The Zero-Inflated Poisson Model and the Decayed, Missing and Filled Teeth Index in Dental Epidemiology

Abstract

For frequency counts, the situation of extra zeros often arises in biomedical applications. This is demonstrated with count data from a dental epidemiological study in Belo Horizonte (the Belo Horizonte caries prevention study) which evaluated various programmes for reducing caries. Extra zeros, however, violate the variance±mean relationship of the Poisson error structure. This extra-Poisson variation can easily be explained by a special mixture model, the zero-in¯ated Poisson (ZIP) model. On the basis of the ZIP model, a graphical device is presented which not only summarizes the mixing distribution but also provides visual information about the overall mean. This device can be exploited to evaluate and compare various groups. Ways are discussed to include covariates and to develop an extension of the conventional Poisson regression. Finally, a method to evaluate intervention effects on the basis of the ZIP regression model is described and applied to the data of the Belo Horizonte caries prevention study.

Finite Mixtures of Generalized Linear Regression Models

“…This approach is similar to the specification of zero-inflated models (Böhning et al, 1999). Even though the component specific densities are in general assumed to be from the same parametric family (e.g.…”

What belongs where? Variable selection for zero-inflated count models with an application to the demand for health care

“…Zero-inflated count models (Mullahy, 1986;Lambert, 1992) account for this data characteristic and are frequently used in the literature. Among others, Grootendorst (1995) analyses prescription drug utilisation, Street et al (1999) examine data on pharmaceutical utilisation and expenditure in Russia and Böhning et al (1999) consider caries prevention in dental epidemiology.…”

Zero Inflated Poisson and Geographically Weighted Zero- Inflated Poisson Regression Model: Application to Elephantiasis (Filariasis) Counts Data

“…However this method assumes the equidispersion of the data (Bohning et al, 1999). Unfortunately this assumption is often violated in the observed data because data are often overdispersed.…”

“…Some of them are Lestari (2008) modeled counts data of commercial sex worker at Clinic for human reproduction, Putat Jaya, Surabaya; Bohning et al (1999) used ZIP to analyze counts data on prevention of dental caries in children; and Mouatassim and Ezzahid (2012) fitted models to the number of claims in a private health insurance scheme. Those research themes showed that ZIP Regression fitted counts data better than Poisson Regression.…”