Employing the Double, Multiplicative and The Com-Poisson Binomial Distributions for modeling Over and Under-dispersed Binary Data
Journal Title: Journal of Advances in Mathematics and Computer Science - Year 2017, Vol 23, Issue 3
Abstract
In this paper, we compare the performances of several models for tting over-dispersed binary data. The distribution models considered in this study include the binomial (BN), the beta- binomial (BB), the multiplicative binomial (MBM), the Com-Poisson binomial (CPB) and the double binomial (DBM) models. Applications of these models to several well known data sets exhibiting under-dispersion and over-dispersion were considered in this paper. We applied these models to two frequency data sets and two data sets with covariates that have been variously analysed in the literature. The rst relates to the Portuguese version of Duke Religiosity Index in a sample of 273 (202 women, 71 Male) postgraduate students of the faculty of Medicine of University of Sao Paulo. The second set that employs the Generalize Linear Model (GLM) is the correlated binary data which studies the cardiotoxic e ects of doxorubicin chemoteraphy on the treatment of acute lymphoblastic leukemia in childhood. In the rst data set, we have a single covariate, Sex (0,1) and two covariates in the second data set (dose and time). Our results indicate that all the models considered here (excluding the binomial) behave reasonably well in modeling over-dispersed binary data with or without covariates, although both the multiplicative binomial and the double binomial models slightly behave better for these speci c data sets. While this result may not be necessarily generalized to other variety of over and under-dispersed data, we would however, encourage the investigation of all possible models so that the right applicable model can be employed for a given data set under consideration. All analyses were carried out using PROC NLMIXED in SAS.
Authors and Affiliations
Bayo H. Lawal
Keywords
Related Articles
- EP ID EP321994
- DOI 10.9734/JAMCS/2017/33475
- Views 95
- Downloads 0
On a Discrete Time Semi-Markov Risk Model with Dividends and Stochastic Premiums
A discrete semi-Markov risk model with dividends and stochastic premiums is investigated. We derive recursive equations for the expected penalty function by using the technique of probability generating function. Finally...
Oscillation of Second Order Difference Equation with a Superlinear Neutral Term
This paper deals with oscillation of certain class of second order difference equation with a superlinear neutral term. Using comparison method some new oscillation criteria are obtained. Examples are included to illustr...
A Financial Prey-predator Model with Infection in the Predator
A modified predator-prey model is proposed with logistic growth in both prey and predator populations and an infection in the predator population. This model uses ideas from the original biological Lotka-Volterra model i...
Wind Speed Equation of Circular Cyclone
This paper uses a point model of cylindrical box wrapped by zero-weighted membrane to derive a wind speed equation of circular cyclone by method of section based on Boyle’s law, Charles’ law and Newton’s laws. The obtain...
Generation of Checkered Patterns and Their Variations by Making Use of Eulerian Graph Features
A variety of pictures of checkered pattern graphics appear on the Internet. However, rarely seen is how those graphics were produced. This paper shows various checkered patterns and their variations generated automatical...