A non-stationary integer-valued autoregressive model

It is frequent to encounter a time series of counts which are small in value and show a trend having relatively large fluctuation. To handle such a non-stationary integer-valued time series with a large dispersion, we introduce a new process called integer-valued autoregressive process of order p with signed binomial thinning (INARS(p)). This INARS(p) uniquely exists and is stationary under the same stationary condition as in the AR(p) process. We provide the properties of the INARS(p) as well as the asymptotic normality of the estimates of the model parameters. This new process includes previous integer-valued autoregressive processes as special cases. To preserve integer-valued nature of the INARS(p) and to avoid difficulty in deriving the distributional properties of the forecasts, we propose a bootstrap approach for deriving forecasts and confidence intervals. We apply the INARS(p) to the frequency of new patients diagnosed with acquired immunodeficiency syndrome (AIDS) in Baltimore, Maryland, U.S. during the period of 108 months from January 1993 to December 2001.     

One mixed negative binomial distribution with application

In this paper we do some research on a three-parameter distribution which is called beta-negative binomial (BNB) distribution, a beta mixture of negative binomial (NB) distribution. The closed form and the factorial moment of the BNB distribution are derived. In addition, we present the recursion on the pdf of BNB stopped-sum distribution, and make stochastic comparison between BNB and NB distributions. Furthermore, we have shown that BNB distribution has heavier tail than NB distribution. The application of BNB distribution is carried out on one sample of insurance data. Based on the results, we have shown that the BNB provides a better fit compared to the Poisson and the NB for count data.     

Testing homogeneity in clustered (longitudinal) count data regression model with over-dispersion

Clustered (longitudinal) count data arise in many bio-statistical practices in which a number of repeated count responses are observed on a number of individuals. The repeated observations may also represent counts over time from a number of individuals. One important problem that arises in practice is to test homogeneity within clusters (individuals) and between clusters (individuals). As data within clusters are observations of repeated responses, the count data may be correlated and/or over-dispersed. For over-dispersed count data with unknown over-dispersion parameter we derive two score tests by assuming a random intercept model within the framework of (i) the negative binomial mixed effects model and (ii) the double extended quasi-likelihood mixed effects model (Lee and Nelder, 2001). These two statistics are much simpler than a statistic derived by Jacqmin-Gadda and Commenges (1995) under the framework of the over-dispersed generalized linear model. The first statistic takes the over-dispersion more directly into the model and therefore is expected to do well when the model assumptions are satisfied and the other statistic is expected to be robust. Simulations show superior level property of the statistics derived under the negative binomial and double extended quasi-likelihood model assumptions. A data set is analyzed and a discussion is given.     

Poisson-mixed Inverse Gaussian Regression Model and Its Application

In this article, we have developed a Poisson-mixed inverse Gaussian (PMIG) distribution. The mixed inverse Gaussian distribution is a mixture of the inverse Gaussian distribution and its length-biased counterpart. A PMIG regression model is developed and the maximum likelihood estimation of the parameters is studied. A dataset dealing with the number of hospital stays among the elderly population is analyzed by using the PMIG and the PIG (Poisson-inverse Gaussian) regression models and it has been shown that the PMIG model fits the data better than the PIG model.     

Comparing Joint GQL Estimation and GMM Adaptive Estimation in COM-Poisson Longitudinal Regression Model

It is of scientific interest to study the application of COM-Poisson model to the case of longitudinal response data, the analysis of which is quite challenging due to the fact that longitudinal responses of a subject are correlated and the correlation pattern is usually unknown. In this article, we extend the COM-Poisson GLM to the generalized linear longitudinal model. We also develop a joint generalized quasi-likelihood estimating equation approach based on a stationary autocorrelation structure for the repeated count data. We further compare the performance of this estimation method with that of Generalized Method of Moments through a simulation study.     

Data Dispersion: Now You See It… Now You Don't

Poisson regression is the most well-known method for modeling count data. When data display over-dispersion, thereby violating the underlying equi-dispersion assumption of Poisson regression, the common solution is to use negative-binomial regression. We show, however, that count data that appear to be equi- or over-dispersed may actually stem from a mixture of populations with different dispersion levels. To detect and model such a mixture, we introduce a generalization of the Conway-Maxwell-Poisson (COM-Poisson) regression model that allows for group-level dispersion. We illustrate mixed dispersion effects and the proposed methodology via semi-authentic data.     

Analysis of one-way layout of count data in the presence of over or under dispersion

This article develops test statistics for the homogeneity of the means of several treatment groups of count data in the presence of over-dispersion or under-dispersion when there is no likelihood available. The C(α)$C(\alpha )$ or score type tests based on the models that are specified by only the first two moments of the counts are obtained using quasi-likelihood, extended quasi-likelihood, and double extended quasi-likelihood. Monte Carlo simulations are then used to study the comparative behavior of these C(α)$C(\alpha )$ statistics compared to the C(α)$C(\alpha )$ statistic based on a parametric model, namely, the negative binomial model, in terms of the following: size; power; robustness for departures from the data distribution as well as dispersion homogeneity. These simulations demonstrate that the C(α)$C(\alpha )$ statistic based on the double extended quasi-likelihood holds the nominal size at the 5% level well in all data situations, and it shows some edge in power over the other statistics, and, in particular, it performs much better than the commonly used statistic based on the quasi-likelihood. This C(α)$C(\alpha )$ statistic also shows robustness for moderate heterogeneity due to dispersion. Finally, applications to ecological, toxicological and biological data are given.