A note on type II error under random effects misspecification in generalized linear mixed models

Litière, Alonso, and Molenberghs (2007, Biometrics, 63, 1038-1044) presented the results of simulation studies that they claimed showed that misspecification of the shape of the random effects distribution can produce marked increases in Type II error (decreases in power) of tests based on fits of generalized linear mixed models. However, the article contains a logical fallacy that invalidates this claim. We present logically correct simulation studies that demonstrate little increase in Type II error, consistent with the earlier work that shows little effect due to misspecification.     

Laplace approximation in measurement error models

Likelihood analysis for regression models with measurement errors in explanatory variables typically involves integrals that do not have a closed-form solution. In this case, numerical methods such as Gaussian quadrature are generally employed. However, when the dimension of the integral is large, these methods become computationally demanding or even unfeasible. This paper proposes the use of the Laplace approximation to deal with measurement error problems when the likelihood function involves high-dimensional integrals. The cases considered are generalized linear models with multiple covariates measured with error and generalized linear mixed models with measurement error in the covariates. The asymptotic order of the approximation and the asymptotic properties of the Laplace-based estimator for these models are derived. The method is illustrated using simulations and real-data analysis.     

Joint generalized models for multidimensional outcomes: A case study of neuroscience data from multimodalities

This paper is motivated from the analysis of neuroscience data in a study of neural and muscular mechanisms of muscle fatigue. Multidimensional outcomes of different natures were obtained simultaneously from multiple modalities, including handgrip force, electromyography (EMG), and functional magnetic resonance imaging (fMRI). We first study individual modeling of the univariate response depending on its nature. A mixed‐effects beta model and a mixed‐effects simplex model are compared for modeling the force/EMG percentages. A mixed‐effects negative‐binomial model is proposed for modeling the fMRI counts. Then, I present a joint modeling approach to model the multidimensional outcomes together, which allows us to not only estimate the covariate effects but also to evaluate the strength of association among the multiple responses from different modalities. A simulation study is conducted to quantify the possible benefits by the new approaches in finite sample situations. Finally, the analysis of the fatigue data is illustrated with the use of the proposed methods.     

Scales of association: hierarchical linear models and the measurement of ecological systems

A fundamental challenge to understanding patterns in ecological systems lies in employing methods that can analyse, test and draw inference from measured associations between variables across scales. Hierarchical linear models (HLM) use advanced estimation algorithms to measure regression relationships and variance–covariance parameters in hierarchically structured data. Although hierarchical models have occasionally been used in the analysis of ecological data, their full potential to describe scales of association, diagnose variance explained, and to partition uncertainty has not been employed. In this paper we argue that the use of the HLM framework can enable significantly improved inference about ecological processes across levels of organization. After briefly describing the principals behind HLM, we give two examples that demonstrate a protocol for building hierarchical models and answering questions about the relationships between variables at multiple scales. The first example employs maximum likelihood methods to construct a two-level linear model predicting herbivore damage to a perennial plant at the individual- and patch-scale; the second example uses Bayesian estimation techniques to develop a three-level logistic model of plant flowering probability across individual plants, microsites and populations. HLM model development and diagnostics illustrate the importance of incorporating scale when modelling associations in ecological systems and offer a sophisticated yet accessible method for studies of populations, communities and ecosystems. We suggest that a greater coupling of hierarchical study designs and hierarchical analysis will yield significant insights on how ecological processes operate across scales.     

Uncovering the drivers of host‐associated microbiota with joint species distribution modelling

In addition to the processes structuring free‐living communities, host‐associated microbiota are directly or indirectly shaped by the host. Therefore, microbiota data have a hierarchical structure where samples are nested under one or several variables representing host‐specific factors, often spanning multiple levels of biological organization. Current statistical methods do not accommodate this hierarchical data structure and therefore cannot explicitly account for the effect of the host in structuring the microbiota. We introduce a novel extension of joint species distribution models (JSDMs) which can straightforwardly accommodate and discern between effects such as host phylogeny and traits, recorded covariates such as diet and collection site, among other ecological processes. Our proposed methodology includes powerful yet familiar outputs seen in community ecology overall, including (a) model‐based ordination to visualize and quantify the main patterns in the data; (b) variance partitioning to assess how influential the included host‐specific factors are in structuring the microbiota; and (c) co‐occurrence networks to visualize microbe‐to‐microbe associations.     

Pattern‐Mixture Zero‐Inflated Mixed Models for Longitudinal Unbalanced Count Data with Excessive Zeros

Analysis of longitudinal data with excessive zeros has gained increasing attention in recent years; however, current approaches to the analysis of longitudinal data with excessive zeros have primarily focused on balanced data. Dropouts are common in longitudinal studies; therefore, the analysis of the resulting unbalanced data is complicated by the missing mechanism. Our study is motivated by the analysis of longitudinal skin cancer count data presented by Greenberg, Baron, Stukel, Stevens, Mandel, Spencer, Elias, Lowe, Nierenberg, Bayrd, Vance, Freeman, Clendenning, Kwan, and the Skin Cancer Prevention Study Group[New England Journal of Medicine 323 , 789–795]. The data consist of a large number of zero responses (83% of the observations) as well as a substantial amount of dropout (about 52% of the observations). To account for both excessive zeros and dropout patterns, we propose a pattern‐mixture zero‐inflated model with compound Poisson random effects for the unbalanced longitudinal skin cancer data. We also incorporate an autoregressive of order 1 correlation structure in the model to capture longitudinal correlation of the count responses. A quasi‐likelihood approach has been developed in the estimation of our model. We illustrated the method with analysis of the longitudinal skin cancer data.     

A Bayesian Approach to Joint Mixed‐Effects Models with a Skew‐Normal Distribution and Measurement Errors in Covariates

Summary In recent years, nonlinear mixed‐effects (NLME) models have been proposed for modeling complex longitudinal data. Covariates are usually introduced in the models to partially explain intersubject variations. However, one often assumes that both model random error and random effects are normally distributed, which may not always give reliable results if the data exhibit skewness. Moreover, some covariates such as CD4 cell count may be often measured with substantial errors. In this article, we address these issues simultaneously by jointly modeling the response and covariate processes using a Bayesian approach to NLME models with covariate measurement errors and a skew‐normal distribution. A real data example is offered to illustrate the methodologies by comparing various potential models with different distribution specifications. It is showed that the models with skew‐normality assumption may provide more reasonable results if the data exhibit skewness and the results may be important for HIV/AIDS studies in providing quantitative guidance to better understand the virologic responses to antiretroviral treatment.     

A relative survival model for clustered responses

Relative Survival is the ratio of the overall survival of a group of patients to the expected survival for a demographically similar group. It is commonly used in disease registries to estimate the effect of a particular disease when the true cause of death is not reliably known. Regression models for relative survival have been described and we extend these models to allow for clustered responses by embedding them into the class of Generalized linear mixed models (GLMM). The method is motivated and demonstrated by a data set from the HALLUCA study, an epidemiological study which investigated provision of medical care to lung cancer patients in the region of Halle in the eastern part of Germany.     

A note on deletion diagnostics for estimating equations

We describe an algorithm based upon the Sherman–Morrison–Woodburyformula for the inversion of matrices with special structurethat occur in formulae for deletion diagnostics. Substantialcomputational savings relative to a method based upon Cholesky'sdecomposition are illustrated. The result has broad applicationto regression diagnostics for clustered data.     

Parameterization of Multivariate Random Effects Models for Categorical Data

Alternative parameterizations and problems of identification and estimation of multivariate random effects models for categorical responses are investigated. The issues are illustrated in the context of the multivariate binomial logit-normal (BLN) model introduced by Coull and Agresti (2000, Biometrics 56, 73-80). We demonstrate that the BLN model is poorly identified unless proper restrictions are imposed on the parameters. Moreover, estimation of BLN models is unduly computationally complex. In the first application considered by Coull and Agresti, an identification problem results in highly unstable, highly correlated parameter estimates and large standard errors. A probit-normal version of the specified BLN model is demonstrated to be underidentified, whereas the BLN model is empirically underidentified. Identification can be achieved by constraining one of the parameters. We show that a one-factor probit model is equivalent to the probit version of the specified BLN model and that a one-factor logit model is empirically equivalent to the BLN model. Estimation is greatly simplified by using a factor model.