An alternative estimation method for the accelerated failure time frailty model

Clustered interval-censored failure time data occur when the failure times of interest are clustered into small groups and known only to lie in certain intervals. A number of methods have been proposed for regression analysis of clustered failure time data, but most of them apply only to clustered right-censored data. In this paper, a sieve estimation procedure is proposed for fitting a Cox frailty model to clustered interval-censored failure time data. In particular, a two-step algorithm for parameter estimation is developed and the asymptotic properties of the resulting sieve maximum likelihood estimators are established. The finite sample properties of the proposed estimators are investigated through a simulation study and the method is illustrated by the data arising from a lymphatic filariasis study.

In this article, we present a frailty model using the generalized gamma distribution as the frailty distribution. It is a power generalization of the popular gamma frailty model. It also includes other frailty models such as the lognormal and Weibull frailty models as special cases. The flexibility of this frailty distribution makes it possible to detect a complex frailty distribution structure which may otherwise be missed. Due to the intractable integrals in the likelihood function and its derivatives, we propose to approximate the integrals either by Monte Carlo simulation or by a quadrature method and then determine the maximum likelihood estimates of the parameters in the model. We explore the properties of the proposed frailty model and the computation method through a simulation study. The study shows that the proposed model can potentially reduce errors in the estimation, and that it provides a viable alternative for correlated data. The merits of proposed model are demonstrated in analysing the effects of sublingual nitroglycerin and oral isosorbide dinitrate on angina pectoris of coronary heart disease patients based on the data set in Danahy et al. (sustained hemodynamic and antianginal effect of high dose oral isosorbide dinitrate. Circulation 1977; 55:381-387).

SUMMARY We propose a generalized method of moments approach to the accelerated failure time model with correlated survival data. We study the semiparametric rank estimator using martingalebased moments. We circumvent direct estimation of correlation parameters by concatenating the moments and minimizing a quadratic objective function. We establish the consistency and asymptotic normality of the parameter estimators, and derive the limiting distribution of the objective function. We carry out simulation studies to examine the finite-sample properties of the method, and demonstrate its substantial efficiency gain over the conventional method. Finally, we illustrate the new proposal with an example from a diabetic retinopathy study.

Survival models allowing for random effects (e.g., frailty models) have been widely used for analyzing clustered time‐to‐event data. Accelerated failure time (AFT) models with random effects are useful alternatives to frailty models. Because survival times are directly modeled, interpretation of the fixed and random effects is straightforward. Moreover, the fixed effect estimates are robust against various violations of the assumed model. In this paper, we propose a penalized h‐likelihood (HL) procedure for variable selection of fixed effects in the AFT random‐effect models. For the purpose of variable selection, we consider three penalty functions, namely, least absolute shrinkage and selection operator (LASSO), smoothly clipped absolute deviation (SCAD), and HL. We demonstrate via simulation studies that the proposed variable selection procedure is robust against the misspecification of the assumed model. The proposed method is illustrated using data from a bladder cancer clinical trial.

ABSTRACTThis paper discusses regression analysis of clustered interval-censored failure time data, which often occur in medical follow-up studies among other areas. For such data, sometimes the failure time may be related to the cluster size, the number of subjects within each cluster or we have informative cluster sizes. For the problem, we present a within-cluster resampling method for the situation where the failure time of interest can be described by a class of linear transformation models. In addition to the establishment of the asymptotic properties of the proposed estimators of regression parameters, an extensive simulation study is conducted for the assessment of the finite sample properties of the proposed method and suggests that it works well in practical situations. An application to the example that motivated this study is also provided.

In randomized clinical trials or observational studies, subjects are recruited at multiple treating sites. Factors that vary across sites may have some influence on outcomes; therefore, they need to be taken into account to get better results. We apply the accelerated failure time (AFT) model with linear mixed effects to analyze failure time data, accounting for correlations between outcomes. Specifically, we use Bayesian approach to fit the data, computing the regression parameters by Gibbs sampler combined with Buckley-James method. This approach is compared with the marginal independence approach and other methods through simulations and an application to a real example.

Accelerated Failure Time (AFT) models are viable alternatives to the Cox proportional hazard model, where failure times are explicitly modelled with respect to covariates. A major problem with parametric AFT models in practice is that statistical distribution used there often have a limited range of shapes, which may be inadequate to cope with real-life data. This paper presents an AFT model algorithm involving generalised lambda distributions (GLD) using maximum likelihood estimation, by extending and adapting existing work on GLD regression model and estimation, which would enhance the capabilities of AFT models owing to the rich shapes of GLDs. The proposed method is demonstrated to achieve parameter consistency and is very robust against outliers. A real-life example demonstrating the use of GLD AFT models compared to more established methods such as semi-parametric models of Buckley James regression, Accelerated Failure Time GEE model and Cox proportional hazard model is also given.

PurposeThe purpose of this paper is to investigate proprietary data from customers of a Southern Louisiana credit union. It analyzes the factors that contribute to an accelerated failure time (AFT) using information from customers’ credit applications as well as information provided in their credit report.Design/methodology/approachThis paper investigates the factors that affect credit risk using survival analysis by employing two primary models – the AFT model and the Cox proportional hazard (PH) model. While several studies employ the Cox PH model, few use the AFT model. However, this paper concludes that the AFT model has superior predictive qualities.FindingsThis paper finds that the factors specific to borrowers and local factors play an important role in the duration of a loan.Practical implicationsThis paper offers an easily interpretable model for determining the duration of a potential borrower. The marketing department of credit unions can then use this information to predict when a customer will default, thus allowing the credit union to intervene in a timely manner to prevent defaults. Further, the credit union can use this information to seek out customers who are less likely to default.Originality/valueThis study is different from the previous research due to its focus on credit unions, which have distinct characteristics. Compared to similar lending institutions, the charter of the credit union does not allow management to sell off loans to other investors.

The Japanese Foundation for Cancer Research (JFCR) has provided a large database on gastric cancer for open use comprised of data on survival times after surgery and related covariates including prognostic factors. Data analysis based on the generalized hazards model incorporating the B-spline function (GHMBS) was performed using a dataset (JFCR dataset) composed of 9,631 cases within this database. A model selection method was adopted for clarifying the meaning of estimated parameters, because the GHMBS was comprised of the proportional hazards model (PHM) and accelerated failure time model (AFTM) as submodels. A preliminary simulation experiment to examine the performance of the model selection method based on the GHMBS was conducted under the condition that multiple covariates were considered, where one was the target covariate and the other was covariate for adjustment. After validation of the method by this simulation experiment, the method was applied to the JFCR dataset to estimate the period effect for prolonging survival time with an adjustment for the stage effect. The analysis revealed that the PHM was suitable for the period effect, while a mixture of the PHM and AFTM was for the stage effect and treatment for gastric cancer made steady progress from the 1950s through the 1990s.

Numerous variable selection techniques have been developed for complete high-dimensional data but very few of them for censored data. The techniques for complete data must be modified if censoring is present. In this paper, we consider the variable selection technique for accelerated failure time (AFT) models by extending the ranking-based variable selection (RBVS) algorithm and its iterative procedure as proposed in the work of Baranowski et al. through the Stute’s weighted least square technique. Simulation studies are conducted to demonstrate the performance of the proposed methods. We further illustrate the performance of this method with a mantle cell lymphoma microarray example. When there is no correlation among the covariates, the proposed method outperforms the iterative sure independence screening and stability selection methods in terms of overall performance for high-dimensional data. Real data analysis also suggests that the proposed method can be chosen for high-dimensional censored data analysis in parallel to other methods in the literature.

The accelerated failure time (AFT) model is a linear model under the log-transformation of survival time that has been introduced as a useful alternative to the proportional hazards (PH) model. In this paper we propose variable-selection procedures of fixed effects in a parametric AFT model using penalized likelihood approaches. We use three popular penalty functions, least absolute shrinkage and selection operator (LASSO), adaptive LASSO and smoothly clipped absolute deviation (SCAD). With these procedures we can select important variables and estimate the fixed effects at the same time. The performance of the proposed method is evaluated using simulation studies, including the investigation of impact of misspecifying the assumed distribution. The proposed method is illustrated with a primary biliary cirrhosis (PBC) data set.

With improvements to cancer diagnoses and treatments, incidences and mortality rates have changed. However, the most commonly used analysis methods do not account for such distributional changes. In survival analysis, change point problems can concern a shift in a distribution for a set of time‐ordered observations, potentially under censoring or truncation. We propose a sequential testing approach for detecting multiple change points in the Weibull accelerated failure time model, since this is sufficiently flexible to accommodate increasing, decreasing, or constant hazard rates and is also the only continuous distribution for which the accelerated failure time model can be reparameterized as a proportional hazards model. Our sequential testing procedure does not require the number of change points to be known; this information is instead inferred from the data. We conduct a simulation study to show that the method accurately detects change points and estimates the model. The numerical results along with real data applications demonstrate that our proposed method can detect change points in the hazard rate.

A popular approach, generalized estimating equations (GEE), has been applied to the multivariate accelerated failure time (AFT) model of the clustered and censored data. However, this method needs to estimate the correlation parameters and calculate the inverse of the correlation matrix. Meanwhile, the efficiency of the parameter estimators is low when the correlation structure is misspecified and/or the marginal distribution is heavy-tailed. This paper proposes using the quadratic inference functions (QIF) with a mixture correlation structure to estimate the coefficients in the multivariate AFT model, which can avoid estimating the correlation parameters and computing the inverse matrix of the correlation matrix. Moreover, the estimator derived from the QIF is consistent and asymptotically normal. Simulation studies indicate that the proposed method outperforms the method based on GEE when the marginal distribution has a heavy tail. Finally, the proposed method is used to analyze a real dataset for illustration.

It has been well known that ignoring measurement error may result in substantially biased estimates in many contexts including linear and nonlinear regressions. For survival data with measurement error in covariates there has been extensive discussion in the literature with the focus being on the Cox proportional hazards models. However, the impact of measurement error on accelerated failure time (AFT) models has received little attention, though AFT models are very useful in survival data analysis. In this paper, we discuss AFT models with error-prone covariates and study the bias induced by the naive approach of ignoring measurement error in covariates. To adjust for such a bias, we describe a simulation and extrapolation method. This method is appealing because it is simple to implement and it does not require modelling the true but error-prone covariate process that is often not observable. Asymptotic normality for the resulting estimators is established. Simulation studies are carried out to evaluate the performance of the proposed method as well as the impact of ignoring measurement error in covariates. The proposed method is applied to analyse a data set arising from the Busselton Health study (Australian J. Public Health 1994; 18:129-135).

A common task in microarray data analysis consists of identifying genes associated with a phenotype. When the outcomes of interest are censored time-to-event data, standard approaches assess the effect of genes by fitting univariate survival models. In this paper, we propose a Bayesian variable selection approach, which allows the identification of relevant markers by jointly assessing sets of genes. We consider accelerated failure time (AFT) models with log-normal and log-t distributional assumptions. A data augmentation approach is used to impute the failure times of censored observations and mixture priors are used for the regression coefficients to identify promising subsets of variables. The proposed method provides a unified procedure for the selection of relevant genes and the prediction of survivor functions. We demonstrate the performance of the method on simulated examples and on several microarray datasets. For the simulation study, we consider scenarios with large number of noisy variables and different degrees of correlation between the relevant and non-relevant (noisy) variables. We are able to identify the correct covariates and obtain good prediction of the survivor functions. For the microarray applications, some of our selected genes are known to be related to the diseases under study and a few are in agreement with findings from other researchers. The Matlab code for implementing the Bayesian variable selection method may be obtained from the corresponding author. mvannucci@stat.tamu.edu Supplementary data are available at Bioinformatics online.