Search

In various fields such as medical science and finance, it is not uncommon that the data are heavy-tailed and/or not fully observed, calling for robust inference methods that can deal with the outliers and incompleteness efficiently. In this paper, the authors propose a rank score test for quantile regression with fixed censored responses, based on the standard quantile regression in an informative subset which is computationally efficient and robust. The authors further select the informative subset by the multiply robust propensity scores, and then derive the asymptotic properties of the proposed test statistic under both the null and local alternatives. Moreover, the authors conduct extensive simulations to verify the validity of the proposed test, and apply it to a human immunodeficiency virus data set to identify the important predictors for the conditional quantiles of the censored viral load.

The partially linear single-index model (PLSIM) is a flexible and powerful model for analyzing the relationship between the response and the multivariate covariates. This paper considers the PLSIM with measurement error possibly in all the variables. The authors propose a new efficient estimation procedure based on the local linear smoothing and the simulation-extrapolation method, and further establish the asymptotic normality of the proposed estimators for both the index parameter and nonparametric link function. The authors also carry out extensive Monte Carlo simulation studies to evaluate the finite sample performance of the new method, and apply it to analyze the osteoporosis prevention data.

ABSTRACTIn this paper, we study ultra-high-dimensional partially linear models when the dimension of the linear predictors grows exponentially with the sample size. For the variable screening, we propose a sequential profile Lasso method (SPLasso) and show that it possesses the screening property. SPLasso can also detect all relevant predictors with probability tending to one, no matter whether the ultra-high models involve both parametric and nonparametric parts. To select the best subset among the models generated by SPLasso, we propose an extended Bayesian information criterion (EBIC) for choosing the final model. We also conduct simulation studies and apply a real data example to assess the performance of the proposed method and compare with the existing method.

The US Food and Drug Administration issued a guidance in 2002, “Food-Effect Bioavailability and Fed Bioequivalence Studies,” in which it states “in addition to a BE [bioequivalence] study under fasting conditions, we recommend a BE study under fed conditions for all orally administered immediate-release drug products” for abbreviated new drug applications. This statement involves 3 studies: a BE study under fasting status, a food-effect (FE) study, and a BE study under fed status. In practice, when it is known that there is no FE with a reference (R) formulation, a sponsor may choose to run a BE study that assesses the drug effect and food effect with a test (T) formulation in a single study that includes 3 treatments: Rformulation at fasting status, Tformulation at fasting status, and Tformulation at fed status. Such a study combines the fasting BE study and the FE study on the Tformulation and may justify the waiver of the fed BE study if conclusions can be made that there is no FE with the Tformulation after this combined study completes. This article discusses how to calculate the sample size for this kind of study with different primary analysis models. Also discussed are (1) sample size calculations with more general BE studies and (2) how they can be implemented using commercial software in a standard 2-treatment, 2-period, and 2-sequence crossover design, as well as (3) a related practical issue of how to retrieve residual intrasubject mean squared error from historical summary results in the literature.

The US Food and Drug Administration issued a guidance in 2002, “Food-Effect Bioavailability and Fed Bioequivalence Studies,” in which it states “in addition to a BE [bioequivalence] study under fasting conditions, we recommend a BE study under fed conditions for all orally administered immediate-release drug products” for abbreviated new drug applications. This statement involves 3 studies: a BE study under fasting status, a food-effect (FE) study, and a BE study under fed status. In practice, when it is known that there is no FE with a reference (R) formulation, a sponsor may choose to run a BE study that assesses the drug effect and food effect with a test (T) formulation in a single study that includes 3 treatments: Rformulation at fasting status, Tformulation at fasting status, and Tformulation at fed status. Such a study combines the fasting BE study and the FE study on the Tformulation and may justify the waiver of the fed BE study if conclusions can be made that there is no FE with the Tformulation after this combined study completes. This article discusses how to calculate the sample size for this kind of study with different primary analysis models. Also discussed are (1) sample size calculations with more general BE studies and (2) how they can be implemented using commercial software in a standard 2-treatment, 2-period, and 2-sequence crossover design, as well as (3) a related practical issue of how to retrieve residual intrasubject mean squared error from historical summary results in the literature.

Chromatin immunoprecipitation followed by massively parallel next-generation sequencing (ChIP-seq) is a valuable experimental strategy for assaying protein-DNA interaction over the whole genome. Many computational tools have been designed to find the peaks of the signals corresponding to protein binding sites. In this paper, three computational methods, ChIP-seq processing pipeline (spp), PeakSeq and CisGenome, used in ChIP-seq data analysis are reviewed. There is also a comparison of how they agree and disagree on finding peaks using the publically available Signal Transducers and Activators of Transcription protein 1 (STAT1) and RNA polymerase II (PolII) datasets with corresponding negative controls.

Abstract: This note revisits Maity and Sherman’s two-sample testing problem with one variance known but the other one unknown [A. Maity, M. Sherman, The two-sample t test with one variance unknown, The American Statistician 60 (2006) 163–166]. Inspired by the fact that the number of degrees of freedom used in their testing method is overestimated, we propose in this note a new testing method by introducing an unbiased estimator of the number of degrees of freedom. Simulation studies indicate that the proposed testing method provides a more accurate control than Maity and Sherman’s method. [Copyright &y& Elsevier]

In clinical trials, it is often desirable to test for superiority conditioned on establishment of noninferiority based on the same primary end-point. According to a guidance document issued by the European regulatory agency Committee for Proprietary Medicinal Products in 2001, no type I error rate adjustment is necessary for switching between superiority and non-inferiority because the family-wise type I error rate is controlled at the same nominal level. However, Ng raised the issues of switching between superiority and noninferiority even though there is no inflation of the family-wise type I error rate and showed that the fake discovery rate could be increased.To alleviate these concerns, we propose to control the conditional type I error rate of the second-step superiority test at the nominal significance level, which leads to a lower (unconditional) significance level of the second-step superiority test. The suggested adjustment posts a more rigorous condition to claim superiority, which is an effort to decrease the number of erroneous claims of superiority.

In clinical trials, it is often desirable to test for superiority conditioned on establishment of noninferiority based on the same primary end-point. According to a guidance document issued by the European regulatory agency Committee for Proprietary Medicinal Products in 2001, no type I error rate adjustment is necessary for switching between superiority and non-inferiority because the family-wise type I error rate is controlled at the same nominal level. However, Ng raised the issues of switching between superiority and noninferiority even though there is no inflation of the family-wise type I error rate and showed that the fake discovery rate could be increased.

High-throughput RNA sequencing is rapidly emerging as a favourite method for gene expression studies. We review three software packages -- edgeR, DEGseq and baySeq -- from Bioconductor http://bioconductor.orgfor analysing RNA-sequencing data. We focus on three aspects: normalisation, statistical models and the testing employed on these methods. We also discuss the advantages and limitations of these software packages.

Breast cancer tumours among African Americans are usually more aggressive than those found in Caucasian populations. African-American patients with breast cancer also have higher mortality rates than Caucasian women. A better understanding of the disease aetiology of these breast cancers can help to improve and develop new methods for cancer prevention, diagnosis and treatment. The main goal of this project was to identify genes that help differentiate between oestrogen receptor-positive and -negative samples among a small group of African-American patients with breast cancer. Breast cancer microarrays from one of the largest genomic consortiums were analysed using 13 African-American and 201 Caucasian samples with oestrogen receptor status. We used a shrinkage-based classification method to identify genes that were informative in discriminating between oestrogen receptor-positive and -negative samples. Subset analysis and permutation were performed to obtain a set of genes unique to the African-American population. We identified a set of 156 probe sets, which gave a misclassification rate of 0.16 in distinguishing between oestrogen receptor-positive and -negative patients. The biological relevance of our findings was explored through literature-mining techniques and pathway mapping. An independent dataset was used to validate our findings and we found that the top ten genes mapped onto this dataset gave a misclassification rate of 0.15. The described method allows us best to utilise the information available from small sample size microarray data in the context of ethnic minorities.

The determinant of the covariance matrix for high-dimensional data plays an important role in statistical inference and decision. It has many real applications including statistical tests and information theory. Due to the statistical and computational challenges with high dimensionality, little work has been proposed in the literature for estimating the determinant of high-dimensional covariance matrix. In this paper, we estimate the determinant of the covariance matrix using some recent proposals for estimating high-dimensional covariance matrix. Specifically, we consider a total of eight covariance matrix estimation methods for comparison. Through extensive simulation studies, we explore and summarize some interesting comparison results among all compared methods. We also provide practical guidelines based on the sample size, the dimension, and the correlation of the data set for estimating the determinant of high-dimensional covariance matrix. Finally, from a perspective of the loss function, the comparison study in this paper may also serve as a proxy to assess the performance of the covariance matrix estimation.