Members’ Discoveries: Fatal Flaws In Cancer Research,
2010
The University of Texas M.D. Anderson Cancer Center
Members’ Discoveries: Fatal Flaws In Cancer Research, Jeffrey S. Morris
Jeffrey S. Morris
A recent article published in The Annals of Applied Statistics (AOAS) by two MD Anderson researchers—Keith Baggerly and Kevin Coombes—dissects results from a highly-influential series of medical papers involving genomics-driven personalized cancer therapy, and outlines a series of simple yet fatal flaws that raises serious questions about the veracity of the original results. Having immediate and strong impact, this paper, along with related work, is providing the impetus for new standards of reproducibility in scientific research.
Statistical Contributions To Proteomic Research,
2010
The University of Texas M.D. Anderson Cancer Center
Statistical Contributions To Proteomic Research, Jeffrey S. Morris, Keith A. Baggerly, Howard B. Gutstein, Kevin R. Coombes
Jeffrey S. Morris
Proteomic profiling has the potential to impact the diagnosis, prognosis, and treatment of various diseases. A number of different proteomic technologies are available that allow us to look at many proteins at once, and all of them yield complex data that raise significant quantitative challenges. Inadequate attention to these quantitative issues can prevent these studies from achieving their desired goals, and can even lead to invalid results. In this chapter, we describe various ways the involvement of statisticians or other quantitative scientists in the study team can contribute to the success of proteomic research, and we outline some of the …
Informatics And Statistics For Analyzing 2-D Gel Electrophoresis Images,
2010
Imperial College London
Informatics And Statistics For Analyzing 2-D Gel Electrophoresis Images, Andrew W. Dowsey, Jeffrey S. Morris, Howard G. Gutstein, Guang Z. Yang
Jeffrey S. Morris
Whilst recent progress in ‘shotgun’ peptide separation by integrated liquid chromatography and mass spectrometry (LC/MS) has enabled its use as a sensitive analytical technique, proteome coverage and reproducibility is still limited and obtaining enough replicate runs for biomarker discovery is a challenge. For these reasons, recent research demonstrates the continuing need for protein separation by two-dimensional gel electrophoresis (2-DE). However, with traditional 2-DE informatics, the digitized images are reduced to symbolic data though spot detection and quantification before proteins are compared for differential expression by spot matching. Recently, a more robust and automated paradigm has emerged where gels are directly …
Bayesian Random Segmentationmodels To Identify Shared Copy Number Aberrations For Array Cgh Data,
2010
Texas A&M University
Bayesian Random Segmentationmodels To Identify Shared Copy Number Aberrations For Array Cgh Data, Veerabhadran Baladandayuthapani, Yuan Ji, Rajesh Talluri, Luis E. Nieto-Barajas, Jeffrey S. Morris
Jeffrey S. Morris
Array-based comparative genomic hybridization (aCGH) is a high-resolution high-throughput technique for studying the genetic basis of cancer. The resulting data consists of log fluorescence ratios as a function of the genomic DNA location and provides a cytogenetic representation of the relative DNA copy number variation. Analysis of such data typically involves estimation of the underlying copy number state at each location and segmenting regions of DNA with similar copy number states. Most current methods proceed by modeling a single sample/array at a time, and thus fail to borrow strength across multiple samples to infer shared regions of copy number aberrations. …
Simulating Multivariate G-And-H Distributions,
2010
Southern Illinois University Carbondale
Simulating Multivariate G-And-H Distributions, Rhonda K. Kowalchuk, Todd C. Headrick
Todd Christopher Headrick
The Tukey family of g-and-h distributions is often used to model univariate real-world data. There is a paucity of research demonstrating appropriate multivariate data generation using the g-and-h family of distributions with specified correlations. Therefore, the methodology and algorithms are presented to extend the g-and-h family from univariate to multivariate data generation. An example is provided along with a Monte Carlo simulation demonstrating the methodology. In addition, algorithms written in Mathematica 7.0 are available from the authors for implementing the procedure.
Statistical Simulation: Power Method Polynomials And Other Transformations,
2010
Southern Illinois University Carbondale
Statistical Simulation: Power Method Polynomials And Other Transformations, Todd C. Headrick
Todd Christopher Headrick
Although power method polynomials based on the standard normal distributions have been used in many different contexts for the past 30 years, it was not until recently that the probability density function (pdf) and cumulative distribution function (cdf) were derived and made available. Focusing on both univariate and multivariate nonnormal data generation, Statistical Simulation: Power Method Polynomials and Other Transformations presents techniques for conducting a Monte Carlo simulation study. It shows how to use power method polynomials for simulating univariate and multivariate nonnormal distributions with specified cumulants and correlation matrices. The book first explores the methodology underlying the power method, …
Comparison And Application Of Three Decorrelation Methods Pca, Maf And Acdc,
2010
Edith Cowan University
Comparison And Application Of Three Decorrelation Methods Pca, Maf And Acdc, Jacqueline Ferreira
Theses : Honours
Geostatistics is a branch of applied mathematics that deals with spatially correlated data. Analysing and modelling spatially correlated data can be difficult and time consuming, especially for a multivariate data set. One of the techniques used to make analysis and modelling easier involves decorrelation, whereby a linear transformation on the sample variables is used to associate the spatially correlated variables with a set of decorrelated factors which are statistically and spatially independent. PCA was one of the first multivariate techniques and is mostly used as a data reduction technique. A popular alternative decorrelation technique often used in the mining industry …
Fast Function-On-Scalar Regression With Penalized Basis Expansions,
2009
New York University
Fast Function-On-Scalar Regression With Penalized Basis Expansions, Philip T. Reiss, Lei Huang, Maarten Mennes
Lei Huang
Regression models for functional responses and scalar predictors are often fitted by means of basis functions, with quadratic roughness penalties applied to avoid overfitting. The fitting approach described by Ramsay and Silverman in the 1990s amounts to a penalized ordinary least squares (P-OLS) estimator of the coefficient functions. We recast this estimator as a generalized ridge regression estimator, and present a penalized generalized least squares (P-GLS) alternative. We describe algorithms by which both estimators can be implemented, with automatic selection of optimal smoothing parameters, in a more computationally efficient manner than has heretofore been available. We discuss pointwise confidence intervals …
Bayesian Inference For A Periodic Stochastic Volatility Model Of Intraday Electricity Prices,
2009
Melbourne Business School
Bayesian Inference For A Periodic Stochastic Volatility Model Of Intraday Electricity Prices, Michael S. Smith
Michael Stanley Smith
The Gaussian stochastic volatility model is extended to allow for periodic autoregressions (PAR) in both the level and log-volatility process. Each PAR is represented as a first order vector autoregression for a longitudinal vector of length equal to the period. The periodic stochastic volatility model is therefore expressed as a multivariate stochastic volatility model. Bayesian posterior inference is computed using a Markov chain Monte Carlo scheme for the multivariate representation. A circular prior that exploits the periodicity is suggested for the log-variance of the log-volatilities. The approach is applied to estimate a periodic stochastic volatility model for half-hourly electricity prices …
Bayesian Skew Selection For Multivariate Models,
2009
Melbourne Business School
Bayesian Skew Selection For Multivariate Models, Michael S. Smith, Anastasios Panagiotelis
Michael Stanley Smith
We develop a Bayesian approach for the selection of skew in multivariate skew t distributions constructed through hidden conditioning in the manners suggested by either Azzalini and Capitanio (2003) or Sahu, Dey and Branco~(2003). We show that the skew coefficients for each margin are the same for the standardized versions of both distributions. We introduce binary indicators to denote whether there is symmetry, or skew, in each dimension. We adopt a proper beta prior on each non-zero skew coefficient, and derive the corresponding prior on the skew parameters. In both distributions we show that as the degrees of freedom increases, …
Fast Function-On-Scalar Regression With Penalized Basis Expansions,
2009
New York University
Fast Function-On-Scalar Regression With Penalized Basis Expansions, Philip T. Reiss, Lei Huang, Maarten Mennes
Philip T. Reiss
Regression models for functional responses and scalar predictors are often fitted by means of basis functions, with quadratic roughness penalties applied to avoid overfitting. The fitting approach described by Ramsay and Silverman in the 1990s amounts to a penalized ordinary least squares (P-OLS) estimator of the coefficient functions. We recast this estimator as a generalized ridge regression estimator, and present a penalized generalized least squares (P-GLS) alternative. We describe algorithms by which both estimators can be implemented, with automatic selection of optimal smoothing parameters, in a more computationally efficient manner than has heretofore been available. We discuss pointwise confidence intervals …
