Underdispersed Count Data Research Articles

Multilevel zero-inflated Generalized Poisson regression modeling for dispersed correlated count data

Poisson or zero-inflated Poisson models often fail to fit count data either because of over- or underdispersion relative to the Poisson distribution. Moreover, data may be correlated due to the hierarchical study design or the data collection methods. In this study, we propose a multilevel zero-inflated generalized Poisson regression model that can address both over- and underdispersed count data. Random effects are assumed to be independent and normally distributed. The method of parameter estimation is EM algorithm base on expectation and maximization which falls into the general framework of maximum-likelihood estimations. The performance of the approach was illustrated by data regarding an index of tooth caries on 9-year-old children. Using various dispersion parameters, through Monte Carlo simulations, the multilevel ZIGP yielded more accurate parameter estimates, especially for underdispersed data.

Two new bivariate zero-inflated generalized Poisson distributions with a flexible correlation structure

To model correlated bivariate count data with extra zero observations, this paper proposes two new bivariate zero-inflated generalized Poisson (ZIGP) distributions by incorporating a multiplicative factor (or dependency parameter) λ, named as Type I and Type II bivariate ZIGP distributions, respectively. The proposed distributions possess a flexible correlation structure and can be used to fit either positively or negatively correlated and either over- or under-dispersed count data, comparing to the existing models that can only fit positively correlated count data with over-dispersion. The two marginal distributions of Type I bivariate ZIGP share a common parameter of zero inflation while the two marginal distributions of Type II bivariate ZIGP have their own parameters of zero inflation, resulting in a much wider range of applications. The important distributional properties are explored and some useful statistical inference methods including maximum likelihood estimations of parameters, standard errors estimation, bootstrap confidence intervals and related testing hypotheses are developed for the two distributions. A real data are thoroughly analyzed by using the proposed distributions and statistical methods. Several simulation studies are conducted to evaluate the performance of the proposed methods.

Two new bivariate zero-inflated generalized Poisson distributions with a flexible correlation structure

To model correlated bivariate count data with extra zero observations, this paper proposes two new bivariate zero-inflated generalized Poisson (ZIGP) distributions by incorporating a multiplicative factor (or dependency parameter) λ, named as Type I and Type II bivariate ZIGP distributions, respectively. The proposed distributions possess a flexible correlation structure and can be used to fit either positively or negatively correlated and either over- or under-dispersed count data, comparing to the existing models that can only fit positively correlated count data with over-dispersion. The two marginal distributions of Type I bivariate ZIGP share a common parameter of zero inflation while the two marginal distributions of Type II bivariate ZIGP have their own parameters of zero inflation, resulting in a much wider range of applications. The important distributional properties are explored and some useful statistical inference methods including maximum likelihood estimations of parameters, standard errors estimation, bootstrap confidence intervals and related testing hypotheses are developed for the two distributions. A real data are thoroughly analyzed by using the proposed distributions and statistical methods. Several simulation studies are conducted to evaluate the performance of the proposed methods.

Control Charts for Dispersed Count Data: An Overview

Control charts based on the Poisson distribution are commonly used to monitor count data in attributes. However, the Poisson distribution is based on the underlying equidispersion assumption that is limiting as discussed by different researchers in the literature. Therefore, a generalized control chart is required that can be used to monitor both overdispersed and underdispersed count data. This article reviews the methods to implement for dispersed count data and present ideas for future work in this area. A comprehensive literature review for researchers and practitioners is presented in this article. Copyright © 2014 John Wiley & Sons, Ltd.

Functional Form for the Zero-Inflated Generalized Poisson Regression Model

The generalized Poisson (GP) regression is an increasingly popular approach for modeling overdispersed as well as underdispersed count data. Several parameterizations have been performed for the GP regression, and the two well known models, the GP-1 and the GP-2, have been applied. The GP-P regression, which has been recently proposed, has the advantage of nesting the GP-1 and the GP-2 parametrically, besides allowing the statistical tests of the GP-1 and the GP-2 against a more general alternative. In several cases, count data often have excessive number of zero outcomes than are expected in the Poisson. This zero-inflation phenomenon is a specific cause of overdispersion, and the zero-inflated Poisson (ZIP) regression model has been proposed. However, if the data continue to suggest additional overdispersion, the zero-inflated negative binomial (ZINB-1 and ZINB-2) and the zero-inflated generalized Poisson (ZIGP-1 and ZIGP-2) regression models have been considered as alternatives. This article proposes a functional form of the ZIGP which mixes a distribution degenerate at zero with a GP-P distribution. The suggested model has the advantage of nesting the ZIP and the two well known ZIGP (ZIGP-1 and ZIGP-2) regression models, besides allowing the statistical tests of the ZIGP-1 and the ZIGP-2 against a more general alternative. The ZIP and the functional form of the ZIGP regression models are fitted, compared and tested on two sets of count data; the Malaysian insurance claim data and the German healthcare data.

Modeling Underdispersed Count Data with Generalized Poisson Regression

We present motivation and new Stata commands for modeling count data. While the focus of this article is on modeling data with underdispersion, the new command for fitting generalized Poisson regression models is also suitable as an alternative to negative binomial regression for overdispersed data.

Semiparametric estimation for the dispersion parameter in the analysis of over- or underdispersed count data

This paper investigates several semiparametric estimators of the dispersion parameter in the analysis of over- or underdispersed count data when there is no likelihood available. In the context of estimating the dispersion parameter, we consider the double-extended quasi-likelihood (DEQL), the pseudo-likelihood and the optimal quadratic estimating (OQE) equations method and compare them with the maximum likelihood method, the method of moments and the extended quasi-likelihood through simulation study. The simulation study shows that the estimator based on the DEQL has superior bias and efficiency property for moderate and large sample size, and for small sample size the estimator based on the OQE equations outperforms the other estimators. Three real-life data sets arising in biostatistical practices are analyzed, and the findings from these analyses are quite similar to what are found from the simulation study.

Count Models Based on Weibull Interarrival Times

The widespread popularity and use of both the Poisson and the negative binomial models for count data arise, in part, from their derivation as the number of arrivals in a given time period assuming exponentially distributed interarrival times (without and with heterogeneity in the underlying base rates, respectively). However, with that clean theory come some limitations including limited flexibility in the assumed underlying arrival rate distribution and the inability to model underdispersed counts (variance less than the mean). Although extant research has addressed some of these issues, there still remain numerous valuable extensions. In this research, we present a model that, due to computational tractability, was previously thought to be infeasible. In particular, we introduce here a generalized model for count data based upon an assumed Weibull interarrival process that nests the Poisson and negative binomial models as special cases. The computational intractability is overcome by deriving the Weibull count model using a polynomial expansion which then allows for closed-form inference (integration term-by-term) when incorporating heterogeneity due to the conjugacy of the expansion and a commonly employed gamma distribution. In addition, we demonstrate that this new Weibull count model can (1) model both over- and underdispersed count data, (2) allow covariates to be introduced in a straightforward manner through the hazard function, and (3) be computed in standard software.

Generalized poisson models arising from Markov processes

We develop a family of distributions which allow for over- and underdispersion relative to the Poisson. This latter feature is particularly appealing since many existing methods only allow for overdispersion. These distributions arise from underlying continuous-time Markov processes in which event rates depend on how many events have already occurred. The results are illustrated with underdispersed count data from a polyspermy study and overdispersed data from the Canadian Sickness Survey.

Generalized hurdle count data regression models

This paper considers generalized hurdle models suitable for the analysis of overdispersed or underdispersed count data. The first stage allows for asymmetric departures from the binary logit model. An application using Medicaid utilization data is given.

COUNT DATA REGRESSION USING SERIES EXPANSIONS: WITH APPLICATIONS

SUMMARY A new class of parametric regression models for both under- and overdispersed count data is proposed. These models are based on squared polynomial expansions around a Poisson baseline density. The approach is similar to that for continuous data using squared Hermite polynomials proposed by Gallant and Nychka and applied to financial data by, among others, Gallant and Tauchen. The count models are applied to underdispersed data on the number of takeover bids received by targeted firms, and to overdispersed data on the number of visits to health practitioners. The models appear to be particularly useful for underdispersed count data. #1997 by John Wiley & Sons, Ltd.

Restricted generalized poisson regression model

The family of generalized Poisson distribution has been found useful in describing over-dispersed and under-dispersed count data. We propose the use of restricted generalized Poisson regression model to predict a response variable affected by one or more explanatory variables. Approximate tests for the adequacy of the model and the estimation of the parameters are considered. Restricted generalized Poisson regression model has been applied to an observed data set.

Generalized poisson regression model

The generalized Poisson distribution has been found useful in fitting over-dispersed as well as under-dispersed count data. Since a number of models and methods have been proposed for the regression analysis of count data either with under-dispersion or with over-dispersion, we define and study a generalized Poisson regression (GPR) model which is useful in predicting a response variable affected by one or more covariates. This regression model is suitable for both types of dispersions. The methods of maximum likelihood and moments are given for the estimation of parameters. Approximate tests for the adequacy of the model are considered. Asymptotic tests are given for the significance of regression parameters. The GPR model has been applied to four observed data sets to which other regression models were applied earlier.