A mixed effect model for bivariate meta‐analysis of diagnostic test accuracy studies using a copula representation of the random effects distribution

Diagnostic test accuracy studies typically report the number of true positives, false positives, true negatives and false negatives. There usually exists a negative association between the number of true positives and true negatives, because studies that adopt less stringent criterion for declaring a test positive invoke higher sensitivities and lower specificities. A generalized linear mixed model (GLMM) is currently recommended to synthesize diagnostic test accuracy studies. We propose a copula mixed model for bivariate meta‐analysis of diagnostic test accuracy studies. Our general model includes the GLMM as a special case and can also operate on the original scale of sensitivity and specificity. Summary receiver operating characteristic curves are deduced for the proposed model through quantile regression techniques and different characterizations of the bivariate random effects distribution. Our general methodology is demonstrated with an extensive simulation study and illustrated by re‐analysing the data of two published meta‐analyses. Our study suggests that there can be an improvement on GLMM in fit to data and makes the argument for moving to copula random effects models. Our modelling framework is implemented in the package CopulaREMADA within the open source statistical environment R . Copyright © 2015 John Wiley & Sons, Ltd.     

The statistical performance of an MCF-7 cell culture assay evaluated using generalized linear mixed models and a score test

Biological assays often utilize experimental designs where observations are replicated at multiple levels, and where each level represents a separate component of the assay's overall variance. Statistical analysis of such data usually ignores these design effects, whereas more sophisticated methods would improve the statistical power of assays. This report evaluates the statistical performance of an in vitro MCF-7 cell proliferation assay (E-SCREEN) by identifying the optimal generalized linear mixed model (GLMM) that accurately represents the assay's experimental design and variance components. Our statistical assessment found that 17beta-oestradiol cell culture assay data were best modelled with a GLMM configured with a reciprocal link function, a gamma error distribution, and three sources of design variation: plate-to-plate; well-to-well, and the interaction between plate-to-plate variation and dose. The gamma-distributed random error of the assay was estimated to have a coefficient of variation (COV) = 3.2 per cent, and a variance component score test described by X. Lin found that each of the three variance components were statistically significant. The optimal GLMM also confirmed the estrogenicity of five weakly oestrogenic polychlorinated biphenyls (PCBs 17, 49, 66, 74, and 128). Based on information criteria, the optimal gamma GLMM consistently out-performed equivalent naive normal and log-normal linear models, both with and without random effects terms. Because the gamma GLMM was by far the best model on conceptual and empirical grounds, and requires only trivially more effort to use, we encourage its use and suggest that naive models be avoided when possible.     

Statistical models for autocorrelated count data

A generalized linear mixed model is an increasingly popular choice for the modelling of correlated, non-normal responses in a regression setting. A number of methods are currently available for fitting a generalized linear mixed model including Monte-Carlo Markov-Chain maximum likelihood algorithms, approximate maximum likelihood (PQL), iterative bias correction, and others. Of interest in this paper is to compare the parameter estimation of the various methods in the modelling of a count data set, the incidence of polio in the USA over the period 1970-1983, using a longlinear generalized linear mixed model with an autoregressive correlation structure. Despite the fact that all of these methods are considered valid modelling techniques, we find that parameter estimates and standard errors differ substantially between analyses, particularly in the estimation of the parameters describing the random effects distribution. A small simulation study is helpful in understanding some of these differences. The methods lead to reasonably similar predictions for future observations, with small differences observed in some monthly counts.     

Proportional hazards model with random effects

We propose a general proportional hazards model with random effects for handling clustered survival data. This generalizes the usual frailty model by allowing a multivariate random effect with arbitrary design matrix in the log relative risk, in a way similar to the modelling of random effects in linear, generalized linear and non-linear mixed models. The distribution of the random effects is generally assumed to be multivariate normal, but other (preferably symmetrical) distributions are also possible. Maximum likelihood estimates of the regression parameters, the variance components and the baseline hazard function are obtained via the EM algorithm. The E-step of the algorithm involves computation of the conditional expectations of functions of the random effects, for which we use Markov chain Monte Carlo (MCMC) methods. Approximate variances of the estimates are computed by Louis' formula, and posterior expectations and variances of the individual random effects can be obtained as a by-product of the estimation. The inference procedure is exemplified on two data sets.     

A Bayesian semiparametric model for bivariate sparse longitudinal data

Mixed‐effects models have recently become popular for analyzing sparse longitudinal data that arise naturally in biological, agricultural and biomedical studies. Traditional approaches assume independent residuals over time and explain the longitudinal dependence by random effects. However, when bivariate or multivariate traits are measured longitudinally, this fundamental assumption is likely to be violated because of intertrait dependence over time. We provide a more general framework where the dependence of the observations from the same subject over time is not assumed to be explained completely by the random effects of the model. We propose a novel, mixed model‐based approach and estimate the error–covariance structure nonparametrically under a generalized linear model framework. We use penalized splines to model the general effect of time, and we consider a Dirichlet process mixture of normal prior for the random‐effects distribution. We analyze blood pressure data from the Framingham Heart Study where body mass index, gender and time are treated as covariates. We compare our method with traditional methods including parametric modeling of the random effects and independent residual errors over time. We conduct extensive simulation studies to investigate the practical usefulness of the proposed method. The current approach is very helpful in analyzing bivariate irregular longitudinal traits. Copyright © 2013 John Wiley & Sons, Ltd.     

A class of generalized linear mixed models adjusted for marginal interpretability

Two popular approaches for relating correlated measurements of a non‐Gaussian response variable to a set of predictors are to fit a marginal model using generalized estimating equations and to fit a generalized linear mixed model (GLMM) by introducing latent random variables. The first approach is effective for parameter estimation, but leaves one without a formal model for the data with which to assess quality of fit or make individual‐level predictions for future observations. The second approach overcomes these deficiencies, but leads to parameter estimates that must be interpreted conditional on the latent variables. To obtain marginal summaries, one needs to evaluate an analytically intractable integral or use attenuation factors as an approximation. Further, we note an unpalatable implication of the standard GLMM. To resolve these issues, we turn to a class of marginally interpretable GLMMs that lead to parameter estimates with a marginal interpretation while maintaining the desirable statistical properties of a conditionally specified model and avoiding problematic implications. We establish the form of these models under the most commonly used link functions and address computational issues. For logistic mixed effects models, we introduce an accurate and efficient method for evaluating the logistic‐normal integral.     

A comparison of seven random‐effects models for meta‐analyses that estimate the summary odds ratio

Comparative trials that report binary outcome data are commonly pooled in systematic reviews and meta‐analyses. This type of data can be presented as a series of 2‐by‐2 tables. The pooled odds ratio is often presented as the outcome of primary interest in the resulting meta‐analysis. We examine the use of 7 models for random‐effects meta‐analyses that have been proposed for this purpose. The first of these models is the conventional one that uses normal within‐study approximations and a 2‐stage approach. The other models are generalised linear mixed models that perform the analysis in 1 stage and have the potential to provide more accurate inference. We explore the implications of using these 7 models in the context of a Cochrane Review, and we also perform a simulation study. We conclude that generalised linear mixed models can result in better statistical inference than the conventional 2‐stage approach but also that this type of model presents issues and difficulties. These challenges include more demanding numerical methods and determining the best way to model study specific baseline risks. One possible approach for analysts is to specify a primary model prior to performing the systematic review but also to present the results using other models in a sensitivity analysis. Only one of the models that we investigate is found to perform poorly so that any of the other models could be considered for either the primary or the sensitivity analysis.     

Residual spatial correlation between geographically referenced observations: a Bayesian hierarchical modeling approach

BACKGROUND: Analytic methods commonly used in epidemiology do not account for spatial correlation between observations. In regression analyses, this omission can bias parameter estimates and yield incorrect standard error estimates. We present a Bayesian hierarchical model (BHM) approach that accounts for spatial correlation, and illustrate its strengths and weaknesses by applying this modeling approach to data on Wuchereria bancrofti infection in Haiti. METHODS: A program to eliminate lymphatic filariasis in Haiti assessed prevalence of W. bancrofti infection in 57 schools across Leogane Commune. We analyzed the spatial pattern in the prevalence data using semi-variograms and correlograms. We then modeled the data using (1) standard logistic regression (GLM); (2) non-Bayesian logistic generalized linear mixed models (GLMMs) with school-specific nonspatial random effects; (3) BHMs with school-specific nonspatial random effects; and (4) BHMs with spatial random effects. RESULTS: An exponential semi-variogram with an effective range of 2.15 km best fit the data. GLMM and nonspatial BHM point estimates were comparable and also were generally similar with the marginal GLM point estimates. In contrast, compared with the nonspatial mixed model results, spatial BHM point estimates were markedly attenuated. DISCUSSION: The clear spatial pattern evident in the Haitian W. bancrofti prevalence data and the observation that point estimates and standard errors differed depending on the modeling approach indicate that it is important to account for residual spatial correlation in analyses of W. bancrofti infection data. Bayesian hierarchical models provide a flexible, readily implementable approach to modeling spatially correlated data. However, our results also illustrate that spatial smoothing must be applied with care.     

Performance of analytical methods for overdispersed counts in cluster randomized trials: Sample size,degree of clustering and imbalance

Many different methods have been proposed for the analysis of cluster randomized trials (CRTs) over the last 30 years. However, the evaluation of methods on overdispersed count data has been based mostly on the comparison of results using empiric data; i.e. when the true model parameters are not known. In this study, we assess via simulation the performance of five methods for the analysis of counts in situations similar to real community‐intervention trials. We used the negative binomial distribution to simulate overdispersed counts of CRTs with two study arms, allowing the period of time under observation to vary among individuals. We assessed different sample sizes, degrees of clustering and degrees of cluster‐size imbalance. The compared methods are: (i) the two‐sample t‐test of cluster‐level rates, (ii) generalized estimating equations (GEE) with empirical covariance estimators, (iii) GEE with model‐based covariance estimators, (iv) generalized linear mixed models (GLMM) and (v) Bayesian hierarchical models (Bayes‐HM). Variation in sample size and clustering led to differences between the methods in terms of coverage, significance, power and random‐effects estimation. GLMM and Bayes‐HM performed better in general with Bayes‐HM producing less dispersed results for random‐effects estimates although upward biased when clustering was low. GEE showed higher power but anticonservative coverage and elevated type I error rates. Imbalance affected the overall performance of the cluster‐level t‐test and the GEE's coverage in small samples. Important effects arising from accounting for overdispersion are illustrated through the analysis of a community‐intervention trial on Solar Water Disinfection in rural Bolivia. Copyright © 2009 John Wiley & Sons, Ltd.     

A robust Bayesian mixed effects approach for zero inflated and highly skewed longitudinal count data emanating from the zero inflated discrete Weibull distribution

This article proposes a Bayesian mixed effects zero inflated discrete Weibull (ZIDW) regression model for zero inflated and highly skewed longitudinal count data, as an alternative to mixed effects regression models that are based on the negative binomial, zero inflated negative binomial, and conventional discrete Weibull (DW) distributions. The mixed effects ZIDW regression model is an extension of a recently introduced model based on the DW distribution and uses the log-link function to specify the relationship between the linear predictors and the median counts. The ZIDW approach offers a more robust characteristic of central tendency, compared to the mean count, when there is skewness in the data. A matrix generalized half-t (MGH-t) prior distribution is specified for the random effects covariance matrix as an alternative to the widely used Wishart prior distribution. The methodology is applied to a longitudinal dataset from an epilepsy clinical trial. In a data contamination simulation study, we show that the mixed effect ZIDW regression model is more robust than the competing mixed effects regression models when the data contain excess zeros or outliers. The performance of the ZIDW regression model is also assessed in a simulation study under the specification of, respectively, the MGH-t and Wishart prior distributions for the random effects covariance matrix. It turns out that the highest posterior density intervals under the MGH-t prior for the fixed effects maintain nominal coverage when the true variability between random slopes over time is small, whereas those under the Wishart prior are generally conservative.     

A comparison of the generalized estimating equation approach with the maximum likelihood approach for repeated measurements

Liang and Zeger proposed an extension of generalized linear models to the analysis of longitudinal data. Their approach is closely related to quasi-likelihood methods and can handle both normal and non-normal outcome variables such as Poisson or binary outcomes. Their approach, however, has been applied mainly to non-normal outcome variables. This is probably due to the fact that there is a large class of multivariate linear models available for normal outcomes such as growth models and random-effects models. Further-more, there are many iterative algorithms that yield maximum likelihood estimators )MLEs( of the model parameters. The multivariate linear model approach, based on maximum likelihood )ML( estimation, specifies the joint multivariate normal distribution of outcome variables, while the approach of Liang and Zeger, based on the quasi-likelihood, specifies only the marginal distributions. In this paper, I compare the approach of Liang and Zeger and the ML approach for the multivariate normal outcomes. I show that the generalized estimating equation )GEE( reduces to the score equation only when the data do not have missing observations and the correlation is unstructured. In more general cases, however, the GEE estimation yields consistent estimators that may differ from the MLEs. That is, the GEE does not always reduce to the score equation even when the outcome variables are multivariate normal. I compare the small sample properties of the GEE estimators and the MLEs by means of a Monte Carlo simulation study.     

Estimation of genetic and environmental factors for binary traits using family data

While the family-based analysis of genetic and environmental contributions to continuous or Gaussian traits is now straightforward using the linear mixed models approach, the corresponding analysis of complex binary traits is still rather limited. In the latter we usually rely on twin studies or pairs of relatives, but these studies often have limited sample size or have difficulties in dealing with the dependence between the pairs. Direct analysis of extended family data can potentially overcome these limitations. In this paper, we will describe various genetic models that can be analysed using an extended family structure. We use the generalized linear mixed model to deal with the family structure and likelihood-based methodology for parameter inference. The method is completely general, accommodating arbitrary family structures and incomplete data. We illustrate the methodology in great detail using the Swedish birth registry data on pre-eclampsia, a hypertensive condition induced by pregnancy. The statistical challenges include the specification of sensible models that contain a relatively large number of variance components compared to standard mixed models. In our illustration the models will account for maternal or foetal genetic effects, environmental effects, or a combination of these and we show how these effects can be readily estimated using family data.     

Long-term survivor model with bivariate random effects: applications to bone marrow transplant and carcinoma study data

Cured patients (or the so-called long-term survivors) are increasingly being observed in clinical trial studies. As exemplified in two data sets, the bone marrow transplantation study for leukaemia patients and the multi-centre study for patients with carcinoma in the oropharynx, a considerable portion of the patients in these studies are deemed to be cured. With the presence of random hospital/centre effects, a long-term survivor model with bivariate random effects is proposed to analyse clustered survival data with a possible portion of cured patients. This model extends earlier work by allowing random effects in both the cured fraction and the hazard function parts to follow a bivariate normal distribution, which gives a generalized model with an additional correlation parameter governing the relationship between the recovery probability and the instantaneous failure rate due to the hospital/centre effects. By adopting the GLMM formulation, random effects are incorporated in the model via the linear predictor terms. REML estimation of parameters is achieved via the EM algorithm. Application to the two sets of data illustrates the usefulness of the proposed model. A simulation study is conducted to assess the performance of the estimators, under the proposed numerical estimation scheme.     

Generalized linear mixed models for meta-analysis

We examine two strategies for meta-analysis of a series of 2 x 2 tables with the odds ratio modelled as a linear combination of study level covariates and random effects representing between-study variation. Penalized quasi-likelihood (PQL), an approximate inference technique for generalized linear mixed models, and a linear model fitted by weighted least squares to the observed log-odds ratios are used to estimate regression coefficients and dispersion parameters. Simulation results demonstrate that both methods perform adequate approximate inference under many conditions, but that neither method works well in the presence of highly sparse data. Under certain conditions with small cell frequencies the PQL method provides better inference.     

A hierarchical Poisson mixture regression model to analyse maternity length of hospital stay

Inpatient length of stay (LOS) is often considered as a proxy of hospital resource consumption. Using statewide obstetrical delivery data, a two-component Poisson mixture model provides a reasonable fit to the heterogeneous LOS distribution. Adopting the generalized linear mixed model (GLMM) approach, random effects are introduced to the two-component Poisson mixture regression model to account for the inherent correlation of patients clustered within hospitals. An EM algorithm is developed for the joint estimation of regression coefficients and variance component parameters. Related diagnostic measures for assessing model adequacy are derived. When applying the method to analyse maternity LOS, appropriate risk factors for the short-stay and long-stay subgroups can be identified from the respective Poisson components. In addition, predicted random hospital effects enable the comparison of relative efficiencies among hospitals after adjustment for patient case-mix and health provision characteristics.     

Real longitudinal data analysis for real people: Building a good enough mixed model

Mixed effects models have become very popular, especially for the analysis of longitudinal data. One challenge is how to build a good enough mixed effects model. In this paper, we suggest a systematic strategy for addressing this challenge and introduce easily implemented practical advice to build mixed effects models. A general discussion of the scientific strategies motivates the recommended five‐step procedure for model fitting. The need to model both the mean structure (the fixed effects) and the covariance structure (the random effects and residual error) creates the fundamental flexibility and complexity. Some very practical recommendations help to conquer the complexity. Centering, scaling, and full‐rank coding of all the predictor variables radically improve the chances of convergence, computing speed, and numerical accuracy. Applying computational and assumption diagnostics from univariate linear models to mixed model data greatly helps to detect and solve the related computational problems. Applying computational and assumption diagnostics from the univariate linear models to the mixed model data can radically improve the chances of convergence, computing speed, and numerical accuracy. The approach helps to fit more general covariance models, a crucial step in selecting a credible covariance model needed for defensible inference. A detailed demonstration of the recommended strategy is based on data from a published study of a randomized trial of a multicomponent intervention to prevent young adolescents' alcohol use. The discussion highlights a need for additional covariance and inference tools for mixed models. The discussion also highlights the need for improving how scientists and statisticians teach and review the process of finding a good enough mixed model. Copyright © 2009 John Wiley & Sons, Ltd.     

Tweedie family of generalized linear models with distribution‐free random effects for skewed longitudinal data

Generalized linear mixed models have played an important role in the analysis of longitudinal data; however, traditional approaches have limited flexibility in accommodating skewness and complex correlation structures. In addition, the existing estimation approaches generally rely heavily on the specifications of random effects distributions; therefore, the corresponding inferences are sometimes sensitive to the choice of random effect distributions under certain circumstance. In this paper, we incorporate serially dependent distribution‐free random effects into Tweedie generalized linear models to accommodate a wide range of skewness and covariance structures for discrete and continuous longitudinal data. An optimal estimation of our model has been developed using the orthodox best linear unbiased predictors of random effects. Our approach unifies population‐averaged and subject‐specific inferences. Our method is illustrated through the analyses of patient‐controlled analgesia data and Framingham cholesterol data.     

A sample size computation method for non-linear mixed effects models with applications to pharmacokinetics models

We propose a simple method to compute sample size for an arbitrary test hypothesis in population pharmacokinetics (PK) studies analysed with non-linear mixed effects models. Sample size procedures exist for linear mixed effects model, and have been recently extended by Rochon using the generalized estimating equation of Liang and Zeger. Thus, full model based inference in sample size computation has been possible. The method we propose extends the approach using a first-order linearization of the non-linear mixed effects model and use of the Wald chi(2) test statistic. The proposed method is general. It allows an arbitrary non-linear model as well as arbitrary distribution of random effects characterizing both inter- and intra-individual variability of the mixed effects model. To illustrate possible uses of the method we present tables of minimum sample sizes, in particular, with an illustration of the effect of sampling design on sample size. We demonstrate how (D-)optimal or frequent sampling requires fewer subjects in comparison to a sparse sampling design. We also present results from Monte Carlo simulations showing that the computed sample size can produce the desired power. The proposed method greatly reduces computing times compared with simulation-based methods of estimating sample sizes for population PK studies.     

广义线性混合模型在煤工尘肺发病影响因素研究中的应用

目的研究广义线性混合模型在煤工尘肺发病影响因素的应用,为煤工尘肺及类似疾病的发病影响因素研究提供新的方法。方法收集煤矿集团所属8个煤矿所有接尘矿工的资料,用SAS进行卡方检验、Logistic回归进行尘肺发病影响因素研究,并与SAS nlmixed模块实现的广义混合现行模型结果进行比较。结果单因素分析、Logistic回归和广义线性混合模型显示:工龄、接尘时间和工种均为尘肺发病的影响因素,工作地点作为随机效应结果差异无统计学意义。结论广义线性混合模型因考虑了不同工人工作地点的不同和随机效应,结果虽然和其他方法一致,但是更有说服力,与其他方法相比是研究尘肺发病影响因素较好的方法。     

广义线性混合效应模型及其应用

[目的]探讨广义线性混合效应模型在医学研究领域中的作用。[方法]通过实例分析说明模型的实际应用。[结果]将实例中的多中心临床实验数据中不能直观观测到的中心的效应以随机应项纳入型来解决由于来自同一中心可能造成的观测间不独立的问题，模型很好地处理了此类数据。[结论]广义线性混合效应模型可以分析观测间相关、因变量为非正态分布的非独立数据。