I need to model a certain response variable in a GLM model. The response variable is a count (amount of insurance claims over a year). So it would be natural to assume a Poisson distribution for this response variable. However, using a goodness of fit test in R, how can I validate this assumption?

  • $\begingroup$ This document has a good run down of most distribution goodness-of-fit measures in R. I would particularly look at fitdistr() in the MASS package and goodfit() in the vcd package. $\endgroup$ – NatWH May 14 '18 at 12:59
  • 1
    $\begingroup$ Sorry, if your response variable depends on covariates (which it should if you want to model with a GLM) it probably is not Poisson distributed. However, that does not matter for regression. What matters is the residual distribution. $\endgroup$ – Roland May 14 '18 at 13:03
  • $\begingroup$ You will need poisson regression, and then this post will be useful: stats.stackexchange.com/questions/331086/… $\endgroup$ – kjetil b halvorsen May 14 '18 at 13:20
  • $\begingroup$ Possible duplicate of Diagnostic plots for count regression $\endgroup$ – kjetil b halvorsen Jun 27 '18 at 11:19