Statistics and Probability Commons^™

Moving Beyond The Conventional Stratified Analysis To Estimate An Overall Treatment Efficacy With The Data From A Comparative Randomized Clinical Study, Lu Tian, Fei Jiang, Takahiro Hasegawa, Hajime Uno, Marc Alan Pfeffer, L.J. Wei

Harvard University Biostatistics Working Paper Series

No abstract provided.

A Generalization Of The Difference Of Slopes Test To Poisson Regression With Three-Way Interaction, Melinda Bierhals

Theses, Dissertations and Capstones

Linear regression models involving interaction can use the difference of slopes test to compare slopes for various situations. We will be generalizing this process to develop a procedure to compare rates in a Poisson regression model, allowing us to consider unbounded count data as opposed to continuous data. We will apply this process to an educational data set from a sample of students located in two different Los Angeles high schools. Our model will include a three-way interaction and address the following questions:

• Does language ability impact the relationship between math ability and attendance in the same way for …

Detectable Viral Load In Late Pregnancy Among Women In The Rwanda Option B+ Pmtct Program: Enrollment Results From The Kabeho Study., Michelle M Gill, Heather J Hoffman, Emily A Bobrow, Placidie Mugwaneza, Dieudonne Ndatimana, Gilles F Ndayisaba, Cyprien Baribwira, Laura Guay, Anita Asiimwe

Epidemiology Faculty Publications

There are limited viral load (VL) data available from programs implementing "Option B+," lifelong antiretroviral treatment (ART) to all HIV-positive pregnant and postpartum women, in resource-limited settings. Extent of viral suppression from a prevention of mother-to-child transmission of HIV program in Rwanda was assessed among women enrolled in the Kigali Antiretroviral and Breastfeeding Assessment for the Elimination of HIV (Kabeho) Study. ARV drug resistance testing was conducted on women with VL>2000 copies/ml. In April 2013-January 2014, 608 pregnant or early postpartum HIV-positive women were enrolled in 14 facilities. Factors associated with detectable enrollment VL (>20 copies/ml) were examined …

Male Pattern Baldness In Relation To Prostate Cancer–Specific Mortality: A Prospective Analysis In The Nhanes I Epidemiologic Follow-Up Study, Cindy Ke Zhou, Paul H Levine, Sean D. Cleary, Heather J. Hoffman, Barry I Graubard, Michael B. Cook

Epidemiology Faculty Publications

We used male pattern baldness as a proxy for long-term androgen exposure and investigated the association of dermatologist-assessed hair loss with prostate cancer–specific mortality in the first National Health and Nutrition Examination Survey Epidemiologic Follow-up Study. From the baseline survey (1971–1974), we included 4,316 men who were 25–74 years of age and had no prior cancer diagnosis. We estimated hazard ratios and used Cox proportional hazards regressions with age as the time metric and baseline hazard stratified by baseline age. A hybrid framework was used to account for stratification and clustering of the sample design, with adjustment for the variables …

Privacy And Accountability In Black-Box Medicine, Roger Allan Ford, W. Nicholson Price Ii

Law Faculty Scholarship

Black-box medicine—the use of big data and sophisticated machine learning techniques for health-care applications—could be the future of personalized medicine. Black-box medicine promises to make it easier to diagnose rare diseases and conditions, identify the most promising treatments, and allocate scarce resources among different patients. But to succeed, it must overcome two separate, but related, problems: patient privacy and algorithmic accountability. Privacy is a problem because researchers need access to huge amounts of patient health information to generate useful medical predictions. And accountability is a problem because black-box algorithms must be verified by outsiders to ensure they are accurate and …

How Often Are Antibiotic-Resistant Bacteria Said To “Evolve” In The News?, Nina Singh, Matthew T. Sit, Deanna M. Chung, Ana A. Lopez, Ranil Weerackoon, Pamela J. Yeh

Department of Statistics: Faculty Publications

Media plays an important role in informing the general public about scientific ideas.We examine whether the word “evolve,” sometimes considered controversial by the general public, is frequently used in the popular press. Specifically, we ask how often articles discussing antibiotic resistance use the word “evolve” (or its lexemes) as opposed to alternative terms such as “emerge” or “develop.” We chose the topic of antibiotic resistance because it is a medically important issue; bacterial evolution is a central player in human morbidity and mortality. We focused on the most widely-distributed newspapers written in English in the United States, United Kingdom, Canada, …

Systematic Evaluation Of The Impact Of Chip-Seq Read Designs On Genome Coverage, Peak Identification, And Allele-Specific Binding Detection, Qi Zhang, Xin Zeng, Sam Younkin, Trupti Kawli, Michael P. Snyder, Sündüz Kele

Department of Statistics: Faculty Publications

Background: Chromatin immunoprecipitation followed by sequencing (ChIP-seq) experiments revolutionized genome-wide profiling of transcription factors and histone modifications. Although maturing sequencing technologies allow these experiments to be carried out with short (36–50 bps), long (75–100 bps), single-end, or paired-end reads, the impact of these read parameters on the downstream data analysis are not well understood. In this paper, we evaluate the effects of different read parameters on genome sequence alignment, coverage of different classes of genomic features, peak identification, and allele-specific binding detection.

Results: We generated 101 bps paired-end ChIP-seq data for many transcription factors from human GM12878 and MCF7 cell …

The Impact Of Hair Coat Color On Longevity Of Holstein Cows In The Tropics, C. N. Lee, K. S. Baek, A. Parkhurst

Department of Statistics: Faculty Publications

Background: Over two decades of observations in the field in South East Asia and Hawai‘i suggest that majority of the commercial dairy herds are of black hair coat. Hence a simple study to determine the accuracy of the observation was conducted with two large dairy herds in Hawaii in the mid-1990s.

Methods: A retrospective study on longevity of Holstein cattle in the tropics was conducted using DairyComp-305 lactation information coupled with phenotypic evaluation of hair coat color in two large dairy farms. Cows were classified into 3 groups: a) black (B, >90%); b) black/white (BW, 50:50) and c) white (W, …

Sex-Specific Hippocampal 5-Hydroxymethylcytosine Is Disrupted In Response To Acute Stress, Ligia A. Papale, Sisi Li, Andy Madrid, Qi Zhang, Li Chen, Pankaj Chopra, Peng Jin, Sunduz Keles, Reid S. Alisch

Department of Statistics: Faculty Publications

Environmental stress is among the most important contributors to increased susceptibility to develop psychiatric disorders. While it is well known that acute environmental stress alters gene expression, the molecular mechanisms underlying these changes remain largely unknown. 5-hydroxymethylcytosine (5hmC) is a novel environmentally sensitive epigenetic modification that is highly enriched in neurons and is associated with active neuronal transcription. Recently,we reported a genome-wide disruption of hippocampal 5hmCin male mice following acute stress that was correlated to altered transcript levels of genes in known stress related pathways. Since sex-specific endocrine mechanisms respond to environmental stimulus by altering the neuronal epigenome, we examined …

A Compendium Of Chromatin Contact Maps Reveals Spatially Active Regions In The Human Genome, Anthony D. Schmitt, Ming Hu, Inkyung Jung, Zheng Xu, Yunjiang Qiu, Catherine L. Tan, Yun Li, Shin Lin, Yiing Lin, Cathy L. Barr, Bing Ren

Department of Statistics: Faculty Publications

The three-dimensional configuration of DNA is integral to all nuclear processes in eukaryotes, yet our knowledge of the chromosome architecture is still limited. Genome-wide chromosome conformation capture studies have uncovered features of chromatin organization in cultured cells, but genome architecture in human tissues has yet to be explored. Here, we report the most comprehensive survey to date of chromatin organization in human tissues. Through integrative analysis of chromatin contact maps in 21 primary human tissues and cell types, we find topologically associating domains highly conserved in different tissues. We also discover genomic regions that exhibit unusually high levels of local …

Hiview: An Integrative Genome Browser To Leverage Hi‑C Results For The Interpretation Of Gwas Variants, Zheng Xu, Guosheng Zhang, Qing Duan, Shengjie Chai, Baqun Zhang, Cong Wu, Fulai Jin, Feng Yue, Yun Li, Ming Hu

Department of Statistics: Faculty Publications

Genome-wide association studies (GWAS) have identified thousands of genetic variants associated with complex traits and diseases. However, most of them are located in the non-protein coding regions, and therefore it is challenging to hypothesize the functions of these non-coding GWAS variants. Recent large efforts such as the ENCODE and Roadmap Epigenomics projects have predicted a large number of regulatory elements. However, the target genes of these regulatory elements remain largely unknown. Chromatin conformation capture based technologies such as Hi-C can directly measure the chromatin interactions and have generated an increasingly comprehensive catalog of the interactome between the distal regulatory elements …

A Bayesian Gwas Method Utilizing Haplotype Clusters For A Composite Breed Population, Danielle F. Wilson-Wells, Stephen D. Kachman

Department of Statistics: Faculty Publications

Commercial beef cattle are often composites of multiple breeds. Current methods used to produce genomic predictors are based on the underlying assumption of animals being sampled from a homogeneous population. As a result, the predictors can perform poorly when used to predict the relative genetic merit of animals whose breed composition are different. In part, this is due to the changes in linkage disequilibrium between the markers and the quantitative trait loci as we move from one breed to the next. An alternative model based on breed specific haplotype clusters was developed to allow for differences in linkage disequilibrium across …

Design Of Probabilistic Random Forests With Applications To Anticancer Drug Sensitivity Prediction- 2016, Raziur Rahman, Saad Haider, Souparno Ghosh, Ranadip Pal

Department of Statistics: Faculty Publications

Random forests consisting of an ensemble of regression trees with equal weights are frequently used for design of predictive models. In this article, we consider an extension of the methodology by representing the regression trees in the form of probabilistic trees and analyzing the nature of heteroscedasticity. The probabilistic tree representation allows for analytical computation of confidence intervals (CIs), and the tree weight optimization is expected to provide stricter CIs with comparable performance in mean error. We approached the ensemble of probabilistic trees’ prediction from the perspectives of a mixture distribution and as a weighted sum of correlated random variables. …

A Descriptive Study Of The Effect Of Payer Source On Multiple Longitudinal Outcome Measures Within The Tbi Model Systems National Database Using Longitudinal Hlm Analyses, Melissa Carole Hofmann

Electronic Theses and Dissertations

Using longitudinal data from the TBIMS ND, this study utilized a longitudinal hierarchical linear modeling approach to describe the effect of primary payer source on individual level change in outcomes including the FIM and DRS. To facilitate the use of parametric statistics, Rasch-transformed FIM and DRS scores were utilized; thus approaching an interval level of measurement. The FIM was separated into 3 separate cognitive, mobility, and self-care subscales. In this way, rehabilitation professionals including speech, physical, and occupational therapists for this TBI sample could reference results to inform current clinical practice.

Results indicated that FIM and DRS trajectories were best …

A Comparison Between Propensity Score Matching, Weighting, And Stratification In Multiple Treatment Groups: A Simulation Study, Priyalatha Govindasamy

Electronic Theses and Dissertations

The application of propensity score techniques (matching, stratification, and weighting) with multiple treatment levels are similar to those used in binary groups. However, given that the application of propensity scores in multiple treatment groups is new, factors affecting the performance of matching, stratification, and weighting in multiple treatment groups are less explored. Therefore, this study was conducted to determine the performance of different propensity score techniques with multiple treatment groups under various circumstances. Specifically, the study focused on examining how the three propensity score corrective techniques perform in estimating treatment effects under (1) overt and (2) hidden types of selection …

Clme: An R Package For Linear Mixed Effects Models Under Inequality Constraints, Casey M. Jelsema, Shyamal D. Peddada

Faculty & Staff Scholarship

In many applications researchers are typically interested in testing for inequality constraints in the context of linear fixed effects and mixed effects models. Although there exists a large body of literature for performing statistical inference under inequality constraints, user friendly statistical software implementing such methods is lacking, especially in the context of linear fixed and mixed effects models. In this article we introduce CLME, a package in the R language that can be used for testing a broad collection of inequality constraints. It uses residual bootstrap based methodology which is reasonably robust to non-normality as well as heteroscedasticity. The package …

Enscat: Clustering Of Categorical Data Via Ensembling, Bertrand S. Clarke, Saeid Amiri, Jennifer L. Clarke

Department of Statistics: Faculty Publications

Background: Clustering is a widely used collection of unsupervised learning techniques for identifying natural classes within a data set. It is often used in bioinformatics to infer population substructure. Genomic data are often categorical and high dimensional, e.g., long sequences of nucleotides. This makes inference challenging: The distance metric is often not well-defined on categorical data; running time for computations using high dimensional data can be considerable; and the Curse of Dimensionality often impedes the interpretation of the results. Up to the present, however, the literature and software addressing clustering for categorical data has not yet led to a standard …

Genomic Bayesian Prediction Model For Count Data With Genotype X Environment Interaction, Abelardo Montesinos-López, Osval A. Montesinos-López, José Crossa, Juan Burgueño, Kent M. Eskridge, Esteban Falconi-Castillo, Xinyao He, Pawan Singh, Karen Cichy

Department of Statistics: Faculty Publications

Genomic tools allow the study of the whole genome, and facilitate the study of genotype-environment combinations and their relationship with phenotype. However, most genomic prediction models developed so far are appropriate for Gaussian phenotypes. For this reason, appropriate genomic prediction models are needed for count data, since the conventional regression models used on count data with a large sample size (n_T ) and a small number of parameters (p) cannot be used for genomic-enabled prediction where the number of parameters (p) is larger than the sample size (n_T ). Here, we propose a Bayesian mixed-negative binomial (BMNB) genomic …

A Genomic Bayesian Multi-Trait And Multi-Environment Model, Osval A. Montesinos-López, Abelardo Montesinos-López, José Crossa, Fernando Toledo, Oscar Pérez-Hernández, Kent M. Eskridge, Jessica Rutkoski

Department of Statistics: Faculty Publications

When information on multiple genotypes evaluated in multiple environments is recorded, a multi-environment single trait model for assessing genotype × environment interaction (G×E) is usually employed. Comprehensive models that simultaneously take into account the correlated traits and trait × genotype × environment interaction (T×G×E) are lacking. In this research, we propose a Bayesian model for analyzing multiple traits and multiple environments for whole-genome prediction (WGP) model. For this model, we used Half-𝑡 priors on each standard deviation term and uniform priors on each correlation of the covariance matrix. These priors were not informative and led to posterior inferences that were …

Student Fact Book, Fall 2016 - Fortieth Annual Edition, Office Of Student Information Systems, Wright State University

Wright State University Student Fact Books

The student fact book has general demographic information on all students enrolled at Wright State University for Fall Semester, 2016.