Dataset Information

Analyzing clustered count data with a cluster specific random effect zero-inflated Conway-Maxwell-Poisson distribution.

ABSTRACT: In recent years, data analysis techniques have been developed in biological and medical research areas with different types of count distributions. In particular, zero-inflated versions of parametric count distributions have been used to model excessive zeros that are often present in these assays. Perhaps, the most common count distribution which has been used for analyzing such data is the Poisson distribution. However, a Poisson distribution, having a single underlying parameter, cannot cope with any other data dispersion pattern besides equidispersion. A negative binomial distribution is capable of modeling overdispersed, but not underdispersed data. However, a Conway-Maxwell-Poisson (CMP) distribution (Conway, R. W., and Maxwell, W. L., 1962) can handle not only overdispersion but also underdispersion. We show with an illustrative data set on next generation sequencing of maize hybrids that both underdispersion and overdispersion can be present in genetic data. Furthermore, if count data consists of clustered observations, one of the most efficient statistical technique is to introduce a cluster specific random effect term. Once again, the maize hybrids data presents such a situation. We develop inference procedures for a zero-inflated CMP regression that incorporates a cluster specific random effect term. Unlike, the Gaussian models, the underlying likelihood is computationally challenging. We use a numerical approximation via a Gaussian quadrature to circumvent this issues. A test for checking zero-inflation has also been developed in our setting. Finite sample properties of our estimators and test have been investigated by extensive simulations. Finally, the statistical methodology has been applied to analyze the maize data mentioned before.

SUBMITTER: Choo-Wosoba H

PROVIDER: S-EPMC6510495 | biostudies-literature | 2018

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Analyzing clustered count data with a cluster specific random effect zero-inflated Conway-Maxwell-Poisson distribution.

Choo-Wosoba Hyoyoung H Datta Somnath S

Journal of applied statistics 20170408 5

In recent years, data analysis techniques have been developed in biological and medical research areas with different types of count distributions. In particular, zero-inflated versions of parametric count distributions have been used to model excessive zeros that are often present in these assays. Perhaps, the most common count distribution which has been used for analyzing such data is the Poisson distribution. However, a Poisson distribution, having a single underlying parameter, cannot cope ...[more]

PMID: 31080303

Similar Datasets

Project description:BackgroundThe assessment of methods for analyzing over-dispersed zero inflated count outcome has received very little or no attention in stratified cluster randomized trials. In this study, we performed sensitivity analyses to empirically compare eight methods for analyzing zero inflated over-dispersed count outcome from the Vitamin D and Osteoporosis Study (ViDOS) - originally designed to assess the feasibility of a knowledge translation intervention in long-term care home setting.MethodForty long-term care (LTC) homes were stratified and then randomized into knowledge translation (KT) intervention (19 homes) and control (21 homes) groups. The homes/clusters were stratified by home size (<250/> = 250) and profit status (profit/non-profit). The outcome of this study was number of falls measured at 6-month post-intervention. The following methods were used to assess the effect of KT intervention on number of falls: i) standard Poisson and negative binomial regression; ii) mixed-effects method with Poisson and negative binomial distribution; iii) generalized estimating equation (GEE) with Poisson and negative binomial; iv) zero inflated Poisson and negative binomial - with the latter used as a primary approach. All these methods were compared with or without adjusting for stratification.ResultsA total of 5,478 older people from 40 LTC homes were included in this study. The mean (=1) of the number of falls was smaller than the variance (=6). Also 72% and 46% of the number of falls were zero in the control and intervention groups, respectively. The direction of the estimated incidence rate ratios (IRRs) was similar for all methods. The zero inflated negative binomial yielded the lowest IRRs and narrowest 95% confidence intervals when adjusted for stratification compared to GEE and mixed-effect methods. Further, the widths of the 95% confidence intervals were narrower when the methods adjusted for stratification compared to the same method not adjusted for stratification.ConclusionThe overall conclusion from the GEE, mixed-effect and zero inflated methods were similar. However, these methods differ in terms of effect estimate and widths of the confidence interval.Trial registrationClinicalTrials.gov: NCT01398527. Registered: 19 July 2011.

Project description:BackgroundTsetse flies are the major vectors of human trypanosomiasis of the form Trypanosoma brucei rhodesiense and T.b.gambiense. They are widely spread across the sub-Saharan Africa and rendering a lot of challenges to both human and animal health. This stresses effective agricultural production and productivity in Africa. Delimiting the extent and magnitude of tsetse coverage has been a challenge over decades due to limited resources and unsatisfactory technology. In a bid to overcome these limitations, this study attempted to explore modelling skills that can be applied to spatially estimate tsetse abundance in the country using limited tsetse data and a set of remote-sensed environmental variables.MethodologyEntomological data for the period 2008-2018 as used in the model were obtained from various sources and systematically assembled using a structured protocol. Data harmonisation for the purposes of responsiveness and matching was carried out. The key tool for tsetse trapping was itemized as pyramidal trap in many instances and biconical trap in others. Based on the spatially explicit assembled data, we ran two regression models; standard Poisson and Zero-Inflated Poisson (ZIP), to explore the associations between tsetse abundance in Uganda and several environmental and climatic covariates. The covariate data were constituted largely by satellite sensor data in form of meteorological and vegetation surrogates in association with elevation and land cover data. We finally used the Zero-Inflated Poisson (ZIP) regression model to predict tsetse abundance due to its superiority over the standard Poisson after model fitting and testing using the Vuong Non-Nested statistic.ResultsA total of 1,187 tsetse sampling points were identified and considered as representative for the country. The model results indicated the significance and level of responsiveness of each covariate in influencing tsetse abundance across the study area. Woodland vegetation, elevation, temperature, rainfall, and dry season normalised difference vegetation index (NDVI) were important in determining tsetse abundance and spatial distribution at varied scales. The resultant prediction map shows scaled tsetse abundance with estimated fitted numbers ranging from 0 to 59 flies per trap per day (FTD). Tsetse abundance was found to be largest at low elevations, in areas of high vegetative activity, in game parks, forests and shrubs during the dry season. There was very limited responsiveness of selected predictors to tsetse abundance during the wet season, matching the known fact that tsetse disperse most significantly during wet season.ConclusionsA methodology was advanced to enable compilation of entomological data for 10 years, which supported the generation of tsetse abundance maps for Uganda through modelling. Our findings indicate the spatial distribution of the G. f. fuscipes as; low 0-5 FTD (48%), medium 5.1-35 FTD (18%) and high 35.1-60 FTD (34%) grounded on seasonality. This approach, amidst entomological data shortages due to limited resources and absence of expertise, can be adopted to enable mapping of the vector to provide better decision support towards designing and implementing targeted tsetse and tsetse-transmitted African trypanosomiasis control strategies.

Dataset Information

Analyzing clustered count data with a cluster specific random effect zero-inflated Conway-Maxwell-Poisson distribution.

Publications

Analyzing clustered count data with a cluster specific random effect zero-inflated Conway-Maxwell-Poisson distribution.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets