Confidence interval estimation of the difference between paired AUCs based on combined biomarkers

In many diagnostic studies, multiple diagnostic tests are performed on each subject or multiple disease markers are available. Commonly, the information should be combined to improve the diagnostic accuracy. We consider the problem of comparing the discriminatory abilities between two groups of biomarkers. Specifically, this article focuses on confidence interval estimation of the difference between paired AUCs based on optimally combined markers under the assumption of multivariate normality. Simulation studies demonstrate that the proposed generalized variable approach provides confidence intervals with satisfying coverage probabilities at finite sample sizes. The proposed method can also easily provide P-values for hypothesis testing. Application to analysis of a subset of data from a study on coronary heart disease illustrates the utility of the method in practice.     

An intuitive risk factors search algorithm: usage of the Bayesian network technique in personalized medicine

The article focuses on the application of the Bayesian networks (BN) technique to problems of personalized medicine. The simple (intuitive) algorithm of BN optimization with respect to the number of nodes using naive network topology is developed. This algorithm allows to increase the BN prediction quality and to identify the most important variables of the network. The parallel program implementing the algorithm has demonstrated good scalability with an increase in the computational cores number, and it can be applied to the large patients database containing thousands of variables. This program is applied for the prediction for the unfavorable outcome of coronary artery disease (CAD) for patients who survived the acute coronary syndrome (ACS). As a result, the quality of the predictions of the investigated networks was significantly improved and the most important risk factors were detected. The significance of the tumor necrosis factor-alpha gene polymorphism for the prediction of the unfavorable outcome of CAD for patients survived after ACS was revealed for the first time.     

Exploring the link between government funding and efficiency in nonprofit colleges

Previous literature has suggested that federal funding can hinder the efficiency of nonprofit organizations, but this has yet not been empirically tested. This study used a two‐stage data envelopment analysis (DEA) model to measure the efficiency of a set of private nonprofit teaching‐oriented colleges, then estimate the impact of federal and state funding on organizational efficiency. The findings indicate that, on average, increases in neither state nor federal funding effect efficiency of nonprofit colleges. Increasing state funding negatively impacted the efficiency of public colleges (N = 799). This study suggests that the challenges for nonprofits that accompany government funding may not rise to a quantifiable negative effect on efficiency.     

Testing for bioequivalence of highly variable drugs from TR‐RT crossover designs with heterogeneous residual variances

Traditional bioavailability studies assess average bioequivalence (ABE) between the test (T) and reference (R) products under the crossover design with TR and RT sequences. With highly variable (HV) drugs whose intrasubject coefficient of variation in pharmacokinetic measures is 30% or greater, assertion of ABE becomes difficult due to the large sample sizes needed to achieve adequate power. In 2011, the FDA adopted a more relaxed, yet complex, ABE criterion and supplied a procedure to assess this criterion exclusively under TRR‐RTR‐RRT and TRTR‐RTRT designs. However, designs with more than 2 periods are not always feasible. This present work investigates how to evaluate HV drugs under TR‐RT designs. A mixed model with heterogeneous residual variances is used to fit data from TR‐RT designs. Under the assumption of zero subject‐by‐formulation interaction, this basic model is comparable to the FDA‐recommended model for TRR‐RTR‐RRT and TRTR‐RTRT designs, suggesting the conceptual plausibility of our approach. To overcome the distributional dependency among summary statistics of model parameters, we develop statistical tests via the generalized pivotal quantity (GPQ). A real‐world data example is given to illustrate the utility of the resulting procedures. Our simulation study identifies a GPQ‐based testing procedure that evaluates HV drugs under practical TR‐RT designs with desirable type I error rate and reasonable power. In comparison to the FDA's approach, this GPQ‐based procedure gives similar performance when the product's intersubject standard deviation is low (≤0.4) and is most useful when practical considerations restrict the crossover design to 2 periods.     

Quantile regression for robust estimation and variable selection in partially linear varying-coefficient models

In this paper, we develop a new estimation procedure based on quantile regression for semiparametric partially linear varying-coefficient models. The proposed estimation approach is empirically shown to be much more efficient than the popular least squares estimation method for non-normal error distributions, and almost not lose any efficiency for normal errors. Asymptotic normalities of the proposed estimators for both the parametric and nonparametric parts are established. To achieve sparsity when there exist irrelevant variables in the model, two variable selection procedures based on adaptive penalty are developed to select important parametric covariates as well as significant nonparametric functions. Moreover, both these two variable selection procedures are demonstrated to enjoy the oracle property under some regularity conditions. Some Monte Carlo simulations are conducted to assess the finite sample performance of the proposed estimators, and a real-data example is used to illustrate the application of the proposed methods.     

On the estimation of a sensitive quantitative mean using blank cards

In this article, we introduce for the first time, the blank card methods for estimation of finite population mean of a sensitive variable. Two generic randomization devices are suggested, and for each device we identify the choices of special models. We introduce additive, multiplicative, and combination of both additive and multiplicative scrambling models that require use of a non sensitive variable. We derive the basic statistical properties of each model. It is interesting to note that various existing estimators can be viewed as the special cases of those presented here. The statistical efficiency of proposed techniques is compared with Greenberg et al. (1971 Greenberg, B.G., Kuebler Jr, R.R., Abernathy, J.R., Horvitz, D.G. (1971). Application of the randomized response technique in obtaining quantitative data. J. Am. Stat. Assoc. 66(334):243–250.[Taylor &; Francis Online], [Web of Science ®] , [Google Scholar]) and modified Perri (2008 Perri, P.F. (2008). Modified randomized devices for Simmons’ model. Model Assisted Stat. Appl. 3(3):233–239. [Google Scholar]) model. The proposed devices can easily be adjusted to achieve the required efficiency level by making suitable choices of different design parameters.     

Parametric bootstrap inferences for the growth curve models with intraclass correlation structure

This paper presents parametric bootstrap (PB) approaches for hypothesis testing and interval estimation of the fixed effects and the variance component in the growth curve models with intraclass correlation structure. The PB pivot variables are proposed based on the sufficient statistics of the parameters. Some simulation results are presented to compare the performance of the proposed approaches with the generalized inferences. Our studies show that the PB approaches perform satisfactorily for various cell sizes and parameter configurations, and tends to outperform the generalized inferences with respect to the coverage probabilities and powers. The PB approaches not only have almost exact coverage probabilities and Type I error rates, but also have the shorter expected lengths and the higher powers. Furthermore, the PB procedure can be simply carried out by a few simulation steps. Finally, the proposed approaches are illustrated by using a real data example.     

A class of exponential-type ratio estimators of a general parameter

This paper addresses the problem of estimating a general parameter using information on an auxiliary variable X. We have suggested a class of exponential-type ratio estimators for the parameter and its properties are studied. It is identified that the estimators due to Upadhyaya et al. [Journal of Statistical Theory and Practice (2011), 5(2), 285–302] and Yadav and Kadilar [Revista Columbiana de Estadistica, (2013), 36(1), 145–152] are members of the proposed estimator. We have also shown that the suggested estimator is more efficient than the estimators of Upadhyaya et al. (2011 Upadhyaya, L.N., Singh, H.P., Chatterjee, S., Yadav, R. (2011). Improved ratio and product exponential type estimators. J. Stat. Theo. Pract. 5 (2): 285–302.[Taylor &; Francis Online] , [Google Scholar]) and Yadav and Kadilar (2013 Yadav, S.K., Kadilar, C. (2013). Improved exponential type ratio estimator of population variance. Revis. Colum. de Estadist. 36(1): 145–152. [Google Scholar]). Numerical illustration is provided in support of the present study.     

Sparse Bayesian variable selection in multinomial probit regression model with application to high-dimensional data classification

Here we consider a multinomial probit regression model where the number of variables substantially exceeds the sample size and only a subset of the available variables is associated with the response. Thus selecting a small number of relevant variables for classification has received a great deal of attention. Generally when the number of variables is substantial, sparsity-enforcing priors for the regression coefficients are called for on grounds of predictive generalization and computational ease. In this paper, we propose a sparse Bayesian variable selection method in multinomial probit regression model for multi-class classification. The performance of our proposed method is demonstrated with one simulated data and three well-known gene expression profiling data: breast cancer data, leukemia data, and small round blue-cell tumors. The results show that compared with other methods, our method is able to select the relevant variables and can obtain competitive classification accuracy with a small subset of relevant genes.