I am trying to model count data in R that is apparently underdispersed (Dispersion Parameter ~ .40). I tried looking for possible tutorials of Conway Maxwell Poisson in R , which apparently can be used for underdispersed distribution but couldn't find any.
Can someone please suggest me how to handle underdispersed distribution
Mahim Khan a generalized Poisson regression model should be appropiate, and you should expect negative values of the dispersion parameter it there was adjustment for underdispersion. Check the VGAM package for R:
https://cran.r-project.org/web/packages/VGAM/vignettes/categoricalVGAM.pdf
Negative binomial regression model is an appropriate model for your data
Mahim Khan just wanted to make sure that you were aware of a very similar question, and answers, over at stats.stackexchange... https://stats.stackexchange.com/questions/67385/what-is-the-appropriate-model-for-underdispersed-count-data
SAS and spss program as analysis of statistic , I hope for you a nice day
Qusay Kh. Al_Dulamey
Hi Mahim Khan I'm having a similar problem with my data, and in my search for a way out, I came across this paper and I think it might be of help to you should your are still finding solution to the problemArticle Dealing with under- and over-dispersed count data in life hi...
- Badges
- Science topic
- Similar topics
- Mathematics
- Statistics
- Statistical Software
- R Statistical Package