I did a logistic regression with a single explanatory factor (which is ordered, hence I cannot set the reference level - it has 11 levels, hence when I get the Wald tests the first three are linear, quadratic and cubic coefficents). I also did a likelihood ratio test to compare this model with a null model, to see if the factor as a whole is significant.
The factor was significant (when compared with the null model), but none of the levels were in the Wald tests (even the coefficents). How would you suggest interpreting this? How can I make conclusions about how the factor affects the data?