Programming the statistical procedures from SAS

GENMOD: LRT for LSMEAN diffs?

Reply
Frequent Contributor
Posts: 80

GENMOD: LRT for LSMEAN diffs?

Is it possible to produce likelihood ratio test (LRT) statistics for the pairwise comparisons with the LSMeans statement rather than Wald statistics?

My model has two variables, one has 3 levels and the other only 2.  I noticed that analysis of the variable with only 2 levels resulted in differing conclusions.  Using the Type 3 LRT, the p-value is 0.0355.  Using the LSMeans Wald (or the Type 3 Wald), I only get 0.1250.  Clearly, the LRT is a bit more powerful in this circumstance, and I can just use that p-value.  That makes me worry about my other variable though, the one with 3 levels.  To do my pairwise comparisons, it looks like GENMOD can only do a Wald test.  Is it possible to get a LRT?  I'd like the extra power.

Thanks!

Ask a Question
Discussion stats
  • 0 replies
  • 222 views
  • 0 likes
  • 1 in conversation