Optimal design for count data

Optimal designs for generalized linear models (GLM) have received increasing attention in recent years. Most of this research focuses on binary data model. This research extends to count data models. The aim and objectives of this research work to determine the appropriate generalized linear model (GLM) that is suitable for count data and identify a design that is best according to statistical optimality criteria, the data use for this research work are simulated data from R statistical package using uniform distribution with sample size 300. The simplest distribution use for modeling count data is Poisson distribution, quasi Poisson were carried out to test for over dispersion in the Poisson regression model and the formal way of dealing with over dispersion is negative binomial regression model, thus AIC was use to compare the two models, the Poisson regression model shows the best with minimum AIC. Furthermore optimal design were carried out using the optimality criterion that is the A and D optimality criterion, using design efficiency to compare the two (2) designs the optimality criterion with the highest efficiency is the best, thus D optimality criterion shows the best design