Biostatistics Commons^™

Arsenic In Drinking Water And Lung Cancer Mortality In The United States: An Analysis Based On Us Counties And 30 Years Of Observation (1950-1979)., Hamid Ferdosi, Elisabeth K Dissen, Nana Ama Afari-Dwamena, Ji Li, Rusan Chen, Manning Feinleib, Steven H Lamm

Epidemiology Faculty Publications

Background. To examine whether the US EPA (2010) lung cancer risk estimate derived from the high arsenic exposures (10-934 µg/L) in southwest Taiwan accurately predicts the US experience from low arsenic exposures (3-59 µg/L). Methods. Analyses have been limited to US counties solely dependent on underground sources for their drinking water supply with median arsenic levels of ≥3 µg/L. Results. Cancer risks (slopes) were found to be indistinguishable from zero for males and females. The addition of arsenic level did not significantly increase the explanatory power of the models. Stratified, or categorical, analysis yielded relative risks that hover about 1.00. …

Salvage Brachytherapy For Biochemically Recurrent Prostate Cancer Following Primary Brachytherapy, John M. Lacy, William A. Wilson, Raevti Bole, Li Chen, Ali S. Meigooni, Randall G. Rowland, William H. St. Clair

Urology Faculty Publications

Purpose. In this study, we evaluated our experience with salvage brachytherapy after discovery of biochemical recurrence after a prior brachytherapy procedure. Methods and Materials. From 2001 through 2012 twenty-one patients treated by brachytherapy within University of Kentucky or from outside centers developed biochemical failure and had no evidence of metastases. Computed tomography (CT) scans were evaluated; patients who had an underseeded portion of their prostate were considered for reimplantation. Results. The majority of the patients in this study (61.9%) were low risk and median presalvage PSA was 3.49 (range 17.41–1.68). Mean follow-up was 61 months. At last follow-up after reseeding, …

Causal Inference In Observational Studies With Clustered Data, Meng Wu

Legacy Theses & Dissertations (2009 - 2024)

In this thesis, we study causal inference in observational studies with clustered data.

Estimating Survival Distributions, Important Covariates And Time-Varying Associations, Yan Wu

Legacy Theses & Dissertations (2009 - 2024)

There are three papers each on a different topic in this thesis. The first paper proposes a new objective methodology to estimate any subject specific survival distribution with potential time-varying effect by adjusting approximated polynomial censored survival function with estimated censoring distribution under three different assumptions: uniform censoring, independent censoring and non-informative censoring. The coefficients of the polynomial censored survival function and underlying censoring probability are estimated at each event or censoring time point across the study time frame, which naturally accommodates potential non-proportional hazards along with time-varying effect. An extensive simulation study indicates that the proposed methods usually perform …

Statistical Methods For Environmental Exposure Data Subject To Detection Limits, Yuchen Yang

Theses and Dissertations--Statistics

In this dissertation, we develop unified and efficient nonparametric statistical methods for estimating and comparing environmental exposure distributions in presence of detection limits. In the first part, we propose a kernel-smoothed nonparametric estimator for the exposure distribution without imposing any independence assumption between the exposure level and detection limit. We show that the proposed estimator is consistent and asymptotically normal. Simulation studies demonstrate that the proposed estimator performs well in practical situations. A colon cancer study is provided for illustration. In the second part, we develop a class of test statistics to compare exposure distributions between two groups by using …

Improved Models For Differential Analysis For Genomic Data, Hong Wang

Theses and Dissertations--Statistics

This paper intend to develop novel statistical methods to improve genomic data analysis, especially for differential analysis. We considered two different data type: NanoString nCounter data and somatic mutation data. For NanoString nCounter data, we develop a novel differential expression detection method. The method considers a generalized linear model of the negative binomial family to characterize count data and allows for multi-factor design. Data normalization is incorporated in the model framework through data normalization parameters, which are estimated from control genes embedded in the nCounter system. For somatic mutation data, we develop beta-binomial model-based approaches to identify highly or lowly …

Evaluating A Bystander Intervention Program On Reproductive Coercion: Using Quasi-Experimental Design Strategies To Address Methodologic Issues In Randomized Community Prevention Trials, Catherine P. Starnes

Theses and Dissertations--Epidemiology and Biostatistics

Community (or cluster) randomized trials are trials in which communities or groups of individuals (clusters) are randomized to receive the intervention of interest. Community randomized trials frequently more closely resemble a natural experiment than a randomized controlled trial (RCT) following intervention allocation. In particular, the effects of non-compliance can pose methodologic challenges in estimating the intervention effect which may require a quasiexperimental approach in order to minimize bias.

The motivating example to illustrate these issues is the Green Dot High School (GDHS) study. The GDHS study was a longitudinal, cluster-randomized controlled trial designed to assess the effectiveness of a bystander …

Aggregated Quantitative Multifactor Dimensionality Reduction, Rebecca E. Crouch

Theses and Dissertations--Statistics

We consider the problem of making predictions for quantitative phenotypes based on gene-to-gene interactions among selected Single Nucleotide Polymorphisms (SNPs). Previously, Quantitative Multifactor Dimensionality Reduction (QMDR) has been applied to detect gene-to-gene interactions associated with elevated quantitative phenotypes, by creating a dichotomous predictor from one interaction which has been deemed optimal. We propose an Aggregated Quantitative Multifactor Dimensionality Reduction (AQMDR), which exhaustively considers all k-way interactions among a set of SNPs and replaces the dichotomous predictor from QMDR with a continuous aggregated score. We evaluate this new AQMDR method in a series of simulations for two-way and three-way interactions, …

Meta-Analytic Estimation Techniques For Non-Convergent Repeated-Measure Clustered Data, Aobo Wang

Theses and Dissertations

Clustered data often feature nested structures and repeated measures. If coupled with binary outcomes and large samples (>10,000), this complexity can lead to non-convergence problems for the desired model especially if random effects are used to account for the clustering. One way to bypass the convergence problem is to split the dataset into small enough sub-samples for which the desired model convergences, and then recombine results from those sub-samples through meta-analysis. We consider two ways to generate sub-samples: the K independent samples approach where the data are split into k mutually-exclusive sub-samples, and the cluster-based approach where naturally existing …

Spatio-Temporal Analysis Of The Occupational Fatal Victimization Of Law Enforcement Officers In The Us, Xueyi Xing

Theses and Dissertations

The models with constant coefficients of the covariates across space and time are commonly used in spatio-temporal analyses. However, the associations between risk factors and the outcome could have locally differential temporal trends in many cases. In this study, a Bayesian latent cluster modeling strategy is employed to identify potential spatial clusters in which locally specific sets of temporally varying coefficients of covariates are allowed. A state-level panel data of police officers occupational fatal victimization for the years 1979-2010 is used. To accommodate overdisperson and excess zeros, a negative binomial model and zero-inflated Poisson/negative binomial models are also utilized. A …

Parametric Reversed Hazards Model For Left Censored Data With Application To Hiv, Farahnaz Islam

Theses and Dissertations

Left censoring is generally a rare type of censoring in time-to-event data, however there are some fields such as HIV related studies where it commonly occurs. Currently, there is no clear recommendation in the literature on the optimal model and distribution to analyze left-censored data. Recommendations can help researchers apply more accurate models for this type of censoring. This study derives the Parametric Reversed Hazards (PRH) Model for a variety of distributions which may be appropriate for left censored data. The performance of these derived PRH models to analyze HIV viral load data are compared using extensive simulations and a …

Score Test Derivations And Implementations For Bivariate Probability Mass And Density Functions With An Application To Copula Functions, Roy Bower

Theses and Dissertations

This dissertation is comprised and grounded in statistical theory with an application to solving real world problems. In particular, the development and implementation of multiple score tests under a variety of scenarios are derived, applied, and interpreted. In chapter 2, I propose a score test for independence of the marginals based on Lakshminarayana’s bivariate Poisson distribution. Each marginal distribution of the bivariate model is a univariate Poisson distribution, and the parameters of the bivariate distribution can be estimated using maximum likelihood methods. The simulation study shows that the score test maintains size close to the nominal level. To assess the …

The Reflected-Shifted-Truncated-Gamma Distribution For Negatively Skewed Survival Data With Application To Pediatric Nephrotic Syndrome, Sophia D. Waymyers

Theses and Dissertations

Negatively skewed survival data arise occasionally in public health fields and in statistical research. Standard distributions such as the exponential, generalized F, generalized gamma, Gompertz, log-logistic, lognormal, Rayleigh, and Weibull distributions are not always well suited to this data. The primary goal of this dissertation is to find a viable alternative for modeling negatively skewed survival data such as the time to first remission for pediatric patients with frequently relapsing or steroid dependent nephrotic syndrome.

We begin with a brief introduction of survival analysis and the nature of pediatric nephrotic syndrome. A meta-analysis on atopy and pediatric nephrotic syndrome using …

Finding The Cutpoint Of A Continuous Covariate In A Parametric Survival Analysis Model, Kabita Joshi

Theses and Dissertations

In many clinical studies, continuous variables such as age, blood pressure and cholesterol are measured and analyzed. Often clinicians prefer to categorize these continuous variables into different groups, such as low and high risk groups. The goal of this work is to find the cutpoint of a continuous variable where the transition occurs from low to high risk group. Different methods have been published in literature to find such a cutpoint. We extended the methods of Contal and O’Quigley (1999) which was based on the log-rank test and the methods of Klein and Wu (2004) which was based on the …

A Weighted Gene Co-Expression Network Analysis For Streptococcus Sanguinis Microarray Experiments, Erik C. Dvergsten

Theses and Dissertations

Streptococcus sanguinis is a gram-positive, non-motile bacterium native to human mouths. It is the primary cause of endocarditis and is also responsible for tooth decay. Two-component systems (TCSs) are commonly found in bacteria. In response to environmental signals, TCSs may regulate the expression of virulence factor genes.

Gene co-expression networks are exploratory tools used to analyze system-level gene functionality. A gene co-expression network consists of gene expression profiles represented as nodes and gene connections, which occur if two genes are significantly co-expressed. An adjacency function transforms the similarity matrix containing co-expression similarities into the adjacency matrix containing connection strengths. Gene …

Modeling Spatially Varying Effects Of Chemical Mixtures, Jenna Czarnota

Theses and Dissertations

Cancer incidence is associated with exposures to multiple environmental chemicals, and geographic variation in cancer rates suggests the importance of accommodating spatially varying effects in the analysis of environmental chemical mixtures and disease risk. Traditional regression methods are challenged by the complex correlation patterns inherent among co-occurring chemicals, and the applicability of geographically weighted regression models is limited in the setting of environmental chemical risk analysis. In comparison to traditional methods, weighted quantile sum (WQS) regression performs well in the identification of important environmental exposures, but is limited by the assumption that effects are fixed over space. We present an …

Selecting Spatial Scale Of Area-Level Covariates In Regression Models, Lauren Grant

Theses and Dissertations

Studies have found that the level of association between an area-level covariate and an outcome can vary depending on the spatial scale (SS) of a particular covariate. However, covariates used in regression models are customarily modeled at the same spatial unit. In this dissertation, we developed four SS model selection algorithms that select the best spatial scale for each area-level covariate. The SS forward stepwise, SS incremental forward stagewise, SS least angle regression (LARS), and SS lasso algorithms allow for the selection of different area-level covariates at different spatial scales, while constraining each covariate to enter at most one spatial …

Early Sex Work Initiation And Condom Use Among Alcohol-Using Female Sex Workers In Mombasa, Kenya: A Cross-Sectional Analysis, A. M. Parcesepe, Kelly L'Engle, S. L. Martin, S. Green, C. Suchindran, P. Mwarogo

Nursing and Health Professions Faculty Research and Publications

Objectives Early initiation of sex work is prevalent among female sex workers (FSWs) worldwide. The objectives of this study were to investigate if early initiation of sex work was associated with: (1) consistent condom use, (2) condom negotiation self-efficacy or (3) condom use norms among alcohol-using FSWs in Mombasa, Kenya.

Methods In-person interviews were conducted with 816 FSWs in Mombasa, Kenya. Sample participants were: recruited from HIV prevention drop-in centres, 18 years or older and moderate risk drinkers. Early initiation was defined as first engaging in sex work at 17 years or younger. Logistic regression modelled outcomes as a function …

Missing Data In Clinical Trial: A Critical Look At The Proportionality Of Mnar And Mar Assumptions For Multiple Imputation, Theophile B. Dipita

College of Graduate Studies: Theses & Dissertations

Randomized control trial is a gold standard of research studies. Randomization helps reduce bias and infer causality. One constraint of these studies is that it depends on participants to obtain the desired data. Whatever the researcher can do, there is a possibility to end up with incomplete data. The problem is more relevant in clinical trials when missing data can be related to the condition under study. The benefits of randomization is compromised by missing data. Multiple imputation is a valid method of treating missing data under the assumption of MAR. Unfortunately this is an unverified assumptions. Current practice advise …

Sample Size Calculation For Ph Mixture Cure Model, Yihong Zhan

Theses and Dissertations

With the development of advanced medical technology, a significant proportion of patients can be cured of many chronic diseases. Because a substantial fraction of patients have censored information, the standard survival model, such as the proportional hazards (PH) model cannot capture the cured information of patients. Thus PH mixture cure model is developed to handle the survival data with potential cured information. A corresponding sample size formula based on log rank test has been proposed by Wang et al. (2012) and the probability of death in their formula is only contributed by the control arm. However, to calculate the sample …