will be missing.

Ask a Question
Discussion stats
  • 3 replies
  • 231 views
  • 0 likes
  • 2 in conversation