In this position, I provide expertise in Bayesian statistical modeling for the design and analysis of early stage clinical trials. My activities in this position include conducting exploratory data analyses into historical clinical trial datasets, conducting Bayesian simulation-based study design analyses, and analyzing clinical trial data using Bayesian models. I ensure that my work is rigorous and reproducible via the use of version-control software (Git) and R Markdown.My notable accomplishments in this position include making methodological contributions to Merck’s guidance on Bayesian decision rules for decision making, and using my research background in Bayesian models for multiple longitudinal outcomes to provide valuable insights into the development of novel vaccines; the latter of these accomplishments was achieved by using a customized Gibbs sampling MCMC algorithm to estimate the complex correlation structure between multiple longitudinal outcomes.

In this position, I collaboratively developed novel Bayesian statistical models for the analysis of Alzheimer’s disease and related dementias (ADRD) study data. These statistical models focused on longitudinal data analysis, (high-dimensional) variable selection, and measurement error. These models were implemented in R via customized MCMC Gibbs sampling algorithms and evaluated via sophisticated simulation studies. I also ensured that my work was rigorous and reproducible via the use of version-control software (Git) and R Markdown.At the end of my postdoctoral training, I was awarded the University of Pennsylvania’s T32 postdoctoral fellowship. This T32 was awarded to 2 postdoctoral trainees for the statistical modeling of ADRD neuroimaging data.

In this position, I collaboratively developed Bayesian statistical models for longitudinal data analysis, variable selection, and spatio-temporal disease incidence data to analyze complex data arising in the study of Alzheimer’s disease. These models were implemented in R via custom MCMC Gibbs sampling algorithms and the NIMBLE probabilistic programming language, and were evaluated via sophisticated simulation studies.For the academic years of 2018 to 2020, I was awarded a position in the TL1 (T32) predoctoral clinical and translational research training program grant at MUSC to develop Bayesian statistical models for the characterization of Alzheimer’s disease risk. As part of this program, I gained extensive collaborative and translational research experience.

At the Dr. Yukiko Sugi lab in Department of Regenerative Medicine and Cell Biology, I conducted experiments via basic molecular biological techniques related to the developmental biology of the heart. I also conducted statistical analyses of subsequent experimental data.