ROC curve estimation based on local smoothing

ROC curve is a graphical representation of the relationship between sensitivity and specificity of a diagnostic test. It is a popular tool for evaluating and comparing different diagnostic tests in medical sciences. In the literature,the ROC curve is often estimated empirically based on an empirical distribution function estimator and an empirical quantile function estimator. In this paper an alternative nonparametric procedure to estimate the ROC Curve is suggested which is based on local smoothing techniques. Several numerical examples are presented to evaluate the performance of this procedure.     

Adjusting ROC curves for covariates in the presence of verification bias

The ROC (receiver operating characteristic) curve is frequently used for describing effectiveness of a diagnostic marker or test. Classical estimation of the ROC curve uses independent identically distributed samples taken randomly from the healthy and diseased populations. Frequently not all subjects undergo a definitive gold standard assessment of disease status (verification). Estimation of the ROC curve based on data only from subjects with verified disease status may be badly biased (verification bias). In this work we investigate the properties of the doubly robust (DR) method for estimating the ROC curve adjusted for covariates (ROC regression) under verification bias. We develop the estimator's asymptotic distribution and examine its finite sample size properties via a simulation study. We apply this procedure to fingerstick postprandial blood glucose measurement data adjusting for age.     

Detecting diagnostic accuracy of two biomarkers through a bivariate log-normal ROC curve

In biomedical research, two or more biomarkers may be available for diagnosis of a particular disease. Selecting one single biomarker which ideally discriminate a diseased group from a healthy group is confront in a diagnostic process. Frequently, most of the people use the accuracy measure, area under the receiver operating characteristic (ROC) curve to choose the best diagnostic marker among the available markers for diagnosis. Some authors have tried to combine the multiple markers by an optimal linear combination to increase the discriminatory power. In this paper, we propose an alternative method that combines two continuous biomarkers by direct bivariate modeling of the ROC curve under log-normality assumption. The proposed method is applied to simulated data set and prostate cancer diagnostic biomarker data set.     

A non-inferiority test for diagnostic accuracy in the absence of the golden standard test based on the paired partial areas under receiver operating characteristic curves

Non-inferiority tests are often measured for the diagnostic accuracy in medical research. The area under the receiver operating characteristic (ROC) curve is a familiar diagnostic measure for the overall diagnostic accuracy. Nevertheless, since it may not differentiate the diverse shapes of the ROC curves with different diagnostic significance, the partial area under the ROC (PAUROC) curve, another summary measure emerges for such diagnostic processes that require the false-positive rate to be in the clinically interested range. Traditionally, to estimate the PAUROC, the golden standard (GS) test on the true disease status is required. Nevertheless, the GS test may sometimes be infeasible. Besides, in a lot of research fields such as the epidemiology field, the true disease status of the patients may not be known or available. Under the normality assumption on diagnostic test results, based on the expectation-maximization algorithm in combination with the bootstrap method, we propose the heuristic method to construct a non-inferiority test for the difference in the paired PAUROCs without the GS test. Through the simulation study, although the proposed method might provide a liberal test, as a whole, the empirical size of the proposed method sufficiently controls the size at the significance level, and the empirical power of the proposed method in the absence of the GS is as good as that of the non-inferiority in the presence of the GS. The proposed method is illustrated with the published data.     

Statistical tests for the comparison of two samples: The general alternative

It is common to test the null hypothesis that two samples were drawn from identical distributions; and the Smirnov (sometimes called Kolmogorov–Smirnov) test is conventionally applied. We present simulation results to compare the performance of this test with three recently introduced alternatives. We consider both continuous and discrete data. We show that the alternative methods preserve type I error at the nominal level as well as the Smirnov test but offer superior power. We argue for the routine replacement of the Smirnov test with the modified Baumgartner test according to Murakami (2006) Murakami, H. (2006). A k-sample rank test based on a modified Baumgartner statistic and its power comparison. Journal of the Japanese Society of Computational Statistics 19:1–13.[Crossref] , [Google Scholar], or with the test proposed by Zhang (2006) Zhang, J. (2006). Powerful two-sample tests based on the likelihood ratio. Technometrics 48:95–103.[Taylor &; Francis Online], [Web of Science ®] , [Google Scholar].     

An extension of parametric ROC analysis for calculating diagnostic accuracy when underlying distributions are mixture of Gaussian

The semiparametric LABROC approach of fitting binormal model for estimating AUC as a global index of accuracy has been justified (except for bimodal forms), while for estimating a local index of accuracy such as TPF, it may lead to a bias in severe departure of data from binormality. We extended parametric ROC analysis for quantitative data when one or both pair members are mixture of Gaussian (MG) in particular for bimodal forms. We analytically showed that AUC and TPF are a mixture of weighting parameters of different components of AUCs and TPFs of a mixture of underlying distributions. In a simulation study of six configurations of MG distributions:{bimodal, normal} and {bimodal, bimodal} pairs, the parameters of MG distributions were estimated using the EM algorithm. The results showed that the estimated AUC from our proposed model was essentially unbiased, and that the bias in the estimated TPF at a clinically relevant range of FPF was roughly 0.01 for a sample size of n=100/100. In practice, with severe departures from binormality, we recommend an extension of the LABROC and software development for future research to allow for each member of the pair of distributions to be a mixture of Gaussian that is a more flexible parametric form.     

An evaluation of some nonparametric multiple comparison procedures by Monte Carlo methods

Computer simulation techniques were employed to investigate the Type I and Type II error rates (experiment-wise and comparison-wise) of three nonparametric multiple comparison procedures. Three different underlying distributions were considered. It was found that the nonparametric analog to Fisher’s LSD (a Kruskal-Wallis test, followed by pairwise Mann-Whitney U tests if a significant overall effect is detected) appeared to be superior to the Nemenyi-Dunn and Steel-Dwass procedures, because of the extreme conservatism of these latter methods.     

Semi-parametric estimation of ROC curves based on binomial regression modelling

This paper presents a method of estimating a receiver operating characteristic (ROC) curve when the underlying diagnostic variable X is continuous and fully observed. The new method is based on modelling the probability of response given X , rather than the distribution of X given response. The method offers advantages in modelling flexibility and computational simplicity. The resulting ROC curve estimates are semi-parametric and can, in principle, take an infinite variety of shapes. Moreover, model selection can be based on standard methods within the binomial regression framework. Statistical accuracy of the curve estimate is provided by a simply implemented bootstrap approach.     

A resampling‐based test for two crossing survival curves

The area between two survival curves is an intuitive test statistic for the classical two‐sample testing problem. We propose a bootstrap version of it for assessing the overall homogeneity of these curves. Our approach allows ties in the data as well as independent right censoring, which may differ between the groups. The asymptotic distribution of the test statistic as well as of its bootstrap counterpart are derived under the null hypothesis, and their consistency is proven for general alternatives. We demonstrate the finite sample superiority of the proposed test over some existing methods in a simulation study and illustrate its application by a real‐data example.     

Statistical inference for the difference of two Lorenz curves

Testing the Lorenz dominance is of importance in economic and social sciences. In this article, we propose new tools to do inferences for the difference of two Lorenz curves. The asymptotic normality of the proposed smoothed nonparametric estimator is proved. We also propose a smoothed jackknife empirical likelihood (JEL) method which avoids to estimate the complicate asymptotic variance. It is proved that the proposed JEL ratio statistics converge to the standard chi-square distribution. Simulation studies and real data analysis are also conducted, and show encouraging finite-sample performance.     

Empirical likelihood confidence regions for comparison distributions and roc curves

Abstract: The authors derive empirical likelihood confidence regions for the comparison distribution of two populations whose distributions are to be tested for equality using random samples. Another application they consider is to ROC curves, which are used to compare measurements of a diagnostic test from two populations. The authors investigate the smoothed empirical likelihood method for estimation in this context, and empirical likelihood based confidence intervals are obtained by means of the Wilks theorem. A bootstrap approach allows for the construction of confidence bands. The method is illustrated with data analysis and a simulation study.     

Comparing the performance of normality tests with ROC analysis and confidence intervals

There are several statistical hypothesis tests available for assessing normality assumptions, which is an a priori requirement for most parametric statistical procedures. The usual method for comparing the performances of normality tests is to use Monte Carlo simulations to obtain point estimates for the corresponding powers. The aim of this work is to improve the assessment of 9 normality hypothesis tests. For that purpose, random samples were drawn from several symmetric and asymmetric nonnormal distributions and Monte Carlo simulations were carried out to compute confidence intervals for the power achieved, for each distribution, by two of the most usual normality tests, Kolmogorov–Smirnov with Lilliefors correction and Shapiro–Wilk. In addition, the specificity was computed for each test, again resorting to Monte Carlo simulations, taking samples from standard normal distributions. The analysis was then additionally extended to the Anderson–Darling, Cramer-Von Mises, Pearson chi-square Shapiro–Francia, Jarque–Bera, D'Agostino and uncorrected Kolmogorov–Smirnov tests by determining confidence intervals for the areas under the receiver operating characteristic curves. Simulations were performed to this end, wherein for each sample from a nonnormal distribution an equal-sized sample was taken from a normal distribution. The Shapiro–Wilk test was seen to have the best global performance overall, though in some circumstances the Shapiro–Francia or the D'Agostino tests offered better results. The differences between the tests were not as clear for smaller sample sizes. Also to be noted, the SW and KS tests performed generally quite poorly in distinguishing between samples drawn from normal distributions and t Student distributions.     

A two sample ordered alternative test for means and variances

A two sample test of likelihood ratio type is proposed, assuming normal distribution theory, for testing the hypothesis that two samples come from identical normal populations versus the alternative that the populations are normal but vary in mean value and variance with one population having a smaller mean and smaller variance than the other. The small sample and large sample distribution of the proposed statistic are derived assuming normality. Some computations are presented which show the speed of convergence of small sample critical values to their asymptotic counterparts. Comparisons of local power of the proposed test are made with several potential competing tests. Asymptotics for the test statistic are derived when underlying distributions are not necessarily normal.     

Selection and combination of biomarkers using ROC method for disease classification and prediction

Based on the SCAD penalty and the area under the ROC curve (AUC), we propose a new method for selecting and combining biomarkers for disease classification and prediction. The proposed estimator for the combination of the biomarkers has an oracle property; that is, the estimated combination of the biomarkers performs as well as it would have been if the biomarkers significantly associated with the outcome had been known in advance, in terms of discriminative power. The proposed estimator is computationally feasible, n^1/2‐consistent and asymptotically normal. Simulation studies show that the proposed method performs better than existing methods. We illustrate the proposed methodology in the acoustic startle response study. The Canadian Journal of Statistics 39: 324–343; 2011 © 2011 Statistical Society of Canada     

Many-to-one comparison of nonlinear growth curves for Washington's Red Delicious apple

In this article, we are interested in comparing growth curves for the Red Delicious apple in several locations to that of a reference site. Although such multiple comparisons are common for linear models, statistical techniques for nonlinear models are not prolific. We theoretically derive a test statistic, considering the issues of sample size and design points. Under equal sample sizes and same design points, our test statistic is based on the maximum of an equi-correlated multivariate chi-square distribution. Under unequal sample sizes and design points, we derive a general correlation structure, and then utilize the multivariate normal distribution to numerically compute critical points for the maximum of the multivariate chi-square. We apply this statistical technique to compare the growth of Red Delicious apples at six locations to a reference site in the state of Washington in 2009. Finally, we perform simulations to verify the performance of our proposed procedure for Type I error and marginal power. Our proposed method performs well in regard to both.     

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.     

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.     

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.     

Non-parametric weighted tests for independence based on empirical copula process

We propose a class of flexible non-parametric tests for the presence of dependence between components of a random vector based on weighted Cramér–von Mises functionals of the empirical copula process. The weights act as a tuning parameter and are shown to significantly influence the power of the test, making it more sensitive to different types of dependence. Asymptotic properties of the test are stated in the general case, for an arbitrary bounded and integrable weighting function, and computational formulas for a number of weighted statistics are provided. Several issues relating to the choice of the weights are discussed, and a simulation study is conducted to investigate the power of the test under a variety of dependence alternatives. The greatest gain in power is found to occur when weights are set proportional to true deviations from independence copula.