The Protective Impact of a Covariate on Competing Failures with an Example from a Bone Marrow Transplantation Study

Starting from an applied Bone Marrow Transplantation(BMT) study, the problem of “unexpected protectivity” in competing risks models is introduced, which occurs when one covariate shows a protective impact not expected from a medical perspective. Current explanations found in the statistical literature suggest that unexpected protectivity might be due to the lack of independence between the competing failures. Actually, in the presence of dependence, the Kaplan-Meier curves are not interpretable. Conversely, the cumulative incidence curves remain interpretable, and therefore seem to be a candidate for solving the problem. We discuss the particular nature of dependence in a competing risks framework and illustrate how this dependence may be created via a common frailty factor. A Monte Carlo experiment is set up which accounts also for the association between the observable covariates and the frailty factor. The aim of the experiment is to understand whether and how the bias showed by the estimates could be related to the omitted frailty variable. The results show that dependence alone does not cause false protectivity, and that the cumulative incidence curves suffer the same bias as the survival curves and therefore do not seem to be a solution to false protectivity. Conversely, false protectivity may occur according to the magnitude and the sign of the dependence between the frailty factor and the covariate. The paper ends with some suggestions for empirical research. This revised version was published online in July 2006 with corrections to the Cover Date.     

Reduced rank proportional hazards model for competing risks: An application to a breast cancer trial

In many cancer trials patients are at risk of recurrence and death after the appearance and the successful treatment of the first diagnosed tumour. In this situation competing risks models that model several competing causes of therapy or surgery failure are a natural framework to describe the evolution of the disease.Typically, regression models for competing risks outcomes are based on proportional hazards model for each of the cause-specific hazard rates. An immediate practical problem is then how to deal with the abundance of regression parameters. The aim of reduced rank proportional hazards models is to reduce the number of parameters that need to be estimated while at the same time keeping the distinction between different transitions. They have the advantage of describing the competing risks model in fewer parameters, cope with transitions where few events are present and facilitate the interpretation of these estimates.We shall illustrate the use of this technique on 2795 patients from a breast cancer trial (EORTC 10854).     

Clustered Survival Data with Left‐truncation

Left‐truncation occurs frequently in survival studies, and it is well known how to deal with this for univariate survival times. However, there are few results on how to estimate dependence parameters and regression effects in semiparametric models for clustered survival data with delayed entry. Surprisingly, existing methods only deal with special cases. In this paper, we clarify different kinds of left‐truncation and suggest estimators for semiparametric survival models under specific truncation schemes. The large‐sample properties of the estimators are established. Small‐sample properties are investigated via simulation studies, and the suggested estimators are used in a study of prostate cancer based on the Finnish twin cohort where a twin pair is included only if both twins were alive in 1974.     

Planning and analyzing clinical trials with competing risks: Recommendations for choosing appropriate statistical methodology

In the analysis of time‐to‐event data, competing risks occur when multiple event types are possible, and the occurrence of a competing event precludes the occurrence of the event of interest. In this situation, statistical methods that ignore competing risks can result in biased inference regarding the event of interest. We review the mechanisms that lead to bias and describe several statistical methods that have been proposed to avoid bias by formally accounting for competing risks in the analyses of the event of interest. Through simulation, we illustrate that Gray's test should be used in lieu of the logrank test for nonparametric hypothesis testing. We also compare the two most popular models for semiparametric modelling: the cause‐specific hazards (CSH) model and Fine‐Gray (F‐G) model. We explain how to interpret estimates obtained from each model and identify conditions under which the estimates of the hazard ratio and subhazard ratio differ numerically. Finally, we evaluate several model diagnostic methods with respect to their sensitivity to detect lack of fit when the CSH model holds, but the F‐G model is misspecified and vice versa. Our results illustrate that adequacy of model fit can strongly impact the validity of statistical inference. We recommend analysts incorporate a model diagnostic procedure and contingency to explore other appropriate models when designing trials in which competing risks are anticipated.     

Testing dependence between the failure time and failure modes: An application of enlarged filtration

The model of independent competing risks provides no information for the assessment of competing failure modes if the failure mechanisms underlying these modes are coupled. Models for dependent competing risks in the literature can be distinguished on the basis of the functional behaviour of the conditional probability of failure due to a particular failure mode given that the failure time exceeds a fixed time, as a function of time. There is an interesting link between monotonicity of such conditional probability and dependence between failure time and failure mode, via crude hazard rates. In this paper, we propose tests for testing the dependence between failure time and failure mode using the crude hazards and using the conditional probabilities mentioned above. We establish the equivalence between the two approaches and provide an asymptotically efficient weight function under a sequence of local alternatives. The tests are applied to simulated data and to mortality follow-up data.     

A grouped beta process model for multivariate resting‐state EEG microstate analysis on twins

EEG microstate analysis investigates the collection of distinct temporal blocks that characterize the electrical activity of the brain. Brain activity within each microstate is stable, but activity switches rapidly between different microstates in a nonrandom way. We propose a Bayesian nonparametric model that concurrently estimates the number of microstates and their underlying behaviour. We use a Markov switching vector autoregressive (VAR) framework, where a hidden Markov model (HMM) controls the nonrandom state switching dynamics of the EEG activity and a VAR model defines the behaviour of all time points within a given state. We analyze the resting‐state EEG data from twin pairs collected through the Minnesota Twin Family Study, consisting of 70 epochs per participant, where each epoch corresponds to 2 s of EEG data. We fit our model at the twin pair level, sharing information within epochs from the same participant and within epochs from the same twin pair. We capture within twin‐pair similarity, using an Indian buffet process, to consider an infinite library of microstates, allowing each participant to select a finite number of states from this library. The state spaces of highly similar twins may completely overlap while dissimilar twins could select distinct state spaces. In this way, our Bayesian nonparametric model defines a sparse set of states that describe the EEG data. All epochs from a single participant use the same set of states and are assumed to adhere to the same state switching dynamics in the HMM model, enforcing within‐participant similarity.     

Accelerated failure time models for the analysis of competing risks

Competing risks are common in clinical cancer research, as patients are subject to multiple potential failure outcomes, such as death from the cancer itself or from complications arising from the disease. In the analysis of competing risks, several regression methods are available for the evaluation of the relationship between covariates and cause-specific failures, many of which are based on Cox’s proportional hazards model. Although a great deal of research has been conducted on estimating competing risks, less attention has been devoted to linear regression modeling, which is often referred to as the accelerated failure time (AFT) model in survival literature. In this article, we address the use and interpretation of linear regression analysis with regard to the competing risks problem. We introduce two types of AFT modeling framework, where the influence of a covariate can be evaluated in relation to either a cause-specific hazard function, referred to as cause-specific AFT (CS-AFT) modeling in this study, or the cumulative incidence function of a particular failure type, referred to as crude-risk AFT (CR-AFT) modeling. Simulation studies illustrate that, as in hazard-based competing risks analysis, these two models can produce substantially different effects, depending on the relationship between the covariates and both the failure type of principal interest and competing failure types. We apply the AFT methods to data from non-Hodgkin lymphoma patients, where the dataset is characterized by two competing events, disease relapse and death without relapse, and non-proportionality. We demonstrate how the data can be analyzed and interpreted, using linear competing risks regression models.     

Competing risks with missing covariates: effect of haplotypematch on hematopoietic cell transplant patients

In this paper we consider a problem from hematopoietic cell transplant (HCT) studies where there is interest on assessing the effect of haplotype match for donor and patient on the cumulative incidence function for a right censored competing risks data. For the HCT study, donor??s and patient??s genotype are fully observed and matched but their haplotypes are missing. In this paper we describe how to deal with missing covariates of each individual for competing risks data. We suggest a procedure for estimating the cumulative incidence functions for a flexible class of regression models when there are missing data, and establish the large sample properties. Small sample properties are investigated using simulations in a setting that mimics the motivating haplotype matching problem. The proposed approach is then applied to the HCT study.     

A dependent Dirichlet process model for survival data with competing risks

In this paper, we first propose a dependent Dirichlet process (DDP) model using a mixture of Weibull models with each mixture component resembling a Cox model for survival data. We then build a Dirichlet process mixture model for competing risks data without regression covariates. Next we extend this model to a DDP model for competing risks regression data by using a multiplicative covariate effect on subdistribution hazards in the mixture components. Though built on proportional hazards (or subdistribution hazards) models, the proposed nonparametric Bayesian regression models do not require the assumption of constant hazard (or subdistribution hazard) ratio. An external time-dependent covariate is also considered in the survival model. After describing the model, we discuss how both cause-specific and subdistribution hazard ratios can be estimated from the same nonparametric Bayesian model for competing risks regression. For use with the regression models proposed, we introduce an omnibus prior that is suitable when little external information is available about covariate effects. Finally we compare the models’ performance with existing methods through simulations. We also illustrate the proposed competing risks regression model with data from a breast cancer study. An R package “DPWeibull” implementing all of the proposed methods is available at CRAN.

     

On the identifiability of copulas in bivariate competing risks models

In competing risks models, the joint distribution of the event times is not identifiable even when the margins are fully known, which has been referred to as the “identifiability crisis in competing risks analysis” (Crowder, 1991). We model the dependence between the event times by an unknown copula and show that identification is actually possible within many frequently used families of copulas. The result is then extended to the case where one margin is unknown. The Canadian Journal of Statistics 41: 291–303; 2013 © 2013 Statistical Society of Canada     

Regression Analysis for Multistate Models Based on a Pseudo-value Approach, with Applications to Bone Marrow Transplantation Studies

Abstract.  Typically, regression analysis for multistate models has been based on regression models for the transition intensities. These models lead to highly nonlinear and very complex models for the effects of covariates on state occupation probabilities. We present a technique that models the state occupation or transition probabilities in a multistate model directly. The method is based on the pseudo-values from a jackknife statistic constructed from non-parametric estimators for the probability in question. These pseudo-values are used as outcome variables in a generalized estimating equation to obtain estimates of model parameters. We examine this approach and its properties in detail for two special multistate model probabilities, the cumulative incidence function in competing risks and the current leukaemia-free survival used in bone marrow transplants. The latter is the probability a patient is alive and in either a first or second post-transplant remission. The techniques are illustrated on a dataset of leukaemia patients given a marrow transplant. We also discuss extensions of the model that are of current research interest.     

Parametric Modeling for Survival with Competing Risks and Masked Failure Causes

We consider a life testing situation in which systems are subject to failure from independent competing risks. Following a failure, immediate (stage-1) procedures are used in an attempt to reach a definitive diagnosis. If these procedures fail to result in a diagnosis, this phenomenon is called masking. Stage-2 procedures, such as failure analysis or autopsy, provide definitive diagnosis for a sample of the masked cases. We show how stage-1 and stage-2 information can be combined to provide statistical inference about (a) survival functions of the individual risks, (b) the proportions of failures associated with individual risks and (c) probability, for a specified masked case, that each of the masked competing risks is responsible for the failure. Our development is based on parametric distributional assumptions and the special case for which the failure times for the competing risks have a Weibull distribution is discussed in detail.     

Shared frailty model based on reversed hazard rate for left censored data

Frailty models are used in the survival analysis to account for the unobserved heterogeneity in the individual risks to disease and death. To analyze the bivariate data on related survival times (e.g., matched pairs experiments, twin or family data), the shared frailty models were suggested. In this article, we introduce the shared gamma frailty models with the reversed hazard rate. We develop the Bayesian estimation procedure using the Markov chain Monte Carlo (MCMC) technique to estimate the parameters involved in the model. We present a simulation study to compare the true values of the parameters with the estimated values. We apply the model to a real life bivariate survival dataset.     

Population-based absolute risk estimation with survey data

Absolute risk is the probability that a cause-specific event occurs in a given time interval in the presence of competing events. We present methods to estimate population-based absolute risk from a complex survey cohort that can accommodate multiple exposure-specific competing risks. The hazard function for each event type consists of an individualized relative risk multiplied by a baseline hazard function, which is modeled nonparametrically or parametrically with a piecewise exponential model. An influence method is used to derive a Taylor-linearized variance estimate for the absolute risk estimates. We introduce novel measures of the cause-specific influences that can guide modeling choices for the competing event components of the model. To illustrate our methodology, we build and validate cause-specific absolute risk models for cardiovascular and cancer deaths using data from the National Health and Nutrition Examination Survey. Our applications demonstrate the usefulness of survey-based risk prediction models for predicting health outcomes and quantifying the potential impact of disease prevention programs at the population level.     

Bayesian analysis of bivariate competing risks models with covariates

Bivariate exponential models have often been used for the analysis of competing risks data involving two correlated risk components. Competing risks data consist only of the time to failure and cause of failure. In situations where there is positive probability of simultaneous failure, possibly the most widely used model is the Marshall–Olkin (J. Amer. Statist. Assoc. 62 (1967) 30) bivariate lifetime model. This distribution is not absolutely continuous as it involves a singularity component. However, the likelihood function based on the competing risks data is then identifiable, and any inference, Bayesian or frequentist, can be carried out in a straightforward manner. For the analysis of absolutely continuous bivariate exponential models, standard approaches often run into difficulty due to the lack of a fully identifiable likelihood (Basu and Ghosh; Commun. Statist. Theory Methods 9 (1980) 1515). To overcome the nonidentifiability, the usual frequentist approach is based on an integrated likelihood. Such an approach is implicit in Wada et al. (Calcutta Statist. Assoc. Bull. 46 (1996) 197) who proved some related asymptotic results. We offer in this paper an alternative Bayesian approach. Since systematic prior elicitation is often difficult, the present study focuses on Bayesian analysis with noninformative priors. It turns out that with an appropriate reparameterization, standard noninformative priors such as Jeffreys’ prior and its variants can be applied directly even though the likelihood is not fully identifiable. Two noninformative priors are developed that consist of Laplace's prior for nonidentifiable parameters and Laplace's and Jeffreys's priors for identifiable parameters. The resulting Bayesian procedures possess some frequentist optimality properties as well. Finally, these Bayesian methods are illustrated with analyses of a data set originating out of a lung cancer clinical trial conducted by the Eastern Cooperative Oncology Group.     

Gamma shared frailty model based on reversed hazard rate

Abstract

Frailty models are used in survival analysis to account for unobserved heterogeneity in individual risks to disease and death. To analyze bivariate data on related survival times (e.g., matched pairs experiments, twin, or family data), shared frailty models were suggested. Shared frailty models are frequently used to model heterogeneity in survival analysis. The most common shared frailty model is a model in which hazard function is a product of random factor(frailty) and baseline hazard function which is common to all individuals. There are certain assumptions about the baseline distribution and distribution of frailty. In this paper, we introduce shared gamma frailty models with reversed hazard rate. We introduce Bayesian estimation procedure using Markov Chain Monte Carlo (MCMC) technique to estimate the parameters involved in the model. We present a simulation study to compare the true values of the parameters with the estimated values. Also, we apply the proposed model to the Australian twin data set.     

Correlated gamma frailty models for bivariate survival data

Frailty models are used in the survival analysis to account for the unobserved heterogeneity in individual risks to disease and death. To analyze the bivariate data on related survival times (e.g., matched pairs experiments, twin or family data) the shared frailty models were suggested. Shared frailty models are used despite their limitations. To overcome their disadvantages correlated frailty models may be used. In this article, we introduce the gamma correlated frailty models with two different baseline distributions namely, the generalized log logistic, and the generalized Weibull. We introduce the Bayesian estimation procedure using Markov chain Monte Carlo (MCMC) technique to estimate the parameters involved in these models. We present a simulation study to compare the true values of the parameters with the estimated values. Also we apply these models to a real life bivariate survival dataset related to the kidney infection data and a better model is suggested for the data.     

Extended Bayesian model averaging for heritability in twin studies

Family studies are often conducted to examine the existence of familial aggregation. Particularly, twin studies can model separately the genetic and environmental contribution. Here we estimate the heritability of quantitative traits via variance components of random-effects in linear mixed models (LMMs). The motivating example was a myopia twin study containing complex nesting data structures: twins and siblings in the same family and observations on both eyes for each individual. Three models are considered for this nesting structure. Our proposal takes into account the model uncertainty in both covariates and model structures via an extended Bayesian model averaging (EBMA) procedure. We estimate the heritability using EBMA under three suggested model structures. When compared with the results under the model with the highest posterior model probability, the EBMA estimate has smaller variation and is slightly conservative. Simulation studies are conducted to evaluate the performance of variance-components estimates, as well as the selections of risk factors, under the correct or incorrect structure. The results indicate that EBMA, with consideration of uncertainties in both covariates and model structures, is robust in model misspecification than the usual Bayesian model averaging (BMA) that considers only uncertainty in covariates selection.     

On Bayesian analyses and finite mixtures for proportions

When the results of biological experiments are tested for a possible difference between treatment and control groups, the inference is only valid if based upon a model that fits the experimental results satisfactorily. In dominant-lethal testing, foetal death has previously been assumed to follow a variety of models, including a Poisson, Binomial, Beta-binomial and various mixture models. However, discriminating between models has always been a particularly difficult problem. In this paper, we consider the data from 6 separate dominant-lethal assay experiments and discriminate between the competing models which could be used to describe them. We adopt a Bayesian approach and illustrate how a variety of different models may be considered, using Markov chain Monte Carlo (MCMC) simulation techniques and comparing the results with the corresponding maximum likelihood analyses. We present an auxiliary variable method for determining the probability that any particular data cell is assigned to a given component in a mixture and we illustrate the value of this approach. Finally, we show how the Bayesian approach provides a natural and unique perspective on the model selection problem via reversible jump MCMC and illustrate how probabilities associated with each of the different models may be calculated for each data set. In terms of estimation we show how, by averaging over the different models, we obtain reliable and robust inference for any statistic of interest.     

Modeling unemployment duration in a dependent competing risks framework: Identification and estimation

Three Mixed Proportional Hazard models for estimation of unemployment duration when attrition is present are considered. The virtue of these models is that they take account of dependence between failure times in a multivariate failure time distribution context. However, identification in dependent competing risks models is not straightforward. We show that these models, independently derived, are special cases of a general frailty model. It is also demonstrated that the three models are identified by means of identification of the general model. An empirical example illustrates the approach to model dependent failure times.