An embedded and charset-unspecified text was scrubbed... Name: not available URL: <https://stat.ethz.ch/pipermail/r-sig-mixed-models/attachments/20130910/2a4083a5/attachment.pl>
GLM question about chi-square and LLH
2 messages · Torvon, Ben Bolker
Torvon <torvon at ...> writes:
Hello, I want to compare two GLMs (binomial dependent variable) , the results are:
m1<-glm(symptoms ~ 1, data=data2) m2<-glm(symptoms ~ phq_index, data=data2
I am used to comparing these kind of models using chi-square values, a chi-square difference, and a chi-square difference test. Since all other models in the paper are compared this way, and since I'd like to report them in a table together: why exactly is this model test different from my other models tests in which I get chi-square values and difference tests? And can I obtain chi-square values from this test?
Sorry, but this isn't an appropriate question for this mailing list, which specifically covers *mixed* models. You might try the main R help list (r-help at r-project.org). It might also help to clarify your question: I didn't understand it, and others might not. What are "all other models in the paper"? Did you look at ?anova.glm ? For GLMs, the difference in deviance is (typically) a chi-square value ... Ben Bolker