The Milk Protein Trial: Influence Analysis of the Dropout Process

Diggle and Kenward (1994) proposed a selection model for continuous longitudinal data subject to possible non‐random dropout. Their method in general, and the milk protein example in particular, has provoked a large debate about the role of such models. The original enthusiasm was followed by skepticism about the strong but untestable assumption upon which this type of models invariably rests. Concern was raised about the very nature of incompleteness which is arguably more due to design reasons (the experiment was stopped due to insufficient feed supply), than to genuine dropout. In the meantime, the view has emerged that these models should ideally be made part of a sensitivity analysis. This paper presents a formal and flexible approach to such a sensitivity assessment, based on both global influence (Chatterjee and Hadi , 1988) as well as local influence (Cook , 1986). It will be argued that local influence is more apt to zoom in on a particular source of influence, such as the assumed non‐response mechanism. The method is applied to a set of data on milk protein contents in dairy cattle. The same data were used in the original paper by Diggle and Kenward (1994), who concluded that the dropout process was non‐random.     

Reparameterizing the pattern mixture model for sensitivity analyses under informative dropout

Pattern mixture models are frequently used to analyze longitudinal data where missingness is induced by dropout. For measured responses, it is typical to model the complete data as a mixture of multivariate normal distributions, where mixing is done over the dropout distribution. Fully parameterized pattern mixture models are not identified by incomplete data; Little (1993, Journal of the American Statistical Association 88, 125-134) has characterized several identifying restrictions that can be used for model fitting. We propose a reparameterization of the pattern mixture model that allows investigation of sensitivity to assumptions about nonidentified parameters in both the mean and variance, allows consideration of a wide range of nonignorable missing-data mechanisms, and has intuitive appeal for eliciting plausible missing-data mechanisms. The parameterization makes clear an advantage of pattern mixture models over parametric selection models, namely that the missing-data mechanism can be varied without affecting the marginal distribution of the observed data. To illustrate the utility of the new parameterization, we analyze data from a recent clinical trial of growth hormone for maintaining muscle strength in the elderly. Dropout occurs at a high rate and is potentially informative. We undertake a detailed sensitivity analysis to understand the impact of missing-data assumptions on the inference about the effects of growth hormone on muscle strength.     

A local influence approach applied to binary data from a psychiatric study

Recently, a lot of concern has been raised about assumptions needed in order to fit statistical models to incomplete multivariate and longitudinal data. In response, research efforts are being devoted to the development of tools that assess the sensitivity of such models to often strong but always, at least in part, unverifiable assumptions. Many efforts have been devoted to longitudinal data, primarily in the selection model context, although some researchers have expressed interest in the pattern-mixture setting as well. A promising tool, proposed by Verbeke et al. (2001, Biometrics 57, 43-50), is based on local influence (Cook, 1986, Journal of the Royal Statistical Society, Series B 48, 133-169). These authors considered the Diggle and Kenward (1994, Applied Statistics 43, 49-93) model, which is based on a selection model, integrating a linear mixed model for continuous outcomes with logistic regression for dropout. In this article, we show that a similar idea can be developed for multivariate and longitudinal binary data, subject to nonmonotone missingness. We focus on the model proposed by Baker, Rosenberger, and DerSimonian (1992, Statistics in Medicine 11, 643-657). The original model is first extended to allow for (possibly continuous) covariates, whereafter a local influence strategy is developed to support the model-building process. The model is able to deal with nonmonotone missingness but has some limitations as well, stemming from the conditional nature of the model parameters. Some analytical insight is provided into the behavior of the local influence graphs.     

Multiple-Imputation-Based Residuals and Diagnostic Plots for Joint Models of Longitudinal and Survival Outcomes

Summary .  The majority of the statistical literature for the joint modeling of longitudinal and time-to-event data has focused on the development of models that aim at capturing specific aspects of the motivating case studies. However, little attention has been given to the development of diagnostic and model-assessment tools. The main difficulty in using standard model diagnostics in joint models is the nonrandom dropout in the longitudinal outcome caused by the occurrence of events. In particular, the reference distribution of statistics, such as the residuals, in missing data settings is not directly available and complex calculations are required to derive it. In this article, we propose a multiple-imputation-based approach for creating multiple versions of the completed data set under the assumed joint model. Residuals and diagnostic plots for the complete data model can then be calculated based on these imputed data sets. Our proposals are exemplified using two real data sets.     

A marginalized conditional linear model for longitudinal binary data when informative dropout occurs in continuous time

Within the pattern-mixture modeling framework for informative dropout, conditional linear models (CLMs) are a useful approach to deal with dropout that can occur at any point in continuous time (not just at observation times). However, in contrast with selection models, inferences about marginal covariate effects in CLMs are not readily available if nonidentity links are used in the mean structures. In this article, we propose a CLM for long series of longitudinal binary data with marginal covariate effects directly specified. The association between the binary responses and the dropout time is taken into account by modeling the conditional mean of the binary response as well as the dependence between the binary responses given the dropout time. Specifically, parameters in both the conditional mean and dependence models are assumed to be linear or quadratic functions of the dropout time; and the continuous dropout time distribution is left completely unspecified. Inference is fully Bayesian. We illustrate the proposed model using data from a longitudinal study of depression in HIV-infected women, where the strategy of sensitivity analysis based on the extrapolation method is also demonstrated.     

Regression modeling of semicompeting risks data

Semicompeting risks data are often encountered in clinical trials with intermediate endpoints subject to dependent censoring from informative dropout. Unlike with competing risks data, dropout may not be dependently censored by the intermediate event. There has recently been increased attention to these data, in particular inferences about the marginal distribution of the intermediate event without covariates. In this article, we incorporate covariates and formulate their effects on the survival function of the intermediate event via a functional regression model. To accommodate informative censoring, a time-dependent copula model is proposed in the observable region of the data which is more flexible than standard parametric copula models for the dependence between the events. The model permits estimation of the marginal distribution under weaker assumptions than in previous work on competing risks data. New nonparametric estimators for the marginal and dependence models are derived from nonlinear estimating equations and are shown to be uniformly consistent and to converge weakly to Gaussian processes. Graphical model checking techniques are presented for the assumed models. Nonparametric tests are developed accordingly, as are inferences for parametric submodels for the time-varying covariate effects and copula parameters. A novel time-varying sensitivity analysis is developed using the estimation procedures. Simulations and an AIDS data analysis demonstrate the practical utility of the methodology.     

Diagnostics for joint longitudinal and dropout time modeling

We present a variety of informal graphical procedures for diagnostic assessment of joint models for longitudinal and dropout time data. A random effects approach for Gaussian responses and proportional hazards dropout time is assumed. We consider preliminary assessment of dropout classification categories based on residuals following a standard longitudinal data analysis with no allowance for informative dropout. Residual properties conditional upon dropout information are discussed and case influence is considered. The proposed methods do not require computationally intensive methods over and above those used to fit the proposed model. A longitudinal trial into the treatment of schizophrenia is used to illustrate the suggestions.     

Models for deploymerizing enzymes: criteria for discrimination of models

Several models for the action of alpha amylase have been proposed to account for the nonrandom distribution of oligosaccharides in the amylase digests of polysaccharides. The preferred-attack model attempts to account for the nonrandom distribution by assuming that the probability for bond cleavage depends upon the position of the bond in the chain. The repetitive, or multiple-attack, model suggests that the nonrandom distribution of oligosaccharides arises because an amylase can form a cage-like complex with a substrate and attack it several times during a single encounter. The multiple-enzyme or dual-site model suggests that the nonrandom yield of oligosaccharides arises from the combined action of exo- and endo-enzymes. The effects of pH, inhibitors, and substrate chain-length on enzyme action have been studied in several laboratories to determine which of the three action-patterns best describes the action of alpha amylase. The influence of these variables on product distributions or enzyme action-patterns are mathematically modeled in the Appendix. The experimental data on porcine-pancreatic alpha amylase are discussed in the light of the derivations.     

Bayesian informative dropout model for longitudinal binary data with random effects using conditional and joint modeling approaches

Dropouts are common in longitudinal study. If the dropout probability depends on the missing observations at or after dropout, this type of dropout is called informative (or nonignorable) dropout (ID). Failure to accommodate such dropout mechanism into the model will bias the parameter estimates. We propose a conditional autoregressive model for longitudinal binary data with an ID model such that the probabilities of positive outcomes as well as the drop‐out indicator in each occasion are logit linear in some covariates and outcomes. This model adopting a marginal model for outcomes and a conditional model for dropouts is called a selection model. To allow for the heterogeneity and clustering effects, the outcome model is extended to incorporate mixture and random effects. Lastly, the model is further extended to a novel model that models the outcome and dropout jointly such that their dependency is formulated through an odds ratio function. Parameters are estimated by a Bayesian approach implemented using the user‐friendly Bayesian software WinBUGS. A methadone clinic dataset is analyzed to illustrate the proposed models. Result shows that the treatment time effect is still significant but weaker after allowing for an ID process in the data. Finally the effect of drop‐out on parameter estimates is evaluated through simulation studies.     

Mixed-effect hybrid models for longitudinal data with nonignorable dropout

Summary .  Selection models and pattern-mixture models are often used to deal with nonignorable dropout in longitudinal studies. These two classes of models are based on different factorizations of the joint distribution of the outcome process and the dropout process. We consider a new class of models, called mixed-effect hybrid models (MEHMs), where the joint distribution of the outcome process and dropout process is factorized into the marginal distribution of random effects, the dropout process conditional on random effects, and the outcome process conditional on dropout patterns and random effects. MEHMs combine features of selection models and pattern-mixture models: they directly model the missingness process as in selection models, and enjoy the computational simplicity of pattern-mixture models. The MEHM provides a generalization of shared-parameter models (SPMs) by relaxing the conditional independence assumption between the measurement process and the dropout process given random effects. Because SPMs are nested within MEHMs, likelihood ratio tests can be constructed to evaluate the conditional independence assumption of SPMs. We use data from a pediatric AIDS clinical trial to illustrate the models.     

Modeling longitudinal data with nonignorable dropouts using a latent dropout class model

In longitudinal studies with dropout, pattern-mixture models form an attractive modeling framework to account for nonignorable missing data. However, pattern-mixture models assume that the components of the mixture distribution are entirely determined by the dropout times. That is, two subjects with the same dropout time have the same distribution for their response with probability one. As that is unlikely to be the case, this assumption made lead to classification error. In addition, if there are certain dropout patterns with very few subjects, which often occurs when the number of observation times is relatively large, pattern-specific parameters may be weakly identified or require identifying restrictions. We propose an alternative approach, which is a latent-class model. The dropout time is assumed to be related to the unobserved (latent) class membership, where the number of classes is less than the number of observed patterns; a regression model for the response is specified conditional on the latent variable. This is a type of shared-parameter model, where the shared "parameter" is discrete. Parameter estimates are obtained using the method of maximum likelihood. Averaging the estimates of the conditional parameters over the distribution of the latent variable yields estimates of the marginal regression parameters. The methodology is illustrated using longitudinal data on depression from a study of HIV in women.     

Mixtures of varying coefficient models for longitudinal data with discrete or continuous nonignorable dropout

The analysis of longitudinal repeated measures data is frequently complicated by missing data due to informative dropout. We describe a mixture model for joint distribution for longitudinal repeated measures, where the dropout distribution may be continuous and the dependence between response and dropout is semiparametric. Specifically, we assume that responses follow a varying coefficient random effects model conditional on dropout time, where the regression coefficients depend on dropout time through unspecified nonparametric functions that are estimated using step functions when dropout time is discrete (e.g., for panel data) and using smoothing splines when dropout time is continuous. Inference under the proposed semiparametric model is hence more robust than the parametric conditional linear model. The unconditional distribution of the repeated measures is a mixture over the dropout distribution. We show that estimation in the semiparametric varying coefficient mixture model can proceed by fitting a parametric mixed effects model and can be carried out on standard software platforms such as SAS. The model is used to analyze data from a recent AIDS clinical trial and its performance is evaluated using simulations.     

Pseudo-Likelihood for Combined Selection and Pattern-Mixture Models for Incomplete Data

In this paper we develop pseudo-likelihood methods for the estimation of parameters in a model that is specified in terms of both selection modelling and pattern-mixture modelling quantities. Two cases are considered: (1) the model is specified directly from a joint model for the measurement and dropout processes; (2) conditional models for the measurement process given dropout and vice versa are specified directly. In the latter case, compatibility constraints to ensure the existence of a joint density are derived. The method is applied to data from a psychiatric study, where a bivariate therapeutic outcome is supplemented with covariate information.     

A deep auto-encoder model for gene expression prediction

Background

Gene expression is a key intermediate level that genotypes lead to a particular trait. Gene expression is affected by various factors including genotypes of genetic variants. With an aim of delineating the genetic impact on gene expression, we build a deep auto-encoder model to assess how good genetic variants will contribute to gene expression changes. This new deep learning model is a regression-based predictive model based on the MultiLayer Perceptron and Stacked Denoising Auto-encoder (MLP-SAE). The model is trained using a stacked denoising auto-encoder for feature selection and a multilayer perceptron framework for backpropagation. We further improve the model by introducing dropout to prevent overfitting and improve performance.

Results

To demonstrate the usage of this model, we apply MLP-SAE to a real genomic datasets with genotypes and gene expression profiles measured in yeast. Our results show that the MLP-SAE model with dropout outperforms other models including Lasso, Random Forests and the MLP-SAE model without dropout. Using the MLP-SAE model with dropout, we show that gene expression quantifications predicted by the model solely based on genotypes, align well with true gene expression patterns.

Conclusion

We provide a deep auto-encoder model for predicting gene expression from SNP genotypes. This study demonstrates that deep learning is appropriate for tackling another genomic problem, i.e., building predictive models to understand genotypes’ contribution to gene expression. With the emerging availability of richer genomic data, we anticipate that deep learning models play a bigger role in modeling and interpreting genomics.

     

Improved Doubly Robust Estimation When Data Are Monotonely Coarsened,with Application to Longitudinal Studies with Dropout

Summary A routine challenge is that of making inference on parameters in a statistical model of interest from longitudinal data subject to dropout, which are a special case of the more general setting of monotonely coarsened data. Considerable recent attention has focused on doubly robust (DR) estimators, which in this context involve positing models for both the missingness (more generally, coarsening) mechanism and aspects of the distribution of the full data, that have the appealing property of yielding consistent inferences if only one of these models is correctly specified. DR estimators have been criticized for potentially disastrous performance when both of these models are even only mildly misspecified. We propose a DR estimator applicable in general monotone coarsening problems that achieves comparable or improved performance relative to existing DR methods, which we demonstrate via simulation studies and by application to data from an AIDS clinical trial.     

Incorporating Genotype Uncertainty into Mark–Recapture-Type Models For Estimating Abundance Using DNA Samples

Summary .  Sampling DNA noninvasively has advantages for identifying animals for uses such as mark–recapture modeling that require unique identification of animals in samples. Although it is possible to generate large amounts of data from noninvasive sources of DNA, a challenge is overcoming genotyping errors that can lead to incorrect identification of individuals. A major source of error is allelic dropout, which is failure of DNA amplification at one or more loci. This has the effect of heterozygous individuals being scored as homozygotes at those loci as only one allele is detected. If errors go undetected and the genotypes are naively used in mark–recapture models, significant overestimates of population size can occur. To avoid this it is common to reject low-quality samples but this may lead to the elimination of large amounts of data. It is preferable to retain these low-quality samples as they still contain usable information in the form of partial genotypes. Rather than trying to minimize error or discarding error-prone samples we model dropout in our analysis. We describe a method based on data augmentation that allows us to model data from samples that include uncertain genotypes. Application is illustrated using data from the European badger ( Meles meles ).     

Missing covariates in longitudinal data with informative dropouts: bias analysis and inference

We consider estimation in generalized linear mixed models (GLMM) for longitudinal data with informative dropouts. At the time a unit drops out, time-varying covariates are often unobserved in addition to the missing outcome. However, existing informative dropout models typically require covariates to be completely observed. This assumption is not realistic in the presence of time-varying covariates. In this article, we first study the asymptotic bias that would result from applying existing methods, where missing time-varying covariates are handled using naive approaches, which include: (1) using only baseline values; (2) carrying forward the last observation; and (3) assuming the missing data are ignorable. Our asymptotic bias analysis shows that these naive approaches yield inconsistent estimators of model parameters. We next propose a selection/transition model that allows covariates to be missing in addition to the outcome variable at the time of dropout. The EM algorithm is used for inference in the proposed model. Data from a longitudinal study of human immunodeficiency virus (HIV)-infected women are used to illustrate the methodology.     

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 new method for handling missing species in diversification analysis applicable to randomly or nonrandomly sampled phylogenies

Chronograms from molecular dating are increasingly being used to infer rates of diversification and their change over time. A major limitation in such analyses is incomplete species sampling that moreover is usually nonrandom. While the widely used γ statistic with the Monte Carlo constant-rates test or the birth-death likelihood analysis with the δ AICrc test statistic are appropriate for comparing the fit of different diversification models in phylogenies with random species sampling, no objective automated method has been developed for fitting diversification models to nonrandomly sampled phylogenies. Here, we introduce a novel approach, CorSiM, which involves simulating missing splits under a constant rate birth-death model and allows the user to specify whether species sampling in the phylogeny being analyzed is random or nonrandom. The completed trees can be used in subsequent model-fitting analyses. This is fundamentally different from previous diversification rate estimation methods, which were based on null distributions derived from the incomplete trees. CorSiM is automated in an R package and can easily be applied to large data sets. We illustrate the approach in two Araceae clades, one with a random species sampling of 52% and one with a nonrandom sampling of 55%. In the latter clade, the CorSiM approach detects and quantifies an increase in diversification rate, whereas classic approaches prefer a constant rate model; in the former clade, results do not differ among methods (as indeed expected since the classic approaches are valid only for randomly sampled phylogenies). The CorSiM method greatly reduces the type I error in diversification analysis, but type II error remains a methodological problem.     

A class of linear spectral models and analyses for the study of longitudinal data

Longitudinal data can always be represented by a time series with a deterministic trend and randomly correlated residuals, the latter of which do not usually form a stationary process. The class of linear spectral models is a basis for the exploratory analysis of these data. The theory and techniques of factor analysis provide a means by which one component of the residual series can be separated from an error series, and then partitioned into a sum of randomly scaled metameters that characterize the sample paths of the residuals. These metameters, together with linear modelling techniques, are then used to partition the nonrandom trend into a determined component, which is associated with the sample paths of the residuals, and an independent inherent component. Linear spectral models are assumption-free and represent both random and nonrandom trends with fewer terms than any other mixed-effects linear model. Data on body-weight growth of juvenile mice are used in this paper to illustrate the application of linear spectral models, through a relatively sophisticated exploratory analysis.