arXiv subjects

Fred A. Wright

Publications and source records attributed to Fred A. Wright.

9 recordsLinked to original sources

arXiv2020

Fast Multivariate Probit Estimation via a Two-Stage Composite Likelihood

The multivariate probit is popular for modeling correlated binary data, with an attractive balance of flexibility and simplicity. However, considerable challenges remain in computation and in devising a clear statistical framework. Interest in the multivariate probit has increased in recent years. Current applications include genomics and precision medicine, where simultaneous modeling of multiple traits may be of interest, and computational efficiency is an important consideration. We propose a fast method for multivariate probit estimation via a two-stage composite likelihood. We explore computational and statistical efficiency, and note that the approach sets the stage for extensions beyond the purely binary setting.

stat.ME↗

arXiv2017

An Empirical Bayes Approach for Multiple Tissue eQTL Analysis

Expression quantitative trait loci (eQTL) analyses, which identify genetic markers associated with the expression of a gene, are an important tool in the understanding of diseases in human and other populations. While most eQTL studies to date consider the connection between genetic variation and expression in a single tissue, complex, multi-tissue data sets are now being generated by the GTEx initiative. These data sets have the potential to improve the findings of single tissue analyses by borrowing strength across tissues, and the potential to elucidate the genotypic basis of differences between tissues. In this paper we introduce and study a multivariate hierarchical Bayesian model (MT-eQTL) for multi-tissue eQTL analysis. MT-eQTL directly models the vector of correlations between expression and genotype across tissues. It explicitly captures patterns of variation in the presence or absence of eQTLs, as well as the heterogeneity of effect sizes across tissues. Moreover, the model is applicable to complex designs in which the set of donors can (i) vary from tissue to tissue, and (ii) exhibit incomplete overlap between tissues. The MT-eQTL model is marginally consistent, in the sense that the model for a subset of tissues can be obtained from the full model via marginalization. Fitting of the MT-eQTL model is carried out via empirical Bayes, using an approximate EM algorithm. Inferences concerning eQTL detection and the configuration of eQTLs across tissues are derived from adaptive thresholding of local false discovery rates, and maximum a-posteriori estimation, respectively. We investigate the MT-eQTL model through a simulation study, and rigorously establish the FDR control of the local FDR testing procedure under mild assumptions appropriate for dependent data.

stat.ME↗

arXiv2017

Estimation of Interpretable eQTL Effect Sizes Using a Log of Linear Model

The study of expression Quantitative Trait Loci (eQTL) is an important problem in genomics and biomedicine. While detection (testing) of eQTL associations has been widely studied, less work has been devoted to the estimation of eQTL effect size. To reduce false positives, detection methods frequently rely on linear modeling of rank-based normalized or log-transformed gene expression data. Unfortunately, these approaches do not correspond to the simplest model of eQTL action, and thus yield estimates of eQTL association that can be uninterpretable and inaccurate. In this paper we propose a new, log-of-linear model for eQTL action, termed ACME, that captures allelic contributions to cis-acting eQTLs in an additive fashion, yielding effect size estimates that correspond to a biologically coherent model of cis-eQTLs. We describe a non-linear least-squares algorithm to fit the model by maximum likelihood, and obtain corresponding $p$-values. We perform careful investigation of the model using a combination of simulated data and data from the Genotype Tissue Expression (GTEx) project. Our results reveal little evidence for dominance effects, a parsimonious result that accords with a simple biological model for allele-specific expression and supports use of the ACME model. We show that Type-I error is well-controlled under our approach in a realistic setting, so that rank-based normalizations are unnecessary. Furthermore, we show that such normalizations can be detrimental to power and estimation accuracy under the proposed model. We then provide summaries of ACME effect sizes for whole-genome cis-eQTLs in the GTEx data.

stat.ME↗

arXiv2017

HT-eQTL: Integrative Expression Quantitative Trait Loci Analysis in a Large Number of Human Tissues

Expression quantitative trait loci (eQTL) analysis identifies genetic markers associated with the expression of a gene. Most existing eQTL analyses and methods investigate association in a single, readily available tissue, such as blood. Joint analysis of eQTL in multiple tissues has the potential to improve, and expand the scope of, single-tissue analyses. Large-scale collaborative efforts such as the Genotype-Tissue Expression (GTEx) program are currently generating high quality data in a large number of tissues. However, computational constraints limit genome-wide multi-tissue eQTL analysis. We develop an integrative method under a hierarchical Bayesian framework for eQTL analysis in a large number of tissues. The model fitting procedure is highly scalable, and the computing time is a polynomial function of the number of tissues. Multi-tissue eQTLs are identified through a local false discovery rate approach, which rigorously controls the false discovery rate. Using simulation and GTEx real data studies, we show that the proposed method has superior performance to existing methods in terms of computing time and the power of eQTL discovery. We provide a scalable method for eQTL analysis in a large number of tissues. The method enables the identification of eQTL with different configurations and facilitates the characterization of tissue specificity.

stat.AP↗

arXiv2014

A procedure to detect general association based on concentration of ranks

In modern high-throughput applications, it is important to identify pairwise associations between variables, and desirable to use methods that are powerful and sensitive to a variety of association relationships. We describe RankCover, a new non-parametric association test for association between two variables that measures the concentration of paired ranked points. Here `concentration' is quantified using a disk-covering statistic that is similar to those employed in spatial data analysis. Analysis of simulated datasets demonstrates that the method is robust and often powerful in comparison to competing general association tests. We illustrate RankCover in the analysis of several real datasets.

stat.ME↗

arXiv2014

Consistent Testing for Recurrent Genomic Aberrations

Genomic aberrations, such as somatic copy number alterations, are frequently observed in tumor tissue. Recurrent aberrations, occurring in the same region across multiple subjects, are of interest because they may highlight genes associated with tumor development or progression. A number of tools have been proposed to assess the statistical significance of recurrent DNA copy number aberrations, but their statistical properties have not been carefully studied. Cyclic shift testing, a permutation procedure using independent random shifts of genomic marker observations on the genome, has been proposed to identify recurrent aberrations, and is potentially useful for a wider variety of purposes, including identifying regions with methylation aberrations or overrepresented in disease association studies. For data following a countable-state Markov model, we prove the asymptotic validity of cyclic shift $p$-values under a fixed sample size regime as the number of observed markers tends to infinity. We illustrate cyclic shift testing for a variety of data types, producing biologically relevant findings for three publicly available datasets.

math.ST↗

arXiv2012

Convergence and prediction of principal component scores in high-dimensional settings

A number of settings arise in which it is of interest to predict Principal Component (PC) scores for new observations using data from an initial sample. In this paper, we demonstrate that naive approaches to PC score prediction can be substantially biased toward 0 in the analysis of large matrices. This phenomenon is largely related to known inconsistency results for sample eigenvalues and eigenvectors as both dimensions of the matrix increase. For the spiked eigenvalue model for random matrices, we expand the generality of these results, and propose bias-adjusted PC score prediction. In addition, we compute the asymptotic correlation coefficient between PC scores from sample and population eigenvectors. Simulation and real data examples from the genetics literature show the improved bias and numerical properties of our estimators.

math.ST↗

arXiv2010

A geometric interpretation of the permutation $p$-value and its application in eQTL studies

Permutation $p$-values have been widely used to assess the significance of linkage or association in genetic studies. However, the application in large-scale studies is hindered by a heavy computational burden. We propose a geometric interpretation of permutation $p$-values, and based on this geometric interpretation, we develop an efficient permutation $p$-value estimation method in the context of regression with binary predictors. An application to a study of gene expression quantitative trait loci (eQTL) shows that our method provides reliable estimates of permutation $p$-values while requiring less than 5% of the computational time compared with direct permutations. In fact, our method takes a constant time to estimate permutation $p$-values, no matter how small the $p$-value. Our method enables a study of the relationship between nominal $p$-values and permutation $p$-values in a wide range, and provides a geometric perspective on the effective number of independent tests.

stat.AP↗

arXiv2008

A statistical framework for testing functional categories in microarray data

Ready access to emerging databases of gene annotation and functional pathways has shifted assessments of differential expression in DNA microarray studies from single genes to groups of genes with shared biological function. This paper takes a critical look at existing methods for assessing the differential expression of a group of genes (functional category), and provides some suggestions for improved performance. We begin by presenting a general framework, in which the set of genes in a functional category is compared to the complementary set of genes on the array. The framework includes tests for overrepresentation of a category within a list of significant genes, and methods that consider continuous measures of differential expression. Existing tests are divided into two classes. Class 1 tests assume gene-specific measures of differential expression are independent, despite overwhelming evidence of positive correlation. Analytic and simulated results are presented that demonstrate Class 1 tests are strongly anti-conservative in practice. Class 2 tests account for gene correlation, typically through array permutation that by construction has proper Type I error control for the induced null. However, both Class 1 and Class 2 tests use a null hypothesis that all genes have the same degree of differential expression. We introduce a more sensible and general (Class 3) null under which the profile of differential expression is the same within the category and complement. Under this broader null, Class 2 tests are shown to be conservative. We propose standard bootstrap methods for testing against the Class 3 null and demonstrate they provide valid Type I error control and more power than array permutation in simulated datasets and real microarray experiments.

stat.AP↗