Optimal design for count data

Journal Title: Scientific Journal of Pure and Applied Sciences - Year 2014, Vol 4, Issue 1

Abstract

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.

Authors and Affiliations

M. Abdulkabir*| Postgraduate Student University of Ilorin, Ilorin, NIGERIA., U. Anietie Edem| Mathematics and Statistics Department Federal Polytechnic, Offa, Kwara State, NIGERIA., B. Latifat Kemi| Mathematics and Statistics Department Federal Polytechnic, Offa, Kwara State, NIGERIA.

Keywords

Related Articles

Reviewing the growth and decadence of communities according to Quran and sociology

What as the main objective was followed in this article was the reasons of growth and Decadence of communities, looking to the issue was based on this issue that, Islam which is Comprehensive and complete religion ha...

Administrative corruption from sociology perspective and the relationship between administrative corruption and social s

certain principles Observance and non- Observance on organizing a social system will have Indisputable effect at the Organization. And administrative systems are not exempt from this, also the selection of the Administ...

Analyzing the constraints to private investment in manufacturing industry

This paper identifiesthe main impediments to investment and industrial productivity, which have ledto a decline in growth. This is done by analyzing the impediments andconstraints to productivity and investment using t...

The investigation of the impacts of walls and green facades on the optimization of energy consumption in buildings and i

In recent decades,artificial environments, compared to the natural spaces in urban areas, areexpanding day by day. Following the same trend in Iran, apartment living framewithout any natural space has changed. And it i...

Sociological study of affecting factors on young offenders deviant behavior aged 15 to 24 years old (case study of young

this study is implemented to evaluate affecting factors on the deviant behavior of young offenders aged 15 to 24 years old. The statically population of this study, is all 15 to 24 years old offenders on the city's ja...

Download PDF file
  • EP ID EP425
  • DOI 10.14196/sjpas.v4i1.1777
  • Views 371
  • Downloads 17

How To Cite

M. Abdulkabir*, U. Anietie Edem, B. Latifat Kemi (2014). Optimal design for count data. Scientific Journal of Pure and Applied Sciences, 4(1), 28-33. https://europub.co.uk/articles/-A-425