Background: The unprecedented outbreak of COVID-19 in December 2019 necessitated the use of emergency response measures to mitigate the spread of the virus. The state …
Background: The escalating frequency, intensity, and duration of extreme heat events due to climate change pose significant threats to public health and strain healthcare systems. …
Risk score models are simple scoring systems that map patient characteristics to the probability of an outcome occurring. These models are popular with clinicians because …
Bladder cancer poses a significant global health burden, necessitating effective prevention and treatment strategies. This study aims to inform the development of the KYSTIS microsimulation …
The random forest algorithm is a popular non-parametric alternative to more parametric approaches when building risk prediction models. In short, the algorithm averages predictions from …
Time introduces complexity in causal inference for observational studies. This thesis investigates two sources of bias for studies involving time-varying data. One is the missing …
Globally over 34 million people with HIV, with 67% in sub-Saharan Africa alone (UNAIDS) 2009. Data from randomized trials to inform on clinical decisions scarce. …
Provider profiling is used to gauge the level of care that is being offered across providers. The extensive repercussions of provider profiling on the health …
This thesis work is motivated by the specific challenges in analyzing data from clinical trials in behavioral medicine. Specifically, smoking cessation and physical activity trials. …
Abstract of Analysis of temporal trends in opioid prescribing: Assessing the Effectiveness of an opioid prescribing policy using segmented regression, difference in difference versus propensity …
This dissertation presents methods for statistical analysis of social network data. First, we develop a Bayesian hierarchical model that calibrates self and peer-reports in order …
Background: Diagnostic models are useless unless they are valid in the population to which they are applied. The validity of a model often involves measures …
We extend the results presented by Antos et al. [1] for nonparametric estimation methods using complete datasets to nonparametric regression estimators that use right censored …
Randomized controlled trials (RCTs) are often considered the gold standard for investigating the effects of an intervention. However, selective recruitment criteria often exclude vulnerable populations …
In practice, it is rare that the true generating mechanism of a data source is known. This uncertainty presents a challenge to statisticians, who are …
Prediction and causality are of significant importance in public health and epidemiology. Questions of interest related to predictive modeling include the screening for high risk …
Individual-Level Data (IPD) approach has become increasingly popular as it does not depend on published results. Combining IPD across multiple studies usually adopts a multilevel …
This study introduces Biologically Annotated Neural Networks (BANNs) for identifying causal Single Nucleotide Polymorphisms (SNPs) linked to complex traits. BANNs combine neural network flexibility with …
Abstract of Calibrating Transition Probabilities for Tobacco Use in Markov Multi-state Modeling, by Breanna Richards, Degree ScM, Brown University, May 2023 Background and Aims: Tobacco …
