Local influence diagnostics for hierarchical count data models with overdispersion and excess zeros

We consider models for hierarchical count data, subject to overdispersion and/or excess zeros. Molenberghs et al. ( 2007 ) and Molenberghs et al. ( 2010 ) extend the Poisson‐normal generalized linear‐mixed model by including gamma random effects to accommodate overdispersion. Excess zeros are handled using either a zero‐inflation or a hurdle component. These models were studied by Kassahun et al. ( 2014 ). While flexible, they are quite elaborate in parametric specification and therefore model assessment is imperative. We derive local influence measures to detect and examine influential subjects, that is subjects who have undue influence on either the fit of the model as a whole, or on specific important sub‐vectors of the parameter vector. The latter include the fixed effects for the Poisson and for the excess‐zeros components, the variance components for the normal random effects, and the parameters describing gamma random effects, included to accommodate overdispersion. Interpretable influence components are derived. The method is applied to data from a longitudinal clinical trial involving patients with epileptic seizures. Even though the data were extensively analyzed in earlier work, the insight gained from the proposed diagnostics, statistically and clinically, is considerable. Possibly, a small but important subgroup of patients has been identified.     

Testing Homogeneity of Two Zero‐inflated Poisson Populations

The problem of testing treatment difference in the occurrence of a safety parameter in a randomized parallel‐group comparative clinical trial under the assumption that the number of occurrence follows a zero‐inflated Poisson (ZIP) distribution is considered. Likelihood ratio tests (LRT) for homogeneity of two ZIP populations are derived under the hypotheses that (i) there is no difference in inflation parameters, (ii) there is no difference in non‐zero means; and (iii) there is no difference in both inflation parameters and non‐zero means. Approximate formulas for sample size calculation are also obtained for achieving a desired power for detecting a clinically meaningful difference under the corresponding alternative hypotheses. An example concerning the assessment of the gastrointestinal (GI) safety in terms of the number of erosion counts of a newly developed compound for the treatment of osteoarthritis and rheumatoid arthritis is given for illustration purpose (© 2009 WILEY‐VCH Verlag GmbH & Co. KGaA, Weinheim)     

Testing transition rates in generalized binomial models

In toxicological experiments the type II error is of important interest, but it is seldom discussed. For certain experiments like those in reproduction toxicology this paper gives some ideas to calculate it analytically. The basis is a generalized binomial model describing transition processes in experimental units. Each experimental unit contains a set of × members which develop from one to another specified state with some probability P. This transition probability P is allowed to vary from one experimental unit to the other; there is no restriction on the distribution of P and X, nor is P assumed to be independent of the total number × in contrast to the commonly used models. The model is extended to describe the treatment of an experimental unit, which permits to separate the treatment effect from the spontaneous development. This allows to investigate the power of some statistical tests for calculating sample sizes and for comparing different experimental designs.     

A score test for testing a zero-inflated Poisson regression model against zero-inflated negative binomial alternatives

Count data often show a higher incidence of zero counts than would be expected if the data were Poisson distributed. Zero-inflated Poisson regression models are a useful class of models for such data, but parameter estimates may be seriously biased if the nonzero counts are overdispersed in relation to the Poisson distribution. We therefore provide a score test for testing zero-inflated Poisson regression models against zero-inflated negative binomial alternatives.     

Semiparametric frailty models for zero‐inflated event count data in the presence of informative dropout

Recurrent events data are commonly encountered in medical studies. In many applications, only the number of events during the follow‐up period rather than the recurrent event times is available. Two important challenges arise in such studies: (a) a substantial portion of subjects may not experience the event, and (b) we may not observe the event count for the entire study period due to informative dropout. To address the first challenge, we assume that underlying population consists of two subpopulations: a subpopulation nonsusceptible to the event of interest and a subpopulation susceptible to the event of interest. In the susceptible subpopulation, the event count is assumed to follow a Poisson distribution given the follow‐up time and the subject‐specific characteristics. We then introduce a frailty to account for informative dropout. The proposed semiparametric frailty models consist of three submodels: (a) a logistic regression model for the probability such that a subject belongs to the nonsusceptible subpopulation; (b) a nonhomogeneous Poisson process model with an unspecified baseline rate function; and (c) a Cox model for the informative dropout time. We develop likelihood‐based estimation and inference procedures. The maximum likelihood estimators are shown to be consistent. Additionally, the proposed estimators of the finite‐dimensional parameters are asymptotically normal and the covariance matrix attains the semiparametric efficiency bound. Simulation studies demonstrate that the proposed methodologies perform well in practical situations. We apply the proposed methods to a clinical trial on patients with myelodysplastic syndromes.     

Flexible cloglog links for binomial regression models as an alternative for imbalanced medical data

The complementary log-log link was originally introduced in 1922 to R. A. Fisher, long before the logit and probit links. While the last two links are symmetric, the complementary log-log link is an asymmetrical link without a parameter associated with it. Several asymmetrical links with an extra parameter were proposed in the literature over last few years to deal with imbalanced data in binomial regression (when one of the classes is much smaller than the other); however, these do not necessarily have the cloglog link as a special case, with the exception of the link based on the generalized extreme value distribution. In this paper, we introduce flexible cloglog links for modeling binomial regression models that include an extra parameter associated with the link that explains some unbalancing for binomial outcomes. For all cases, the cloglog is a special case or the reciprocal version loglog link is obtained. A Bayesian Markov chain Monte Carlo inference approach is developed. Simulations study to evaluate the performance of the proposed algorithm is conducted and prior sensitivity analysis for the extra parameter shows that a uniform prior is the most convenient for all models. Additionally, two applications in medical data (age at menarche and pulmonary infection) illustrate the advantages of the proposed models.     

Darwin was right: inbreeding depression on male fertility in the Darwin family

Charles Darwin, who was married to his first cousin Emma Wedgwood, was the first experimentalist to demonstrate the adverse effects of inbreeding. He documented the deleterious consequences of self‐fertilization on progeny in numerous plant species, and this research led him to suspect that the health problems of his 10 children, who were very often ill, might have been a consequence of his marriage to his first cousin. Because Darwin's concerns regarding the consequences of cousin marriage on his children even nowadays are considered controversial, we analyzed the potential effects of inbreeding on fertility in 30 marriages of the Darwin–Wedgwood dynasty, including the marriages of Darwin's children, which correspond to the offspring of four cousin marriages and three marriages between unrelated individuals. Analysis of the number of children per woman through zero‐inflated regression models showed a significantly adverse effect of the husband inbreeding coefficient on family size. Furthermore, a statistically significant adverse effect of the husband inbreeding coefficient on reproductive period duration was also detected. To our knowledge, this is the first time that inbreeding depression on male fertility has been detected in humans. Because Darwin's sons had fewer children in comparison to non‐inbred men of the dynasty, our findings give empirical support to Darwin's concerns on the consequences of consanguineous marriage in his own progeny. © 2014 The Linnean Society of London, Biological Journal of the Linnean Society, 2015, 114 , 474–483.     

Differential measurement errors in zero-truncated regression models for count data

Measurement errors in covariates may result in biased estimates in regression analysis. Most methods to correct this bias assume nondifferential measurement errors-i.e., that measurement errors are independent of the response variable. However, in regression models for zero-truncated count data, the number of error-prone covariate measurements for a given observational unit can equal its response count, implying a situation of differential measurement errors. To address this challenge, we develop a modified conditional score approach to achieve consistent estimation. The proposed method represents a novel technique, with efficiency gains achieved by augmenting random errors, and performs well in a simulation study. The method is demonstrated in an ecology application.     

Hierarchical Bayesian Analysis of Correlated Zero‐inflated Count Data

This article presents two‐component hierarchical Bayesian models which incorporate both overdispersion and excess zeros. The components may be resultants of some intervention (treatment) that changes the rare event generating process. The models are also expanded to take into account any heterogeneity that may exist in the data. Details of the model fitting, checking and selecting alternative models from a Bayesian perspective are also presented. The proposed methods are applied to count data on the assessment of an efficacy of pesticides in controlling the reproduction of whitefly. (© 2004 WILEY‐VCH Verlag GmbH & Co. KGaA, Weinheim)     

基于负二项和零膨胀负二项回归模型的大兴安岭地区雷击火与气象因素的关系

雷击火的发生与气象因子之间存在着密切的关系。该文选用符合大兴安岭地区林火发生数据结构的负二项(negative binomial,NB)和零膨胀负二项(zero-inflated negative binomial,ZINB)两种模型对大兴安岭林区1980–2005年间雷击火的发生与气象因素间的关系进行建模分析,并与以往研究中所使用的最小二乘(OLS)回归方法相对比。使用SAS和R-Project统计软件进行模型拟合运算,计算得出模型各参数。结果表明,NB和ZINB模型对数据拟合较好,模型内各气象因子显著性水平较高,对雷击火发生次数均具有较好的预测能力。运用AIC和Vuong等检验方法,进一步比较了NB和ZINB模型对数据的拟合水平以及模型预测水平,结果表明ZINB模型无论在数据拟合还是模型预测上都要优于NB模型。提出了大兴安岭地区林火发生与气象因子关系的最优模型。     

Chain binomial models and binomial autoregressive processes

Summary We establish a connection between a class of chain‐binomial models of use in ecology and epidemiology and binomial autoregressive (AR) processes. New results are obtained for the latter, including expressions for the lag‐ conditional distribution and related quantities. We focus on two types of chain‐binomial model, extinction–colonization and colonization–extinction models, and present two approaches to parameter estimation. The asymptotic distributions of the resulting estimators are studied, as well as their finite‐sample performance, and we give an application to real data. A connection is made with standard AR models, which also has implications for parameter estimation.     

Estimating plant abundance using inflated beta distributions: Applied learnings from a lichen–caribou ecosystem

Quantifying abundance and distribution of plant species can be difficult because data are often inflated with zero values due to rarity or absence from many ecosystems. Terrestrial fruticose lichens (Cladonia and Cetraria spp.) occupy a narrow ecological niche and have been linked to the diets of declining caribou and reindeer populations (Rangifer tarandus) across their global distribution, and conditions related to their abundance and distribution are not well understood. We attempted to measure effects related to the occupancy and abundance of terrestrial fruticose lichens by sampling and simultaneously modeling two discrete conditions: absence and abundance. We sampled the proportion cover of terrestrial lichens at 438 vegetation plots, including 98 plots having zero lichens. A zero‐inflated beta regression model was employed to simultaneously estimate both the absence and the proportion cover of terrestrial fruticose lichens using fine resolution satellite imagery and light detection and ranging (LiDAR) derived covariates. The probability of lichen absence significantly increased with shallower groundwater, taller vegetation, and increased Sphagnum moss cover. Vegetation productivity, Sphagnum moss cover, and seasonal changes in photosynthetic capacity were negatively related to the abundances of terrestrial lichens. Inflated beta regression reliably estimated the abundance of terrestrial lichens (R² = .74) which was interpolated on a map at fine resolution across a caribou range to support ecological conservation and reclamation. Results demonstrate that sampling for and simultaneously estimating both occupancy and abundance offer a powerful approach to improve statistical estimation and expand ecological inference in an applied setting. Learnings are broadly applicable to studying species that are rare, occupy narrow niches, or where the response variable is a proportion value containing zero or one, which is typical of vegetation cover data.     

Testing approaches for overdispersion in poisson regression versus the generalized poisson model

Overdispersion is a common phenomenon in Poisson modeling, and the negative binomial (NB) model is frequently used to account for overdispersion. Testing approaches (Wald test, likelihood ratio test (LRT), and score test) for overdispersion in the Poisson regression versus the NB model are available. Because the generalized Poisson (GP) model is similar to the NB model, we consider the former as an alternate model for overdispersed count data. The score test has an advantage over the LRT and the Wald test in that the score test only requires that the parameter of interest be estimated under the null hypothesis. This paper proposes a score test for overdispersion based on the GP model and compares the power of the test with the LRT and Wald tests. A simulation study indicates the score test based on asymptotic standard Normal distribution is more appropriate in practical application for higher empirical power, however, it underestimates the nominal significance level, especially in small sample situations, and examples illustrate the results of comparing the candidate tests between the Poisson and GP models. A bootstrap test is also proposed to adjust the underestimation of nominal level in the score statistic when the sample size is small. The simulation study indicates the bootstrap test has significance level closer to nominal size and has uniformly greater power than the score test based on asymptotic standard Normal distribution. From a practical perspective, we suggest that, if the score test gives even a weak indication that the Poisson model is inappropriate, say at the 0.10 significance level, we advise the more accurate bootstrap procedure as a better test for comparing whether the GP model is more appropriate than Poisson model. Finally, the Vuong test is illustrated to choose between GP and NB2 models for the same dataset.     

Littoral habitat loss caused by multiyear drought and the response of an endemic fish species in a deep desert lake

相似文献   

A comparison of different ways of including baseline counts in negative binomial models for data from falls prevention trials

A common design for a falls prevention trial is to assess falling at baseline, randomize participants into an intervention or control group, and ask them to record the number of falls they experience during a follow‐up period of time. This paper addresses how best to include the baseline count in the analysis of the follow‐up count of falls in negative binomial (NB) regression. We examine the performance of various approaches in simulated datasets where both counts are generated from a mixed Poisson distribution with shared random subject effect. Including the baseline count after log‐transformation as a regressor in NB regression (NB‐logged) or as an offset (NB‐offset) resulted in greater power than including the untransformed baseline count (NB‐unlogged). Cook and Wei's conditional negative binomial (CNB) model replicates the underlying process generating the data. In our motivating dataset, a statistically significant intervention effect resulted from the NB‐logged, NB‐offset, and CNB models, but not from NB‐unlogged, and large, outlying baseline counts were overly influential in NB‐unlogged but not in NB‐logged. We conclude that there is little to lose by including the log‐transformed baseline count in standard NB regression compared to CNB for moderate to larger sized datasets.