For a GLM in R, is it correct to interpret that Higher the difference between NULL & RESIDUAL deviance, better is your model? If not, then how do i know if my model is good or bad (for GLM - poisson, gamma, tweedie)
2
$\begingroup$
$\endgroup$
1
$\begingroup$
$\endgroup$
Simply check your model using anova.glm()
with a F test or a Chi-squared test. If your write anova(model,test="F")
this will automatically compare it to a null model and send back a p-value. Check Zuur et al. 2009 and, in R, ?anova.glm