Biostatistics Commons^™

Randomization-Based Confidence Intervals For Cluster Randomized Trials, Dustin J. Rabideau, Rui Wang

Harvard University Biostatistics Working Paper Series

In a cluster randomized trial (CRT), groups of people are randomly assigned to different interventions. Existing parametric and semiparametric methods for CRTs rely on distributional assumptions or a large number of clusters to maintain nominal confidence interval (CI) coverage. Randomization-based inference is an alternative approach that is distribution-free and does not require a large number of clusters to be valid. Although it is well-known that a CI can be obtained by inverting a randomization test, this requires randomization testing a non-zero null hypothesis, which is challenging with non-continuous and survival outcomes. In this paper, we propose a general method for …

Power Calculation For Cross-Sectional Stepped-Wedge Cluster Randomized Trials With Binary Outcomes, Linda J. Harrison, Rui Wang

Harvard University Biostatistics Working Paper Series

Power calculation for stepped-wedge cluster randomized trials (SW-CRTs) presents unique challenges, beyond those of standard cluster randomized trials (CRTs), due to the need to consider temporal within cluster correlations and background period effects. To date, power calculation methods specific to SW-CRTs have primarily been developed under a linear model. When the outcome is binary, the use of a linear model corresponds to assessing a prevalence difference; yet trial analysis often employs a non-linear link function. We assess power for cross-sectional SW-CRTs under a logistic model fitted by generalized estimating equations. Firstly, under an exchangeable correlation structure, we show the power …

Markov Chain Epidemic Models And Parameter Estimation, Oluwatobiloba Ige

Theses, Dissertations and Capstones

Over the years, various parts of the world have experienced disease outbreaks. Mathematical models are used to describe these outbreaks. We study the transmission of disease in simple cases of disease outbreaks by using compartmental models with Markov chains. First, we explore the formulation of compartmental SIS (Susceptible-Infectious-Susceptible) and SIR (Susceptible-Infectious-Recovered) disease models. These models are the basic building blocks of other compartmental disease models. Second, we build SIS and SIR disease models using both discrete and continuous time Markov chains. In discrete time models, transmission occurs at fixed time steps, and in continuous time models, transmission may occur at …

Predicting Diabetes Diagnoses, Sarah Netchert

Student Research Poster Presentations 2020

This study explored the traits and health state of African Americans in central Virginia in order to determine what traits put people at a higher probability of being diagnosed with diabetes. We also want to know which traits will generate the highest probability a person will be diagnosed with diabetes. Traits that were included and used in this study were cholesterol, stabilized glucose, high density lipoprotein levels, age(years), gender, height(inches), weight(pounds), systolic blood pressure, diastolic blood pressure, waist size(inches), and hip size(inches). There were 403 individuals included in study since they were only ones screened for diabetes out of 1,046 …

Shrinkage Priors For Isotonic Probability Vectors And Binary Data Modeling, Philip S. Boonstra, Daniel R. Owen, Jian Kang

The University of Michigan Department of Biostatistics Working Paper Series

This paper outlines a new class of shrinkage priors for Bayesian isotonic regression modeling a binary outcome against a predictor, where the probability of the outcome is assumed to be monotonically non-decreasing with the predictor. The predictor is categorized into a large number of groups, and the set of differences between outcome probabilities in consecutive categories is equipped with a multivariate prior having support over the set of simplexes. The Dirichlet distribution, which can be derived from a normalized cumulative sum of gamma-distributed random variables, is a natural choice of prior, but using mathematical and simulation-based arguments, we show that …

A Modular Framework For Early-Phase Seamless Oncology Trials, Philip S. Boonstra, Thomas M. Braun, Elizabeth C. Chase

The University of Michigan Department of Biostatistics Working Paper Series

Background: As our understanding of the etiology and mechanisms of cancer becomes more sophisticated and the number of therapeutic options increases, phase I oncology trials today have multiple primary objectives. Many such designs are now 'seamless', meaning that the trial estimates both the maximum tolerated dose and the efficacy at this dose level. Sponsors often proceed with further study only with this additional efficacy evidence. However, with this increasing complexity in trial design, it becomes challenging to articulate fundamental operating characteristics of these trials, such as (i) what is the probability that the design will identify an acceptable, i.e. safe …

After-Hours Incentives And Emergency Department Visits: Evidence From Ontario Forthcoming At Canadian Public Policy, Rose Anne Devlin, Koffi Ahoto Kpelitse, Lihua Li, Nirav Mehta, Sisira Sarma

Epidemiology and Biostatistics Publications

No abstract provided.

Evaluating The Effectiveness Of Aquatic Therapy On Mobility, Balance, And Level Of Functional Independence In Stroke Rehabilitation: A Systematic Review And Meta-Analysis., Alice Mary Iliescu, Amanda Mcintyre, Joshua C. Wiener, Jerome Iruthayarajah, Andrea Lee, Sarah Caughlin, Robert Teasell

Epidemiology and Biostatistics Publications

OBJECTIVE: To meta-analyze and systematically review the effectiveness of aquatic therapy in improving mobility, balance, and functional independence after stroke.

DATA SOURCES: Articles published in Medline, Embase, CINAHL, PsycINFO, and Scopus up to 20 August 2019.

STUDY SELECTION: Studies met the following inclusion criteria: (1) English, (2) adult stroke population, (3) randomized or non-randomized prospectively controlled trial (RCT or PCT, respectively) study design, (4) the experimental group received >1 session of aquatic therapy, and (5) included a clinical outcome measure of mobility, balance, or functional independence.

DATA EXTRACTION: Participant characteristics, treatment protocols, between-group outcomes, point measures, and measures of variability …

A Multinational Study Of The Etiology And Clinical Teleology Of Moral Evaluations Of Patient Behaviors, Anna Yu Lee

CGU Theses & Dissertations

This dissertation is a collection of four studies which collectively explore a hypothesized construct of ‘moral evaluation of patient behaviors’ (MEPB) as a driver of health professionals’ readiness to interact humanistically with their patients. In these studies, ‘humanistic interactions’ refer to the non-technical, intangible skills and factors of clinical competence; the factors specifically explored in these studies were compassion toward patients, self-efficacy for treating patients, and optimism toward patient treatment. For the purpose of specificity, all factors were examined as they pertained to patients with substance use disorders. Survey data from a convenience sample of 524 health professionals (i.e. physicians, …

Nutrition And Health Status Of Hemodialysis Patients In Dhaka, Bangladesh, Tanjina Rahman

Wayne State University Dissertations

Methods to identify patients at risk for End stage renal disease (ESRD) are a high priority in Bangladesh, where kidney transplants/dialysis options are limited and costly. Every year, 35,000 to 40,000 people reach ESRD in Bangladesh, but currently available facilities can hardly accommodate only 9000 to 10,000 new patients with twice weekly dialysis and the remaining 66% have no access to any kind of renal replacement therapy (RRT) in the form of dialysis or transplantation. Nutrition is an important factor in maintaining good health of hemodialysis patients. However, data on nutritional status of Bangladeshi dialysis patients is limited and is …

Integrated Multiple Adaptive Design Involving Sample Size Re-Estimation And (Covariate-Adjusted) Response-Adaptive Randomization For Continuous And Binary Outcomes, Christine M. Orndahl

Theses and Dissertations

Historically, clinical trials have been performed based on decisions made prior to the start of the trial. Adaptive designs have been developed to provide increased flexibility, allowing pre-specified changes to occur based on interim data. Each adaptive design addresses a unique pitfall of a non-adaptive design, such as minimizing the chance of an under- or over-powered study by utilizing interim data to update the sample size estimate (sample size re-estimation) or increasing the ethical benefit of a trial by allocating more participants to the better performing treatment group ([covariate-adjusted] response-adaptive randomization). Additional benefit is attainable by combining more than one …

Short-Term Effects Of Ambient Ozone, Pm2. 5, And Meteorological Factors On Covid-19 Confirmed Cases And Deaths In Queens, New York., Atin Adhikari, Jingjing Yin

Biostatistics, Epidemiology & Environmental Health Sciences: Faculty Publications

The outbreak of coronavirus disease 2019 (COVID-19), caused by the virus SARS-CoV-2, has been rapidly increasing in the United States. Boroughs of New York City, including Queens county, turn out to be the epicenters of this infection. According to the data provided by the New York State Department of Health, most of the cases of new COVID-19 infections in New York City have been found in the Queens county where 42,023 people have tested positive, and 3221 people have died as of 20 April 2020. Person-to-person transmission and travels were implicated in the initial spread of the outbreaks, but factors …

Molecular Typing Of Rickettsia Akari, Marina E. Eremeeva

Biostatistics, Epidemiology & Environmental Health Sciences: Faculty Publications

Rickettsia akari is an obligate intracellular bacterium that causes smallpox rickettsia. Rickettsia akari is an atypical member of the rickettsia spotted fever (SFG) group because it circulates in gamasid mites; however, only limited data are available regarding the degree of genetic diversity of R. akari isolates. We examined 13 isolates of R. akari isolated from humans, rodents, and ticks in the United States, the countries of the former USSR, and the former Yugoslavia for the period from 1946 to 2003 for diversity in the composition of tandem repeats (TR) and intergenic regions (IGR). Using the Tandem Repeat Finder software (http://tandem.bu.edu) …

Rickettsialpox – A Rare But Not Extinct Disease: A Review Of The Literature And New Directions, Marina Eremeeva, Kamalich Muniz-Rodriguez

Biostatistics, Epidemiology & Environmental Health Sciences: Faculty Publications

Smallpox rickettsia is an urban zoonosis caused by Rickettsia akari. To date, R. akari is the only characterized representative of the group of spotted fevers transmitted by the gamasid mite Liponyssoides sanguineus, which is common among peridomic rodents. This disease was first described in New York in 1946, and a few years later a similar outbreak occurred in the Ukrainian SSR. Numerous serological studies and diagnostics of sporadic cases of smallpox rickettsiosis suggest its widespread occurrence on the planet; however, the current geography and incidence of smallpox rickettsiosis is unknown. Smallpox rickettsiosis is characterized by the classic clinical triad of …

Nonparametric Misclassification Simulation And Extrapolation Method And Its Application, Congjian Liu

College of Graduate Studies: Theses & Dissertations

The misclassification simulation extrapolation (MC-SIMEX) method proposed by Küchenho et al. is a general method of handling categorical data with measurement error. It consists of two steps, the simulation and extrapolation steps. In the simulation step, it simulates observations with varying degrees of measurement error. Then parameter estimators for varying degrees of measurement error are obtained based on these observations. In the extrapolation step, it uses a parametric extrapolation function to obtain the parameter estimators for data with no measurement error. However, as shown in many studies, the parameter estimators are still biased as a result of the parametric extrapolation …

Multiple Imputation Using Influential Exponential Tilting In Case Of Non-Ignorable Missing Data, Kavita Gohil

College of Graduate Studies: Theses & Dissertations

Modern research strategies rely predominantly on three steps, data collection, data analysis, and inference. In research, if the data is not collected as designed, researchers may face challenges of having incomplete data, especially when it is non-ignorable. These situations affect the subsequent steps of evaluation and make them difficult to perform. Inference with incomplete data is a challenging task in data analysis and clinical trials when missing data related to the condition under the study. Moreover, results obtained from incomplete data are prone to biases. Parameter estimation with non-ignorable missing data is even more challenging to handle and extract useful …

Adjusting For Dropout In Randomized Controlled Clinical Trials, Katharine Stromberg

Theses and Dissertations

Dropout is a common issue in randomized controlled clinical trials and can negatively impact the internal validity of a study and potentially bias the treatment effect. When subjects discontinue study participation, they are not being given the opportunity to gain from the investigational therapy as if they had remained in the study, defeating one of the main purposes of clinical trials, providing treatment. Specifically in unblinded studies, such as the wait-list control (WLC) design, dropout is often due to group membership. Subjects allocated to the control group often dropout at higher rates than in the treatment group. Adaptive designs have …

Zero-Inflated Longitudinal Mixture Model For Stochastic Radiographic Lung Compositional Change Following Radiotherapy Of Lung Cancer, Viviana A. Rodríguez Romero

Theses and Dissertations

Compositional data (CD) is mostly analyzed as relative data, using ratios of components, and log-ratio transformations to be able to use known multivariable statistical methods. Therefore, CD where some components equal zero represent a problem. Furthermore, when the data is measured longitudinally, observations are spatially related and appear to come from a mixture population, the analysis becomes highly complex. For this matter, a two-part model was proposed to deal with structural zeros in longitudinal CD using a mixed-effects model. Furthermore, the model has been extended to the case where the non-zero components of the vector might a two component mixture …

A Comparative Spatial And Climate Analysis Of Human Granulocytic Anaplasmosis And Human Babesiosis In New York State (2013-2018), Collin J. O'Connor

Legacy Theses & Dissertations (2009 - 2024)

Human granulocytic anaplasmosis (HGA) and human babesiosis are tick-borne diseases spread by Ixodes scapularis (the blacklegged or deer tick) and are the result of infection with Anaplasma phagocytophilum and Babesia microti, respectively. In New York State (NYS), incidence rates of these diseases increased concordantly until around 2013, when rates of HGA began to increase more rapidly than human babesiosis, and the spatial extent of the diseases diverged. Surveillance data of tick-borne pathogens (2007 to 2018) and reported human cases of HGA (n=4,297) and human babesiosis (n=2,986) (2013 to 2018) from the New York State Department of Health (NYSDOH) showed a …

Semiparametric And Nonparametric Methods For Comparing Biomarker Levels Between Groups, Yuntong Li

Theses and Dissertations--Statistics

Comparing the distribution of biomarker measurements between two groups under either an unpaired or paired design is a common goal in many biomarker studies. However, analyzing biomarker data is sometimes challenging because the data may not be normally distributed and contain a large fraction of zero values or missing values. Although several statistical methods have been proposed, they either require data normality assumption, or are inefficient. We proposed a novel two-part semiparametric method for data under an unpaired setting and a nonparametric method for data under a paired setting. The semiparametric method considers a two-part model, a logistic regression for …