Question

2. For this problem the Horseshoe Crab Mating is going to be used. The description can be found in Agresti page 123. To obtain the data you need to run the following R codes, ## Horseshoe Crab data ## ## To install the package rsq install.packages('rsq') library(rsq) data(hcrabs) (i) Execute a Poisson regression to estimate the mean number of satellites using all the other covariates (ii) Execute a negative binomial regression to estimate the mean number of satellites using all the other covariates (iii) Compare the models. Which model performed better

Answer 1

We can test whether poisson regression is better than the negative binomial distribution by following ways

1. AIC criterion whichever model that has less AIC is good model

2.by performing the ANOVA test for two models

3.likelihood ratio test

4.overdispersion test

By using these four criterion negative binomial is better than poisson regression

I am. Sending the file containing r commandscommandsñ

1ibrary(rsqD 2 Tibrarycar 3 library(MASS) 4 data herabs head (data) attach(data) pois modelgim(num. satellites-,data-data,fami ly summary (pois model) 10 11 "poisson") = negative model-glm. nb(num. satellites ,data-=data ) summary (negative mode1) 12 13 14 anova-anova(pois model,negative model) 16 15 summary(anova) 17 logLik(pois model) 18 logLik(negative model) 19 Tibrarymtest) 20 rtest (pois_model,negative model) 21 rtest (negative_model, pois model) 22 23 24 25 26 1ibrary psc1) 27 odTest (negative model) 28