Search

Suppose we are interested in the effect of a treatment in a clinical trial. The efficiency of inference may be limited due to small sample size. However, external control data are often available from historical studies. Motivated by an application to Helicobacter pylori infection, we show how to borrow strength from such data to improve efficiency of inference in the clinical trial. Under an exchangeability assumption about the potential outcome mean, we show that the semiparametric efficiency bound for estimating the average treatment effect can be reduced by incorporating both the clinical trial data and external controls. We then derive a doubly robust and locally efficient estimator. The improvement in efficiency is prominent especially when the external control dataset has a large sample size and small variability. Our method allows for a relaxed overlap assumption, and we illustrate with the case where the clinical trial only contains a treated group. We also develop doubly robust and locally efficient approaches that extrapolate the causal effect in the clinical trial to the external population and the overall population. Our results also offer a meaningful implication for trial design and data collection. We evaluate the finite-sample performance of the proposed estimators via simulation. In the Helicobacter pylori infection application, our approach shows that the combination treatment has potential efficacy advantages over the triple therapy., Accepted for publication in Biometrics; 1 figure, 3 tables

This study proposes novel estimation and inference approaches for heterogeneous local treatment effects using high-dimensional covariates and observational data without a strong ignorability assumption. To achieve this, with a binary instrumental variable, the parameters of interest are identified on an unobservable subgroup of the population (compliers). Lasso estimation under a non-convex objective function is developed for a two-stage generalized linear model, and a debiased estimator is proposed to construct confidence intervals for treatment effects conditioned on covariates. Notably, this approach simultaneously corrects the biases due to high-dimensional estimation at both stages. The finite sample performance is evaluated via simulation studies, and real data analysis is performed on the Oregon Health Insurance Experiment to illustrate the feasibility of the proposed procedure.

Parallel-group thorough QT/QTc studies focus on the change of QT/QTc values at several time-matched points from a pretreatment day (baseline) to a posttreatment day for different groups of treatment. The International Council for Harmonisation E14 stresses that QTc prolongation beyond a threshold represents high cardiac risk and calls for a test on the largest time-matched treatment effect (QTc prolongation). QT/QTc analysis usually assumes a jointly multivariate normal (MVN) distribution of pretreatment and posttreatment QT/QTc values, with a blocked compound symmetry covariance matrix. Existing methods use an analysis of covariance (ANCOVA) model including day-averaged baseline as a covariate to deal with the MVN model. However, the ANCOVA model tends to underestimate the variation of the estimator for treatment effects, resulting in the inflation of empirical type I error rate when testing whether the largest QTc prolongation is beyond a threshold. In this article, we propose two new methods to estimate the time-matched treatment effects under the MVN model, including maximum likelihood estimation and ordinary-least-square-based two-stage estimation. These two methods take advantage of the covariance structure and are asymptotically efficient. Based on these estimators, powerful tests for QT/QTc prolongation are constructed. Simulation shows that the proposed estimators have smaller mean square error, and the tests can control the type I error rate with high power. The proposed methods are applied on testing the carryover effect of diltiazem to inhibit dofetilide in a randomized phase 1 trial.

With a large number of baseline covariates, we propose a new semi-parametric modeling strategy for heterogeneous treatment effect estimation and individualized treatment selection, which are two major goals in personalized medicine. We achieve the first goal through estimating a covariate-specific treatment effect (CSTE) curve modeled as an unknown function of a weighted linear combination of all baseline covariates. The weight or the coefficient for each covariate is estimated by fitting a sparse semi-parametric logistic single-index coefficient model. The CSTE curve is estimated by a spline-backfitted kernel procedure, which enables us to further construct a simultaneous confidence band (SCB) for the CSTE curve under a desired confidence level. Based on the SCB, we find the subgroups of patients that benefit from each treatment, so that we can make individualized treatment selection. The innovations of the proposed method are three-fold. First, the proposed method can quantify variability associated with the estimated optimal individualized treatment rule with high-dimensional covariates. Second, the proposed method is very flexible to depict both local and global associations between the treatment and baseline covariates in the presence of high-dimensional covariates, and thus it enjoys flexibility while achieving dimensionality reduction. Third, the SCB achieves the nominal confidence level asymptotically, and it provides a uniform inferential tool in making individualized treatment decisions.

The adequacy check of regression models is a fundamental approach to avoid model misspecifications. Three types of tests: the weighted integrated squared distance test, the U-statistic test and the empirical process based test, are very popular due to attractive theoretical merits such as consistency and satisfactory performances in practice. In this paper, we apply these three tests to check the adequacy of a mean parametric regression model with measurement error. By rigorously investigating the asymptotic properties of three testing methods under the null, local and global alternative hypotheses, we make detailed comparisons for the three tests. To the best of our knowledge, the results of these theoretical comparisons are novel. We conduct simulation studies and a real data analysis to compare the finite sample behaviors of the proposed methods.

Under the random design of longitudinal data, observation times are irregular, and there are mainly two frameworks for analyzing such kind of longitudinal data. One is the clustered data framework and the other is the counting process framework. In this paper, we give a thorough comparison of these two frameworks in terms of data structure, model assumptions and estimation procedures. We find that modeling the observation times in the counting process framework will not gain any efficiency when the observation times are correlated with covariates but independent of the longitudinal response given covariates. Some simulation studies are conducted to compare the finite sample behaviors of the related estimators, and a real data analysis of the Alzheimer’s disease study is implemented for further comparison.

Average bioequivalence tests are used in clinical trials to determine whether a generic drug has the same effect as an original drug in the population. For highly variable drugs whose intra-subject variances of direct drug effects are high, extra criteria are needed in bioequivalence studies. Currently used average bioequivalence tests for highly variable drugs recommended by the European Medicines Agency and the US Food and Drug Administration use sample estimators in the null hypotheses of interest. They cannot control the empirical type I error rate, so the consumer's risk is higher than the predetermined level. In this paper, we propose two new statistically sound methods that can control the empirical type I error rate without involving any sample estimators in the null hypotheses. In the proposed methods, we consider the average level of direct drug effects and the intra-subject variance of the direct drug effects. The first proposed method tests the latter parameter first to determine whether a product should be regarded as a highly variable drug, and then tests the former using corresponding bioequivalence limits. The second proposed method tests these two parameters simultaneously to capture the bioequivalence region. Extensive simulations are done to compare these methods. The simulation results show that the proposed methods have good performance on controlling the empirical type I error rate. The proposed methods are useful for pharmaceutical manufacturers and regulators.

Meta-analysis provides a quantitative method for combining results from independent studies with the same treatment. However, existing estimation methods are sensitive to the presence of outliers in the datasets. In this paper we study the robust estimation for the parameters in meta-regression, including the between-study variance and regression parameters. Huber’s rho function and Tukey’s biweight function are adopted to derive the formulae of robust maximum likelihood ( ML ) estimators. The corresponding algorithms are developed. The asymptotic confidence interval and second-order-corrected confidence interval are investigated. Extensive simulation studies are conducted to assess the performance of the proposed methodology, and our results show that the robust estimators are promising and outperform the conventional ML and restricted maximum likelihood estimators when outliers exist in the dataset. The proposed methods are applied in three case studies and the results further support the eligibility of our methods in practical situations.

The incubation period and generation time are key characteristics in the analysis of infectious diseases. The commonly used contact‐tracing based estimation of incubation distribution is highly influenced by the individuals' judgment on the possible date of exposure, and might lead to significant errors. On the other hand, interval censoring based methods are able to utilize a much larger set of traveling data but may encounter biased sampling problems. The distribution of generation time is usually approximated by observed serial intervals. However, it may result in a biased estimation of generation time, especially when the disease is infectious during incubation. In this paper, the theory from renewal process is partially adopted by considering the incubation period as the inter‐arrival time, and the duration between departure from Wuhan and onset of symptoms as the mixture of forward time and inter‐arrival time with censored intervals. In addition, a consistent estimator for the distribution of generation time based on incubation period and serial interval is proposed for incubation‐infectious diseases. A real case application to the current outbreak of COVID‐19 is implemented. We find that the incubation period has a median of 8.50 days (95% CI: 7.22, 9.15). The basic reproduction number in the early phase of COVID‐19 outbreak based on the proposed generation time estimation is estimated to be 2.96 (95% CI: 2.15, 3.86). This article is protected by copyright. All rights reserved

COVID-19 caused rapid mass infection worldwide. Understanding its transmission characteristics, including heterogeneity and the emergence of super spreading events (SSEs) where certain individuals infect large numbers of secondary cases, is of vital importance for prediction and intervention of future epidemics. Here, we collected information of all infected cases (135 cases) between 21 January and 26 February 2020 from official public sources in Tianjin, a metropolis of China, and grouped them into 43 transmission chains with the largest chain of 45 cases and the longest chain of four generations. Utilizing a heterogeneous transmission model based on branching process along with a negative binomial offspring distribution, we estimated the reproductive number R and the dispersion parameter k (lower value indicating higher heterogeneity) to be 0.67 (95% CI: 0.54&ndash, 0.84) and 0.25 (95% CI: 0.13&ndash, 0.88), respectively. A super-spreader causing six infections was identified in Tianjin. In addition, our simulation allowing for heterogeneity showed that the outbreak in Tianjin would have caused 165 infections and sustained for 7.56 generations on average if no control measures had been taken by local government since 28 January. Our results highlighted more efforts are needed to verify the transmission heterogeneity of COVID-19 in other populations and its contributing factors.

This study estimated the incubation distribution of COVID-19 using the theory of renewal process., We have proposed a novel, accurate low-cost method to estimate the incubation-period distribution of COVID-19 by conducting a cross-sectional and forward follow-up study. We identified those presymptomatic individuals at their time of departure from Wuhan and followed them until the development of symptoms. The renewal process was adopted by considering the incubation period as a renewal and the duration between departure and symptoms onset as a forward time. Such a method enhances the accuracy of estimation by reducing recall bias and using the readily available data. The estimated median incubation period was 7.76 days [95% confidence interval (CI): 7.02 to 8.53], and the 90th percentile was 14.28 days (95% CI: 13.64 to 14.90). By including the possibility that a small portion of patients may contract the disease on their way out of Wuhan, the estimated probability that the incubation period is longer than 14 days was between 5 and 10%.

Background: The 2019 novel coronavirus (2019-nCoV) outbreak in Wuhan, China has attracted world-wide attention. As of February 11, 2020, a total of 44,730 cases of pneumonia associated with the 2019-nCoV were confirmed by the National Health Commission (NHC) of China. Methods: Three approaches, namely Poisson likelihood-based method (ML), exponential growth rate-based method (EGR) and stochastic Susceptible-Infected-Removed dynamic model-based method (SIR), were implemented to estimate the basic and controlled reproduction numbers. Results: A total of 71 chains of transmission together with dates of symptoms onset and 67 dates of infections were identified among 5,405 confirmed cases outside Hubei as reported by February 2, 2020. Based on this information, we find the serial interval having an average of 4.27 days with a standard deviation of 3.44 days, the incubation period having an average of 5.33 days with a standard deviation of 3.36 days and the infectious period having an average of 10.91 days with a standard deviation of 3.95 days. The estimated controlled reproduction numbers, 𝑅𝑐 , produced by all three methods in all analyzed regions of China are significantly smaller compared with the basic reproduction numbers 𝑅0. Conclusions: The controlled reproduction number is declining. It is lower than one in most regions of China, but still larger than one in Hubei Province. Sustained efforts are needed to further keep/reduce the 𝑅𝑐 to below one in order to end the current epidemic. Funding Statement: The authors stated that they have no financial relationships (regardless of amount of compensation) with any entities. Declaration of Interests: The authors declare there is no conflict of interest. Ethics Approval Statement: The authors stated this was not required.

Right censored survival data collected on a prevalent cohort with constant incidence rate are termed as length-biased survival data. In this paper, we consider semiparametric estimation for the Cox proportional hazards model with length-biased survival data. Utilizing the special structure of length-biased sampling, we give the semiparametric maximum likelihood estimators for the regression parameter and cumulative hazard function. The estimators are shown to be consistent and asymptotically normal, and the limiting variance of the regression parameter estimator achieves the semiparametric efficiency bound. The asymptotic variance of the estimators can be estimated consistently. Simulation studies show the proposed semiparametric maximum likelihood estimator is more efficient than existing estimators in the literature. An analysis of the prevalent data from Canadian Study of Health and Aging (CSHA) illustrates the proposed method.

In a clinical trial, statistical reports are typically concerned about the mean difference in two groups. Now there is increasing interest in the heterogeneity of the treatment effect, which has important implications in treatment evaluation and selection. The treatment harm rate (THR), which is defined by the proportion of people who has a worse outcome on the treatment compared to the control, was used to characterize the heterogeneity. Since THR involves the joint distribution of the two potential outcomes, it cannot be identified without further assumptions even in the randomized trials. We can only derive the simple bounds with the observed data. But the simple bounds are usually too wide. In this paper, we use a secondary outcome that satisfies the monotonicity assumption to tighten the bounds. It is shown that the bounds we derive cannot be wider than the simple bounds. We also construct some simulation studies to assess the performance of our bounds in finite sample. The results show that a secondary outcome, which is more closely related to the primary outcome, can lead to narrower bounds. Finally, we illustrate the application of the proposed bounds in a randomized clinical trial of determining whether the intensive glycemia could reduce the risk of development or progression of diabetic retinopathy.

It is common in medical studies that the outcome of interest is truncated by death, meaning that a subject has died before the outcome could be measured. In this case, restricted analysis among survivors may be subject to selection bias. Hence, it is of interest to estimate the survivor average causal effect, defined as the average causal effect among the subgroup consisting of subjects who would survive under either exposure. In this paper, we consider the identification and estimation problems of the survivor average causal effect. We propose to use a substitution variable in place of the latent membership in the always-survivor group. The identification conditions required for a substitution variable are conceptually similar to conditions for a conditional instrumental variable, and may apply to both randomized and observational studies. We show that the survivor average causal effect is identifiable with use of such a substitution variable, and propose novel model parameterizations for estimation of the survivor average causal effect under our identification assumptions. Our approaches are illustrated via simulation studies and a data analysis., Comment: Correct a typo in equation (8)

Quantile residual lifetime models are often of concern in survival analysis, especially when studying a chronic or irreversible disease like dementia. In the past several decades residual life models have been studied extensively with right-censored survival data. However these methods are not suitable to analyze the length-biased and right-censored data from the prevalent cohort sampling. In this article we propose nonparametric and semiparametric model-based procedures to estimate the quantile residual lifetime with censored length-biased data. Two test statistics are established for comparing the quantile residual lifetimes of two groups, evaluated, respectively, on ratio and difference in terms of type I error probabilities and powers. Some simulations are conducted to compare the proposed method with existing approaches. Real dementia data from the National Alzheimer's Coordinating Center are used to illustrate the proposed estimation methods by estimating the quantile residual lifetimes of the dementia patients. The Canadian Journal of Statistics 45: 220–250; 2017 © 2017 Statistical Society of Canada

Mediation analysis is an important topic as it helps researchers to understand why an intervention works. Most previous mediation analyses define effects in the mean scale and require a binary or continuous outcome. Recently, possible ways to define direct and indirect effects for causal mediation analysis with survival outcome were proposed. However, these methods mainly rely on the assumption of sequential ignorability, which implies no unmeasured confounding. To handle the potential confounding between the mediator and the outcome, in this article, we proposed a structural additive hazard model for mediation analysis with failure time outcome and derived estimators for controlled direct effects and controlled mediator effects. Our methods allow time-varying effects. Simulations showed that our proposed estimator is consistent in the presence of unmeasured confounding while the traditional additive hazard regression ignoring unmeasured confounding produces biased results. We applied our method to the Women's Health Initiative data to study whether the dietary intervention affects breast cancer risk through changing body weight.

Prognostic studies are widely conducted to examine whether biomarkers are associated with patient's prognoses and play important roles in medical decisions. Because findings from one prognostic study may be very limited, meta-analyses may be useful to obtain sound evidence. However, prognostic studies are often analyzed by relying on a study-specific cut-off value, which can lead to difficulty in applying the standard meta-analysis techniques. In this paper, we propose two methods to estimate a time-dependent version of the summary receiver operating characteristics curve for meta-analyses of prognostic studies with a right-censored time-to-event outcome. We introduce a bivariate normal model for the pair of time-dependent sensitivity and specificity and propose a method to form inferences based on summary statistics reported in published papers. This method provides a valid inference asymptotically. In addition, we consider a bivariate binomial model. To draw inferences from this bivariate binomial model, we introduce a multiple imputation method. The multiple imputation is found to be approximately proper multiple imputation, and thus the standard Rubin's variance formula is justified from a Bayesian view point. Our simulation study and application to a real dataset revealed that both methods work well with a moderate or large number of studies and the bivariate binomial model coupled with the multiple imputation outperforms the bivariate normal model with a small number of studies. Copyright © 2016 John Wiley & Sons, Ltd.

The objective of diagnostic studies or prognostic studies is to evaluate and compare predictive capacities of biomarkers. Suppose we are interested in evaluation and comparison of predictive capacities of continuous biomarkers for a binary outcome based on research synthesis. In analysis of each study, subjects are often classified into two groups of the high-expression and low-expression groups according to a cut-off value, and statistical analysis is based on a 2 × 2 table defined by the response and the high expression or low expression of the biomarker. Because the cut-off is study specific, it is difficult to interpret a combined summary measure such as an odds ratio based on the standard meta-analysis techniques. The summary receiver operating characteristic curve is a useful method for meta-analysis of diagnostic studies in the presence of heterogeneity of cut-off values to examine discriminative capacities of biomarkers. We develop a method to estimate positive or negative predictive curves, which are alternative to the receiver operating characteristic curve based on information reported in published papers of each study. These predictive curves provide a useful graphical presentation of pairs of positive and negative predictive values and allow us to compare predictive capacities of biomarkers of different scales in the presence of heterogeneity in cut-off values among studies. Copyright © 2016 John Wiley & Sons, Ltd.

Introduction: Four new nonproprietary tests were recommended for use in the National Alzheimer’s Coordinating Center’s Uniform Data Set Neuropsychological Battery. These tests are similar to previous tests but also allow for continuity of longitudinal data collection and wide dissemination among research collaborators. Methods: A Crosswalk Study was conducted in early 2014 to assess the correlation between each set of new and previous tests. Tests with good correlation were equated using equipercentile equating. The resulting conversion tables allow scores on the new tests to be converted to equivalent scores on the previous tests. Results: All pairs of tests had good correlation (ρ=0.68 to 0.78). Learning effects were detected for Logical Memory only. Confidence intervals were narrow at each point estimate, and prediction accuracy was high. Discussion: The recommended new tests are well correlated with the previous tests. The equipercentile equating method produced conversion tables that provide a useful reference for clinicians and researchers.

Dynamic conditional score (DCS) model is a new type of observation-driven model based on the score function. Based on time-varying scale, Harvey (2013) proposed univariate DCS models with skew Student distribution. We redescribe these models based on log-variance and extend them to models based on variance. In the modeling process, calculating score of the distribution is a key part. When selecting scale or variance to calculate the score, two subclasses of DCS models with skew Student distribution are derived. We study them separately in detail, and the models with leverage have been presented too. For estimating one-day-ahead VaR and ES, we combine these models with AR(1) into new ones. By backtesting their performance for four international stock indices, we find that all these AR–DCS models perform well on forcasting VaR and ES at the confidence levels 95%, 99% and 99.5%.

In observational studies, estimation of average causal treatment effect on a patient's response should adjust for confounders that are associated with both treatment exposure and response. In addition, the response, such as medical cost, may have incomplete follow-up. In this article, a double robust estimator is proposed for average causal treatment effect for right censored medical cost data. The estimator is double robust in the sense that it remains consistent when either the model for the treatment assignment or the regression model for the response is correctly specified. Double robust estimators increase the likelihood the results will represent a valid inference. Asymptotic normality is obtained for the proposed estimator, and an estimator for the asymptotic variance is also derived. Simulation studies show good finite sample performance of the proposed estimator and a real data analysis using the proposed method is provided as illustration. Copyright © 2016 John Wiley & Sons, Ltd.

Noncompliance and missing data often occur in randomized trials, which complicate the inference of causal effects. When both noncompliance and missing data are present, previous papers proposed moment and maximum likelihood estimators for binary and normally distributed continuous outcomes under the latent ignorable missing data mechanism. However, the latent ignorable missing data mechanism may be violated in practice, because the missing data mechanism may depend directly on the missing outcome itself. Under noncompliance and an outcome-dependent nonignorable missing data mechanism, previous studies showed the identifiability of complier average causal effect for discrete outcomes. In this paper, we study the semiparametric identifiability and estimation of complier average causal effect in randomized clinical trials with both all-or-none noncompliance and the outcome-dependent nonignorable missing continuous outcomes, and propose a two-step maximum likelihood estimator in order to eliminate the infinite dimensional nuisance parameter. Our method does not need to specify a parametric form for the missing data mechanism. We also evaluate the finite sample property of our method via extensive simulation studies and sensitivity analysis, with an application to a double-blinded psychiatric clinical trial., Transactions on Intelligent Systems and Technology 2014

Latent class models with crossed subject-specific and test(rater)-specific random effects have been proposed to estimate the diagnostic accuracy (sensitivity and specificity) of a group of binary tests or binary ratings. However, the computation of these models are hindered by their complicated Monte Carlo Expectation-Maximization (MCEM) algorithm. In this article, a class of pseudo-likelihood functions is developed for conducting statistical inference with crossed random-effects latent class models in diagnostic medicine. Theoretically, the maximum pseudo-likelihood estimation is still consistent and has asymptotic normality. Numerically, our results show that not only the pseudo-likelihood approach significantly reduces the computational time, but it has comparable efficiency relative to the MCEM algorithm. In addition, dimension-wise likelihood, one of the proposed pseudo-likelihoods, demonstrates its superior performance in estimating sensitivity and specificity.

In this paper, we consider the nonparametric estimation of the partially linear single-index transformation model, where the transformation function, single-index function and error distribution are all completely unknown. We first use the minimum average variance estimation method to estimate the regression coefficients, and then propose a new incorporated local linear regression estimator for the derivative function of the single-index function. Accordingly by integration we can obtain the estimator of the single-index function. Finally we propose a constrained least square estimator for the transformation function, where basis function approximation is employed and cross validation method is proposed to select suitable sets of basis functions. Asymptotical properties of the estimators are established. Simulation studies show that our proposed estimators work well. A real-world data analysis of total health care charges was used to illustrate the proposed procedure. The Canadian Journal of Statistics 43: 97–117; 2015 © 2015 Statistical Society of Canada Resume Les auteurs traitent de l'estimation non parametrique du modele de transformation partiellement lineaire a un indice dans le cas ou la transformation, la fonction d'indice et la distribution de l'erreur sont toutes completement inconnues. Ils estiment d'abord les coefficients de regression par la methode de la variance moyenne minimale, puis ils proposent un nouvel estimateur local de regression lineaire pour la derivee de la fonction d'indice, menant a l'estimation de cette fonction par integration. Finalement, ils proposent un estimateur aux moindres carres avec contraintes pour la fonction de transformation dont une approximation est effectuee a l'aide de fonctions de base, elles-memes selectionnees par une procedure de validation croisee. Les auteurs etablissent les proprietes asymptotiques de leurs estimateurs et montrent a l'aide de simulations que ceux-ci donnent de bons resultats. Ils illustrent egalement leur methode en analysant un jeu de donnees reelles portant sur les couts des soins de sante. La revue canadienne de statistique 43: 97–117; 2015 © 2015 Societe statistique du Canada

Background Framingham Stroke Risk Score (FSRS) is the most well-regarded risk appraisal tools for evaluating an individual’s absolute risk on stroke onset. However, several widely accepted risk factors for stroke were not included in the original Framingham model. This study proposed a new model which combines an existing risk models with new risk factors using synthesis analysis, and applied it to the longitudinal Atherosclerosis Risk in Communities (ARIC) data set. Methods Risk factors in original prediction models and new risk factors in proposed model had been discussed. Three measures, like discrimination, calibration and reclassification, were used to evaluate the performance of the original Framingham model and new risk prediction model. Results Modified C-statistics, Hosmer-Lemeshow Test and classless NRI, class NRI were the statistical indices which, respectively, denoted the performance of discrimination, calibration and reclassification for evaluating the newly developed risk prediction model on stroke onset. It showed that the NEW-STROKE (new stroke risk score prediction model) model had higher modified C-statistics, smaller Hosmer-Lemeshow chi-square values after recalibration than original FSRS model, and the classless NRI and class NRI of the NEW-STROKE model over the original FSRS model were all significantly positive in overall group. Conclusion The NEW-STROKE integrated with seven literature-derived risk factors outperformed the original FSRS model in predicting the risk score of stroke. It illustrated that seven literature-derived risk factors contributed significantly to stroke risk prediction.

In this paper, we discuss the identifiability and estimation of causal effects of a continuous treatment on a binary response when the treatment is measured with errors and there exists a latent categorical confounder associated with both treatment and response. Under some widely used parametric models, we first discuss the identifiability of the causal effects and then propose an approach for estimation and inference. Our approach can eliminate the biases induced by latent confounding and measurement errors by using only a single instrumental variable. Based on the identification results, we give guidelines for determining the existence of a latent categorical confounder and for selecting the number of levels of the latent confounder. We apply the proposed approach to a data set from the Framingham Heart Study to evaluate the effect of the systolic blood pressure on the coronary heart disease.

Summary In observational studies, interest mainly lies in estimation of the population level relationship between the explanatory variables and dependent variables, and the estimation is often undertaken by using a sample of longitudinal data. In some situations, the longitudinal data sample features biases and loss of estimation efficiency due to non-random dropout. However, inclusion of population level information can increase estimation efficiency. We propose an empirical-likelihood-based method to incorporate population level information in a longitudinal study with dropout. The population level information is incorporated via constraints on functions of the parameters, and non-random dropout bias is corrected by using a weighted generalized estimating equations method. We provide a three-step estimation procedure that makes computation easier. Some commonly used methods are compared in simulation studies, which demonstrate that our proposed method can correct the non-random dropout bias and increase the estimation efficiency, especially for small sample sizes or when the missing proportion is high. In some situations, the improvement in efficiency is substantial. Finally, we apply the method to an Alzheimer's disease study.

In this paper, we develop a semiparametric regression model for longitudinal skewed data. In the new model, we allow the transformation function and the baseline function to be unknown. The proposed model can provide a much broader class of models than the existing additive and multiplicative models. Our estimators for regression parameters, transformation function and baseline function are asymptotically normal. Particularly, the estimator for the transformation function converges to its true value at the rate n − 1 ∕ 2, the convergence rate that one could expect for a parametric model. In simulation studies, we demonstrate that the proposed semiparametric method is robust with little loss of efficiency. Finally, we apply the new method to a study on longitudinal health care costs.

This paper considered interval estimations for the mean of lognormal distribution with excess zeros. We proposed two methods for interval estimation based on an approximate generalized pivotal quantity and a fiducial quantity. Simulation results show that the fiducial approach has highly accurate coverage probability and fairly low bias.

Confounding is very fundamental to the design and analysis of studies of causal effects. A variable is not a confounder if it is not a risk factor to disease or if it has the same distribution in the exposed and unexposed population. Whether or not to adjust for a non confounder to improve the precision of estimation has been argued by many authors. This article shows that if C is a non confounder, the pooled and standardized (log) relative risk estimators are asymptotic normal distributions with the mean being the true (log) relative risk, and that the asymptotic variance of the pooled (log) relative risk estimator is less than that of the stratified estimator.

In observational studies, interest often lies in estimation of the population-level relationship between the explanatory variables and dependent variables, and the estimation is often done using longitudinal data. Longitudinal data often feature sampling error and bias due to nonrandom drop-out. However, inclusion of population-level information can increase estimation efficiency. In this article, we consider a generalized partially linear model for incomplete longitudinal data in the presence of the population-level information. A pseudo-empirical likelihood-based method is introduced to incorporate population-level information, and nonrandom drop-out bias is corrected by using a weighted generalized estimating equations method. A three-step estimation procedure is proposed, which makes the computation easier. Several methods that are often used in practice are compared in simulation studies, which demonstrate that our proposed method can correct the nonrandom drop-out bias and increase the estimation efficiency, especially for small sample size or when the missing proportion is high. We apply this method to an Alzheimer's disease study.

In ROC analysis, covariate adjustment is advocated when the covariates impact the magnitude or accuracy of the test under study. Meanwhile, for many large scale screening tests, the true condition status may be subject to missingness because it is expensive and/or invasive to ascertain the disease status. The complete-case analysis may end up with a biased inference, also known as "verification bias." To address the issue of covariate adjustment with verification bias in ROC analysis, we propose several estimators for the area under the covariate-specific and covariate-adjusted ROC curves (AUCx and AAUC). The AUCx is directly modeled in the form of binary regression, and the estimating equations are based on the U statistics. The AAUC is estimated from the weighted average of AUCx over the covariate distribution of the diseased subjects. We employ reweighting and imputation techniques to overcome the verification bias problem. Our proposed estimators are initially derived assuming that the true disease status is missing at random (MAR), and then with some modification, the estimators can be extended to the not missing at random (NMAR) situation. The asymptotic distributions are derived for the proposed estimators. The finite sample performance is evaluated by a series of simulation studies. Our method is applied to a data set in Alzheimer's disease research.

The covariate-specific receiver operating characteristic curve is frequently used to evaluate the classification accuracy of a diagnostic test when it is associated with certain covariates. In this paper, we propose a new procedure for estimating this curve based on a reformulation of the conventional location-scale model and the idea of composite quantile regression. Asymptotic normality of the proposed estimators is established, both for the regression parameters and for the covariate-specific receiver operating characteristic curve at a fixed false-positive point. Simulation results show that the new estimators compare favourably to their main competitors in terms of the standard error. We apply the new procedure to data from the National Alzheimer's Coordinating Center. Copyright 2013, Oxford University Press.

Study planning is particularly complex for survival trials because it usually involves an accrual period and a continued observation period after accrual closure. The three-arm clinical trial design, which includes a test treatment, an active reference, and a placebo control, is the gold standard design for the assessment of non-inferiority. The existing statistical methods of calculating minimal sample size for non-inferiority trials with three-arm design and survival-type endpoints cannot take into consideration the accrual rate of patients to the trial, the length of accrual period, the length of continued observation period after accrual closure, and unbalanced allocation of the total sample size. The purpose of this paper is to develop a statistical method, which allows for all these sources of variability for planning non-inferiority trials with the gold standard design for censored, exponentially distributed time-to-event data. The proposed method is based on the assumption of exponentially distributed failure times and a non-inferiority test formulated in terms of the retention of effect hypotheses. It can be used to calculate the duration of accrual required to assure a desired power for non-inferiority trials with active and placebo control. We illustrate the use of the method by considering a randomized, active- and placebo-controlled trial in depression associated with Parkinson’s disease. We then explore the validity of the proposed method by simulation studies. An R-language program for the implementation of the proposed algorithm is provided as supplementary material.

Many analyses for incomplete longitudinal data are directed to examining the impact of covariates on the marginal mean responses. We consider the setting in which longitudinal responses are collected from individuals nested within clusters. We discuss methods for assessing covariate effects on the mean and association parameters when covariates are incompletely observed. Weighted first and second order estimating equations are constructed to obtain consistent estimates of mean and association parameters when covariates are missing at random. Empirical studies demonstrate that estimators from the proposed method have negligible finite sample biases in moderate samples. An application to the National Alzheimer's Coordinating Center (NACC) Uniform Data Set (UDS) demonstrates the utility of the proposed method.

Nonignorable nonresponse is a nonresponse mechanism that depends on the values of the variable having nonresponse. When an observed data of a binomial distribution suffer missing values from a nonignorable nonresponse mechanism, the binomial distribution parameters become unidentifiable without any other auxiliary information or assumption. To address the problems of non identifiability, existing methods mostly based on the log-linear regression model. In this article, we focus on the model when the nonresponse is nonignorable and we consider to use the auxiliary data to improve identifiability; furthermore, we derive the maximum likelihood estimator (MLE) for the binomial proportion and its associated variance. We present results for an analysis of real-life data from the SARS study in China. Finally, the simulation study shows that the proposed method gives promising results.

For censored survival outcomes, it can be of great interest to evaluate the predictive power of individual markers or their functions. Compared with alternative evaluation approaches, the time-dependent ROC (receiver operating characteristics) based approaches rely on much weaker assumptions, can be more robust, and hence are preferred. In this article, we examine evaluation of markers’ predictive power using the time-dependent ROC curve and a concordance measure which can be viewed as a weighted area under the time-dependent AUC (area under the ROC curve) profile. This study significantly advances from existing time-dependent ROC studies by developing nonparametric estimators of the summary indexes and, more importantly, rigorously establishing their asymptotic properties. It reinforces the statistical foundation of the time-dependent ROC based evaluation approaches for censored survival outcomes. Numerical studies, including simulations and application to an HIV clinical trial, demonstrate the satisfactory finite-sample performance of the proposed approaches.

This paper proposes a general framework of marker validation designs, which includes most of existing validation designs. The sample size calculation formulas for the proposed general design are derived on the basis of the optimal allocation that minimizes the expected number of treatment failures. The optimal allocation is especially important in the targeted design which is often motivated by preliminary evidence that marker-positive patients respond to one treatment better than the other. Our sample size calculation also takes into account the classification error of a marker. The numerical studies are conducted to investigate the expected reduction on the treatment failures and the relative efficiency between the targeted design and the traditional design based on the optimal ratios. We illustrate the calculation of the optimal allocation and sample sizes through a hypothetical stage II colon cancer trial.

We consider the estimation of three-dimensional ROC surfaces for continuous tests given covariates. Three way ROC analysis is important in our motivating example where patients with Alzheimer’s disease are usually classified into three categories and should receive different category-specific medical treatment. There has been no discussion on how covariates affect the three way ROC analysis. We propose a regression framework induced from the relationship between test results and covariates. We consider several practical cases and the corresponding inference procedures. Simulations are conducted to validate our methodology. The application on the motivating example illustrates clearly the age and sex effects on the accuracy for Mini-Mental State Examination of Alzheimer’s disease.

In this article, we propose a separation curve method to identify the range of false positive rates for which two receiver operating characteristic (ROC) curves differ or one ROC curve is superior to the other. Our method is based on a general multivariate ROC curve model, including interaction terms between discrete covariates and false positive rates. It is applicable with most existing ROC curve models. Furthermore, we introduce a semiparametric least squares ROC estimator and apply the estimator to the separation curve method. We derive a sandwich estimator for the covariance matrix of the semiparametric estimator. We illustrate the application of our separation curve method through two real life examples. The technical proofs, a dataset, and the computer code are available in the online supplementary materials.

Summary As new diagnostic tests are developed and marketed, it is very important to be able to compare the accuracy of a given two continuous-scale diagnostic tests. An effective method to evaluate the difference between the diagnostic accuracy of two tests is to compare partial areas under the receiver operating characteristic curves (AUCs). In this paper, we review existing parametric methods. Then, we propose a new semiparametric method and a new nonparametric method to investigate the difference between two partial AUCs. For the difference between two partial AUCs under each method, we derive a normal approximation, define an empirical log-likelihood ratio, and show that the empirical log-likelihood ratio follows a scaled chi-square distribution. We construct five confidence intervals for the difference based on normal approximation, bootstrap, and empirical likelihood methods. Finally, extensive simulation studies are conducted to compare the finite-sample performances of these intervals, and a real example is used as an application of our recommended intervals. The simulation results indicate that the proposed hybrid bootstrap and empirical likelihood intervals outperform other existing intervals in most cases.

The classification accuracy of new diagnostic tests is based on receiver operating characteristic (ROC) curves. The area under the ROC curve (AUC) is one of the well-accepted summary measures for describing the accuracy of diagnostic tests. The AUC summary measure can vary by patient and testing characteristics. Thus, the performance of the test may be different in certain subpopulation of patients and readers. For this purpose, we propose a direct semi-parametric regression model for the non-parametric AUC measure for ordinal data while accounting for discrete and continuous covariates. The proposed method can be used to estimate the AUC value under degenerate data where certain rating categories are not observed. We will discuss the non-standard asymptotic theory, since the estimating functions were based on cross-correlated random variables. Simulation studies based on different classification models showed that the proposed model worked reasonably well with small percent bias and percent mean-squared error. The proposed method was applied to the prostate cancer study to estimate the AUC for four readers, and the carotid vessel study with age, gender, history of previous stroke, and total number of risk factors as covariates, to estimate the accuracy of the diagnostic test in the presence of subject-level covariates.

In medical studies, there are many situations where the final outcomes are truncated by death, in which patients die before outcomes of interest are measured. In this article we consider identifiability and estimation of causal effects by principal stratification when some outcomes are truncated by death. Previous studies mostly focused on large sample bounds, Bayesian analysis, sensitivity analysis. In this article, we propose a new method for identifying the causal parameter of interest under a nonparametric and semiparametric model. We show that the causal parameter of interest is identifiable under some regularity assumptions and the assumption that there exists a pretreatment covariate whose conditional distributions among two principal strata are not the same, but our approach does not need the assumption of a mixture normal distribution for outcomes as required by Zhang, Rubin, and Mealli (2009). Hence, the proposed method is applicable not only to a continuous outcome but also to a binary outcome....

Principal strata are defined by the potential values of a post-treatment variable, and a principal effect is a causal effect within a principal stratum. Identifying the principal effect within every principal stratum is quite challenging. In this paper, we propose an approach for identifying principal effects on a binary outcome via a pre-treatment covariate. We prove the identifiability with single post-treatment intervention under the monotonicity assumption. Furthermore, we discuss the local identifiability with multicomponent intervention. Simulations are performed to evaluate our approach. We also apply it to a real data set from the Improving Mood-Promoting Access to Collaborate Treatment program.

Markov regression models are useful tools for estimating the impact of risk factors on rates of transition between multiple disease states. Alzheimer's disease (AD) is an example of a multi-state disease process in which great interest lies in identifying risk factors for transition. In this context, non-homogeneous models are required because transition rates change as subjects age. In this report we propose a non-homogeneous Markov regression model that allows for reversible and recurrent disease states, transitions among multiple states between observations, and unequally spaced observation times. We conducted simulation studies to demonstrate performance of estimators for covariate effects from this model and compare performance with alternative models when the underlying non-homogeneous process was correctly specified and under model misspecification. In simulation studies, we found that covariate effects were biased if non-homogeneity of the disease process was not accounted for. However, estimates from non-homogeneous models were robust to misspecification of the form of the non-homogeneity. We used our model to estimate risk factors for transition to mild cognitive impairment (MCI) and AD in a longitudinal study of subjects included in the National Alzheimer's Coordinating Center's Uniform Data Set. Using our model, we found that subjects with MCI affecting multiple cognitive domains were significantly less likely to revert to normal cognition.

Two common problems in assessing the accuracy of traditional Chinese medicine (TCM) doctors in detecting a particular symptom are the unknown true symptom status and the ordinal-scale of the symptom status. Wang et al. (Biostatistics 2011; DOI: 10.1093/biostatistics/kxq075) proposed a nonparametric maximum likelihood method for estimating the accuracy of different TCM doctors without a gold standard when the true symptom status is measured on an ordinal-scale. A key assumption of their work is that the diagnosis results are independent conditional on the gold standard. This assumption can be violated in many practical situations.In this paper, we propose a random effects modeling approach that extends their method to incorporate dependence structure among different tests or doctors. The proposed method is illustrated on a real data set from TCM, which contains the diagnostic results from five doctors for the same patients regarding symptoms related to Chills disease. The same data set was analyzed by Wang et al. under the conditional independence assumption. In addition, we also discuss an ad hoc test for the model fitting and a likelihood ratio test on the random effects.

For many medical conditions, several treatment options may be available for treating patients. We consider evaluating markers based on a simple treatment selection policy that incorporates information on the patient's marker value. For example, colon cancer patients may be treated by surgery alone or surgery plus chemotherapy. The c-myc gene expression level may be used as a biomarker for treatment selection. Although traditional regression methods may assess the effect of the marker and treatment on outcomes, it is more appealing to quantify directly the potential impact on the population of using the marker to select treatment. A useful tool is the selection impact (SI) curve proposed by Song and Pepe for binary outcomes (Biometrics 2004; 60:874–883). However, the current SI method does not deal with continuous outcomes, nor does it allow to adjust for other covariates that are important for treatment selection. In this paper, we extend the SI curve for general outcomes, with a specific focus on survival time. We further propose the covariate-specific SI curve to incorporate covariate information in treatment selection. Nonparametric and semiparametric estimators are developed accordingly. We show that the proposed estimators are consistent and asymptotically normal. The performance is assessed by simulation studies and illustrated through an application to data from a cancer clinical trial. Copyright © 2011 John Wiley & Sons, Ltd.

Covariate-specific receiver operating characteristic (ROC) curves are often used to evaluate the classification accuracy of a medical diagnostic test or a biomarker, when the accuracy of the test is associated with certain covariates. In many large-scale screening tests, the gold standard is subject to missingness due to high cost or harmfulness to the patient. In this article, we propose a semiparametric estimation of the covariate-specific ROC curves with a partial missing gold standard. A location-scale model is constructed for the test result to model the covariates' effect, but the residual distributions are left unspecified. Thus the baseline and link functions of the ROC curve both have flexible shapes. With the gold standard missing at random (MAR) assumption, we consider weighted estimating equations for the location-scale parameters, and weighted kernel estimating equations for the residual distributions. Three ROC curve estimators are proposed and compared, namely, imputation-based, inverse probability weighted, and doubly robust estimators. We derive the asymptotic normality of the estimated ROC curve, as well as the analytical form of the standard error estimator. The proposed method is motivated and applied to the data in an Alzheimer's disease research.