Are there some alternatives to Poisson regression for count data?

[TomHsiung]

Is there any two-sample test for data with Poisson distribution? Poisson regression derives ratios but sometimes we want differences. Thx

[StatDave]

Using Poisson regression you can still estimate differences in counts, or if an offset is included. Just use the NLMeans macro after fitting the model. See this note.

[TomHsiung]

Oh, great. Let met study it. Thank you, sir.

Hmmm, it seems that the example in the thread used simple poisson regression with only one independent variable. But in reality, we often have multiple independent variables.

Tom