Statistics and Probability Commons^™

Infer: An R Package For Tidyverse-Friendly Statistical Inference, Simon P. Couch, Andrew P. Bray, Chester Ismay, Evgeni Chasnovski, B. Baumer, Mine Cetinkaya-Rundel

Statistical and Data Sciences: Faculty Publications

infer implements an expressive grammar to perform statistical inference that adheres to the tidyverse design framework (Wickham et al., 2019). Rather than providing methods for specific statistical tests, this package consolidates the principles that are shared among common hypothesis tests and confidence intervals into a set of four main verbs (functions), supplemented with many utilities to visualize and extract value from their outputs.

Blood Biomarkers For Mild Traumatic Brain Injury: A Selective Review Of Unresolved Issues, Daniel B. Hier, Tayo Obafemi-Ajayi, Matthew S. Thimgan, Gayla R. Olbricht, Sima Azizi, Blaine Allen, Bassam A. Hadi, Donald C. Wunsch

Biological Sciences Faculty Research & Creative Works

Background: The use of blood biomarkers after mild traumatic brain injury (mTBI) has been widely studied. We have identified eight unresolved issues related to the use of five commonly investigated blood biomarkers: neurofilament light chain, ubiquitin carboxy-terminal hydrolase-L1, tau, S100B, and glial acidic fibrillary protein. We conducted a focused literature review of unresolved issues in three areas: mode of entry into and exit from the blood, kinetics of blood biomarkers in the blood, and predictive capacity of the blood biomarkers after mTBI.

Findings: Although a disruption of the blood brain barrier has been demonstrated in mild and severe traumatic brain …

Controlled Branching Processes With Continuous Time, Miguel Gonzalez, Manuel Molina, Ines Del Puerto, Nikolay Yanev, George Yanev

School of Mathematical & Statistical Sciences Faculty Publications

A class of controlled branching processes with continuous time is introduced and some limiting distributions are obtained in the critical case. An extension of this class as regenerative controlled branching processes with continuous time is proposed and some asymptotic properties are considered.

Analysis Of Genes (Tmem106b, Grn, Abcc9, Kcnmb2, And Apoe) Implicated In Risk For Late-Nc And Hippocampal Sclerosis Provides Pathogenetic Insights: A Retrospective Genetic Association Study, Adam J. Dugan, Peter T. Nelson, Yuriko Katsumata, Lincoln M. P. Shade, Kevin L. Boehme, Merilee A. Teylan, Matthew D. Cykowski, Shubhabrata Mukherjee, John S. K. Kauwe, Timothy J. Hohman, Julie A. Schneider, Alzheimer’S Disease Genetics Consortium, David W. Fardo

Biostatistics Faculty Publications

Limbic-predominant age-related TDP-43 encephalopathy neuropathologic change (LATE-NC) is the most prevalent subtype of TDP-43 proteinopathy, affecting up to 1/3rd of aged persons. LATE-NC often co-occurs with hippocampal sclerosis (HS) pathology. It is currently unknown why some individuals with LATE-NC develop HS while others do not, but genetics may play a role. Previous studies found associations between LATE-NC phenotypes and specific genes: TMEM106B, GRN, ABCC9, KCNMB2, and APOE. Data from research participants with genomic and autopsy measures from the National Alzheimer’s Coordinating Center (NACC; n = 631 subjects included) and the Religious Orders Study and Memory …

Conservative Unconditionally Stable Decoupled Numerical Schemes For The Cahn-Hilliard-Navier-Stokes-Darcy-Boussinesq System, Wenbin Chen, Daozhi Han, Xiaoming Wang, Yichao Zhang

Mathematics and Statistics Faculty Research & Creative Works

We propose two mass and heat energy conservative, unconditionally stable, decoupled numerical algorithms for solving the Cahn-Hilliard-Navier-Stokes-Darcy-Boussinesq system that models thermal convection of two-phase flows in superposed free flow and porous media. The schemes totally decouple the computation of the Cahn-Hilliard equation, the Darcy equations, the heat equation, the Navier-Stokes equations at each time step, and thus significantly reducing the computational cost. We rigorously show that the schemes are conservative and energy-law preserving. Numerical results are presented to demonstrate the accuracy and stability of the algorithms.

A Southwestern United States Pilot Investigation Of Triatomine–Mite Prevalence, Kyndall C. Dye-Braumuller, Hanna Waltz, Mary K. Lynn, Stephen A. Klotz, Justin O. Schmidt, Alvaro Romero, Marvin Stanley Rodriguez Aquino, Jose Ricardo Palacios Valladares, Pamela Michelle Cornejo Rivas, Melissa Nolan Ph.D., Mph

Faculty Publications

An estimated 70 million persons in the Western Hemisphere are living at risk for Chagas disease, a parasitic infection transmitted to humans by over 156 different competent triatomine insect vector species. Prior Pan American Health Organization insecticide campaigns throughout Latin America in the 1990s and 2000s demonstrated that domestic insecticide spraying had temporary effects, which resulted in the re-establishment of triatomine species within a few years. Serendipitously, our team found ectoparasitic mites parasitizing triatomines collected from the field in multiple locations in the southwestern United States, where human–triatomine interaction was high but human parasite infection remains low. Upon further investigation …

Ratio And Difference Of Average Hazard With Survival Weight: New Measures To Quantify Survival Benefit Of New Therapy, Hajime Uno, Miki Horiguchi

Harvard University Biostatistics Working Paper Series

The hazard ratio (HR) has been the most popular measure to quantify the magnitude of treatment effect on time-to-event outcomes in clinical research. However, the HR estimated by Cox's method has several drawbacks. One major issue is that there is no clear interpretation when the proportional hazards (PH) assumption does not hold, because it is affected by study-specific censoring time distribution in non-PH cases. Another major issue is that the lack of a group-specific absolute hazard value in each group obscures the clinical significance of the magnitude of the treatment effect. Given these, we propose average hazard with survival weight …

Maternal Diet In Pregnancy And Child’S Respiratory Outcomes: An Individual Participant Data Meta-Analysis Of 18 000 Children, Sara M. Mensink-Bout, Evelien R. Van Meel, Johan C. De Jongste, Isabella Annesi-Maesano, Adrien M. Aubert, Jonathan Y. Bernard, Ling-Wei Chen, Cyrus Cooper, Sarah R. Crozier, Wojciech Hanke, Nicholas C. Harvey, James R. Hébert Scd, Barbara Heude, Joanna Jerzynska, Cecily C. Kelleher, John Mehegan, Fionnuala M. Mcauliffe, Catherine M. Phillips, Kinga Polanska, Caroline L. Relton, Nitin Shivappa Mbbs, Mph, Ph.D., Matthew Suderman, Vincent W.V. Jaddoe, Liesbeth Duijts

Faculty Publications

Rationale Severe fetal malnutrition has been related to an increased risk of respiratory diseases later in life, but evidence for the association of a suboptimal diet during pregnancy with respiratory outcomes in childhood is conflicting. We aimed to examine whether a pro-inflammatory or low-quality maternal diet during pregnancy was associated with child's respiratory health.

Methods We performed an individual participant meta-analysis among 18 326 mother–child pairs from seven European birth cohorts. Maternal pro-inflammatory and low-quality diets were estimated by energy-adjusted Dietary Inflammatory Index (E-DII) and Dietary Approaches to Stop Hypertension (DASH) scores. Preschool wheezing and school-age asthma were measured using …

Hiv Infection And The Risk Of World Health Organization-Defined Sudden Cardiac Death, Matthew S. Freiberg, Meredith S. Duncan, Charles Alcorn, Chung-Chou H. Chang, Suman Kundu, Asri Mumpuni, Emily K. Smith, Sarah Loch, Annie Bedigian, Eric Vittinghoff, Kaku So-Armah, Priscilla Y. Hsue, Amy C. Justice, Zian H. Tseng

Biostatistics Faculty Publications

Background

People living with HIV have higher sudden cardiac death (SCD) rates compared with the general population. Whether HIV infection is an independent SCD risk factor is unclear.

Methods and Results

This study evaluated participants from the Veterans Aging Cohort Study, an observational, longitudinal cohort of veterans with and without HIV infection matched 1:2 on age, sex, race/ethnicity, and clinical site. Baseline for this study was a participant's first clinical visit on or after April 1, 2003. Participants were followed through December 31, 2014. Using Cox proportional hazards regression, we assessed whether HIV infection, CD4 cell counts, and/or HIV viral …

Associations Of Circulating Dimethylarginines With The Metabolic Syndrome In The Framingham Offspring Study, Ibrahim Musa Yola, Carlee Moser, Meredith S. Duncan, Edzard Schwedhelm, Dorothee Atzler, Renke Maas, Juliane Hannemann, Rainer H. Böger, Ramachandran S. Vasan, Vanessa Xanthakis

Biostatistics Faculty Publications

BACKGROUND: Circulating levels of the endogenous inhibitor of nitric oxide synthase, asymmetric dimethylarginine (ADMA), are positively associated with the prevalence of metabolic syndrome (MetS) in cross-sectional investigations. It is unclear if circulating ADMA and other methylarginines are associated with incident MetS prospectively.

METHODS: We related circulating ADMA, symmetric dimethylarginine (SDMA), L-arginine (ARG) concentrations (measured with a validated tandem mass spectrometry assay) and the ARG/ADMA ratio to MetS and its components in 2914 (cross-sectional analysis, logistic regression; mean age 58 years, 55% women) and 1656 (prospective analysis, Cox regression; mean age 56 years, 59% women) individuals from the Framingham Offspring Study …

A Computational Study Of Genotype-Phenotype Mutation Patterns, Kamaludin Dingle, Omar Tawfik, Ahmed Aldabagh

Undergraduate Research Symposium

Understanding properties of genotype-phenotype maps is important for understanding biology and evolution. In this project we make a computational study of the statistical effects of genetic mutations, in particular computing the probabilities of each phenotype transitioning to any other phenotype. We also investigate the importance of the local phenotypic environment of a single genotype, and its role in determining mutation transition probabilities. We use HP protein folding, RNA structure, and a simplified GRN matrix model to study these questions.

Estimation Of Conditional Power For Cluster-Randomized Trials With Interval-Censored Endpoints, Kaitlyn Cook, Rui Wang

Statistical and Data Sciences: Faculty Publications

Cluster-randomized trials (CRTs) of infectious disease preventions often yield correlated, interval-censored data: dependencies may exist between observations from the same cluster, and event occurrence may be assessed only at intermittent study visits. This data structure must be accounted for when conducting interim monitoring and futility assessment for CRTs. In this article, we propose a flexible framework for conditional power estimation when outcomes are correlated and interval-censored. Under the assumption that the survival times follow a shared frailty model, we first characterize the correspondence between the marginal and cluster-conditional survival functions, and then use this relationship to semiparametrically estimate the cluster-specific …

Prevalence, Awareness, And Control Of Hypertension Among Bangladeshi Adults: An Analysis Of Demographic And Health Survey 2017-18, Gulam Muhammed Al Kibria, Rajat Das Gupta Ph.D., Jannatun Nayeem

Faculty Publications

Background

The prevalence of hypertension is increasing in Bangladesh, however, few recent studies investigated the proportion of people and factors associated with prevalence, awareness, and control of this condition in this country. This study investigated these among Bangladeshi adults.

Methods

Using Bangladesh Demographic and Health Survey 2017–18 data, a cross-sectional study was conducted. Multilevel logistic regression analysis was employed after descriptive analysis and prevalence estimation.

Results

Among 12,926 persons (mean age: 40 years, 57% women), the prevalence of hypertension was 27.4% (n = 3551), it was 28.4 and 26.2% among females and males, respectively. Among hypertensive people, about 42.4% …

Characterizing Convolutional Neural Network Early-Learning And Accelerating Non-Adaptive, First-Order Methods With Localized Lagrangian Restricted Memory Level Bundling, Benjamin O. Morris

Theses and Dissertations

This dissertation studies the underlying optimization problem encountered during the early-learning stages of convolutional neural networks and introduces a training algorithm competitive with existing state-of-the-art methods. First, a Design of Experiments method is introduced to systematically measure empirical second-order Lipschitz upper bound and region size estimates for local regions of convolutional neural network loss surfaces experienced during the early-learning stages. This method demonstrates that architecture choices can significantly impact the local loss surfaces traversed during training. Next, a Design of Experiments method is used to study the effects convolutional neural network architecture hyperparameters have on different optimization routines' abilities to …

Wavelet Methods For Very-Short Term Forecasting Of Functional Time Series, Jared K. Nystrom

Theses and Dissertations

Space launch operations at Kennedy Space Center and Cape Canaveral Space Force Station (KSC/CCSFS) are complicated by unique requirements for near-real time determination of risk from lightning. Lightning forecast weather sensor networks produce data that are noisy, high volume, and high frequency time series for which traditional forecasting methods are often ill-suited. Current approaches result in significant residual uncertainties and consequentially may result in forecasting operational policies that are excessively conservative or inefficient. This work proposes a new methodology of wavelet-enabled semiparametric modeling to develop accurate and timely forecasts robust against chaotic functional data. Wavelets methods are first used to …

Finding Similar Stocks By Detecting Cliques In Market Graphs, Sudhashree Sayenju

Symposium of Student Scholars

The stock market provides an abundant source of data. However, when the amount of raw data becomes overwhelming it grows increasingly difficult to know how the stocks interact with each other. Stock data visualization as a market graph serves as one of the most popular way of summarizing important information. When modelling the data as a graph, vertices correspond to stocks and edges correspond to strong correlation in their pricing in a certain period of time. This project presents a technique to find stocks that behave very similarly. Such information helps investors make decisions on which stocks to purchase next. …

The Relationship Of Delivery Method, Birth Weight And Race On Infant Mortality, Anjie Adeyemo

Symposium of Student Scholars

Infant mortality is defined as the number of deaths per 1000 births. The U.S. infant mortality rate in 2014 was reported as 5.8 deaths per 1000 births which is very high compared to other countries such as Japan where the rate 2.1 deaths per 1000 births. The leading causes of infant death are congenital malformations, SIDS, low birthweight, pre-term births and maternal complications. For this project, I will analyze birthweight in addition to other factors related to infant death. My research aims to see how the factors of delivery method, birthweight, and race influence infant mortality to see how it …

Anti-Vaxxers: Parents Fighting Science, Katie West

Symposium of Student Scholars

Immunizing children helps protect the health of our community, especially those people who cannot be immunized. Yet, since 1996 after a study was released that linked autism to vaccinations, there has been a trend of parents refusing to vaccinate their children. What are the demographics of the parents who believe their children are better off without vaccines? By knowing where these parents live and what decisions they make for their children’s education, counties and medical professionals can provide education and address their concerns.

My research involves data on 116,141 kindergarten classes from 2000-2015 in California. The two vaccine exemption options …

Why Does An Ex-Offender Reoffend?, Jacob Rybak

Symposium of Student Scholars

What leads to an offender to go back to prison? Iowa has collected data tracking recidivism to evaluate the effectiveness of its programs for released offenders. This data set includes the following for all of the offenders: age groups, type of release (parole vs being discharged at the end of their sentence), race, sex, year of release, supervising district, original offense, and whether they recidivated. For the offenders who return to prison, the data set includes measures on days to return, type of recidivism (technicality or new crime), and what the specific offense was that caused their return.

In the …

Opioid Abuse: Are Doctors Creating The Problem?, Nguyen Tran

Symposium of Student Scholars

Opioid abuse and overdose are serious health problems in the United States. Current research has concentrated on the treatment and prevention of opioid abuse. Using data from the Controlled Substance Utilization Review and Evaluation System (CURES) for California zip codes, my research focuses on the causes of opioid overdose by considering the relationships between the following variables within each zip code: population size, average number of prescriptions per doctor, percentage of people who receive opioid prescriptions, percentage of people receiving the same prescription drug from 3 or more doctors, average number of opioid pills per prescription and number of people …