Semi-empirical likelihood inference for the ROC curve with missing data

The receiver operating characteristic (ROC) curve is one of the most commonly used methods to compare the diagnostic performance of two or more laboratory or diagnostic tests. In this paper, we propose semi-empirical likelihood based confidence intervals for ROC curves of two populations, where one population is parametric and the other one is non-parametric and both have missing data. After imputing missing values, we derive the semi-empirical likelihood ratio statistic and the corresponding likelihood equations. It is shown that the log-semi-empirical likelihood ratio statistic is asymptotically scaled chi-squared. The estimating equations are solved simultaneously to obtain the estimated lower and upper bounds of semi-empirical likelihood confidence intervals. We conduct extensive simulation studies to evaluate the finite sample performance of the proposed empirical likelihood confidence intervals with various sample sizes and different missing probabilities.     

Robust transformation mixed‐effects models for longitudinal continuous proportional data

The authors propose a robust transformation linear mixed‐effects model for longitudinal continuous proportional data when some of the subjects exhibit outlying trajectories over time. It becomes troublesome when including or excluding such subjects in the data analysis results in different statistical conclusions. To robustify the longitudinal analysis using the mixed‐effects model, they utilize the multivariate t distribution for random effects or/and error terms. Estimation and inference in the proposed model are established and illustrated by a real data example from an ophthalmology study. Simulation studies show a substantial robustness gain by the proposed model in comparison to the mixed‐effects model based on Aitchison's logit‐normal approach. As a result, the data analysis benefits from the robustness of making consistent conclusions in the presence of influential outliers. The Canadian Journal of Statistics © 2009 Statistical Society of Canada     

Nonparametric estimation of the ROC curve for length-biased and right-censored data

Abstract

ROC curve is a fundamental evaluation tool in medical researches and survival analysis. The estimation of ROC curve has been studied extensively with complete data and right-censored survival data. However, these methods are not suitable to analyze the length-biased and right-censored data. Since this kind of data includes the auxiliary information that truncation time and residual time share the same distribution, the two new estimators for the ROC curve are proposed by taking into account this auxiliary information to improve estimation efficiency. Numerical simulation studies with different assumed cases and real data analysis are conducted.     

Estimation of the area under ROC curve with censored data

The area under the receiver operating characteristic curve is the most commonly used summary measure of diagnostic accuracy for a continuous-scale diagnostic test. In this paper, we develop methods to estimate the area under the curve (AUC) with censored data. Based on two different integration representations of this parameter, two nonparametric estimators are defined by the “plug in” method. Both the proposed estimators are shown to be asymptotically normal based on counting process and martingale theory. A simulation study is conducted to evaluate the performances of the proposed estimators.     

Improving an estimator of Hsieh and Turnbull for the binormal ROC curve

The estimator of Hsieh and Turnbull (1996) for the binormal receiver operating characteristic (ROC) curve is extended from grouped to ungrouped data. The new estimator is shown to be consistent and asymptotically normally distributed, and simulation results show that it outperforms Hsieh and Turnbull's original estimator.     

Flexible Tweedie regression models for continuous data

Tweedie regression models (TRMs) provide a flexible family of distributions to deal with non-negative right-skewed data and can handle continuous data with probability mass at zero. Estimation and inference of TRMs based on the maximum likelihood (ML) method are challenged by the presence of an infinity sum in the probability function and non-trivial restrictions on the power parameter space. In this paper, we propose two approaches for fitting TRMs, namely quasi-likelihood (QML) and pseudo-likelihood (PML). We discuss their asymptotic properties and perform simulation studies to compare our methods with the ML method. We show that the QML method provides asymptotically efficient estimation for regression parameters. Simulation studies showed that the QML and PML approaches present estimates, standard errors and coverage rates similar to the ML method. Furthermore, the second-moment assumptions required by the QML and PML methods enable us to extend the TRMs to the class of quasi-TRMs in Wedderburn's style. It allows to eliminate the non-trivial restriction on the power parameter space, and thus provides a flexible regression model to deal with continuous data. We provide an R implementation and illustrate the application of TRMs using three data sets.     

Area under the ROC curve comparison in the presence of missing data

The area under the receiver operating characteristic (ROC) curve (AUC) is broadly accepted and often used as a diagnostic accuracy index. Moreover, the equality among the predictive capacity of two or more diagnostic systems is frequently checked from the comparison of their respective AUCs. In paired designs, this comparison is usually performed by using only the subjects who have collected all the necessary information, in the so-called available-case analysis. On the other hand, the presence of missing data is a frequent problem, especially in retrospective and observational studies. The loss of statistical power and the misuse of the available information (with the resulting ethical implications) are the main consequences. In this paper a non-parametric method is developed to exploit all available information. In order to approximate the distribution for the proposed statistic, the asymptotic distribution is computed and two different resampling plans are studied. In addition, the methodology is applied to a real-world medical problem. Finally, some technical issues are also reported in the Appendix.     

Additive transformation models for clustered failure time data

We propose a class of additive transformation risk models for clustered failure time data. Our models are motivated by the usual additive risk model for independent failure times incorporating a frailty with mean one and constant variability which is a natural generalization of the additive risk model from univariate failure time to multivariate failure time. An estimating equation approach based on the marginal hazards function is proposed. Under the assumption that cluster sizes are completely random, we show the resulting estimators of the regression coefficients are consistent and asymptotically normal. We also provide goodness-of-fit test statistics for choosing the transformation. Simulation studies and real data analysis are conducted to examine the finite-sample performance of our estimators.     

Imputation for semiparametric transformation models with biased-sampling data

Widely recognized in many fields including economics, engineering, epidemiology, health sciences, technology and wildlife management, length-biased sampling generates biased and right-censored data but often provide the best information available for statistical inference. Different from traditional right-censored data, length-biased data have unique aspects resulting from their sampling procedures. We exploit these unique aspects and propose a general imputation-based estimation method for analyzing length-biased data under a class of flexible semiparametric transformation models. We present new computational algorithms that can jointly estimate the regression coefficients and the baseline function semiparametrically. The imputation-based method under the transformation model provides an unbiased estimator regardless whether the censoring is independent or not on the covariates. We establish large-sample properties using the empirical processes method. Simulation studies show that under small to moderate sample sizes, the proposed procedure has smaller mean square errors than two existing estimation procedures. Finally, we demonstrate the estimation procedure by a real data example.     

Semiparametric linear transformation models for current status data

Current status data arise when the death of every subject in a study cannot be determined precisely, but is known only to have occurred before or after a random monitoring time. The authors discuss the analysis of such data under semiparametric linear transformation models for which they propose a general inference procedure based on estimating functions. They determine the properties of the estimates they propose for the regression parameters of the model and illustrate their technique using tumorigenicity data.     

A transformation for estimating the trinomial logit model with grouped data

For logit models where the outcome variables are the proportions of individuals falling into each of three categories, this paper develops a data transformation through which GLS estimates can be obtained by running OLS on the transformed data.     

Bayesian ROC curve estimation under binormality using an ordinal category likelihood

Receiver operating characteristic (ROC) curve has been widely used in medical diagnosis. Various methods are proposed to estimate ROC curve parameters under the binormal model. In this paper, we propose a Bayesian estimation method from the continuously distributed data which is constituted by the truth-state-runs in the rank-ordered data. By using an ordinal category data likelihood and following the Metropolis–Hastings (M–H) procedure, we compute the posterior distribution of the binormal parameters, as well as the group boundaries parameters. Simulation studies and real data analysis are conducted to evaluate our Bayesian estimation method.     

Optimal nonparametric estimator of the area under ROC curve based on clustered data

Abstract

In diagnostic trials, clustered data are obtained when several subunits of the same patient are observed. Intracluster correlations need to be taken into account when analyzing such clustered data. A nonparametric method has been proposed by Obuchowski (1997 Obuchowski, N. A. 1997. Nonparametric analysis of clustered ROC curve data. Biometrics 53 (2):567–78.[Crossref], [PubMed], [Web of Science ®] , [Google Scholar]) to estimate the Receiver Operating Characteristic curve area (AUC) for such clustered data. However, Obuchowski’s estimator is not efficient as it gives equal weight to all pairwise rankings within and between cluster. In this paper, we propose a more efficient nonparametric AUC estimator with two sets of optimal weights. Simulation results show that the loss of efficiency of Obuchowski’s estimator for a single AUC or the AUC difference can be substantial when there is a moderate intracluster test correlation and the cluster size is large. The efficiency gain of our weighted AUC estimator for a single AUC or the AUC difference is further illustrated using the data from a study of screening tests for neonatal hearing.     

Varying coefficient transformation cure models for failure time data

This article discusses regression analysis of right-censored failure time data where there may exist a cured subgroup, and also covariate effects may be varying with time, a phenomena that often occurs in many medical studies. To address the problem, we discuss a class of varying coefficient transformation models along with a logistic model for the cured subgroup. For inference, a sieve maximum likelihood approach is developed with the use of spline functions, and the asymptotic properties of the proposed estimators are established. The proposed method can be easily implemented, and the conducted simulation study suggests that the proposed method works well in practical situations. An illustrative example is provided.

     

Asymptotics and bootstrap for random-effects panel data transformation models

This article investigates the asymptotic properties of quasi-maximum likelihood (QML) estimators for random-effects panel data transformation models where both the response and (some of) the covariates are subject to transformations for inducing normality, flexible functional form, homoskedasticity, and simple model structure. We develop a QML-type procedure for model estimation and inference. We prove the consistency and asymptotic normality of the QML estimators, and propose a simple bootstrap procedure that leads to a robust estimate of the variance-covariance (VC) matrix. Monte Carlo results reveal that the QML estimators perform well in finite samples, and that the gains by using the robust VC matrix estimate for inference can be enormous.     

General partially linear varying-coefficient transformation models for ranking data

In this paper,we propose a class of general partially linear varying-coefficient transformation models for ranking data. In the models, the functional coefficients are viewed as nuisance parameters and approximated by B-spline smoothing approximation technique. The B-spline coefficients and regression parameters are estimated by rank-based maximum marginal likelihood method. The three-stage Monte Carlo Markov Chain stochastic approximation algorithm based on ranking data is used to compute estimates and the corresponding variances for all the B-spline coefficients and regression parameters. Through three simulation studies and a Hong Kong horse racing data application, the proposed procedure is illustrated to be accurate, stable and practical.     

Analysing competing risks data with transformation models

We present a flexible class of marginal models for the cumulative incidence function. The semiparametric transformation model is utilized in a decomposition for the marginal failure probabilities which extends previous work on Farewell's cure model. Novel estimation, inference and prediction procedures are developed, with large sample properties derived from the theory of martingales and U-statistics. A small simulation study demonstrates that the methods are appropriate for practical use. The methods are illustrated with a thorough analysis of a prostate cancer clinical trial. Simple graphical displays are used to check for the goodness of fit.     

Confidence intervals and bands for the binormal ROC curve revisited

Two types of confidence intervals (CIs) and confidence bands (CBs) for the receiver operating characteristic (ROC) curve are studied: pointwise CIs and simultaneous CBs. An optimized version of the pointwise CI with the shortest width is developed. A new ellipse-envelope simultaneous CB for the ROC curve is suggested as an adaptation of the Working-Hotelling-type CB implemented in a paper by Ma and Hall (1993). Statistical simulations show that our ellipse-envelope CB covers the true ROC curve with a probability close to nominal while the coverage probability of the Ma and Hall CB is significantly smaller. Simulations also show that our CI for the area under the ROC curve is close to nominal while the coverage probability of the CI suggested by Hanley and McNail (1982) uniformly overestimates the nominal value. Two examples illustrate our simultaneous ROC bands: radiation dose estimation from time to vomiting and discrimination of breast cancer from benign abnormalities using electrical impedance measurements.