Welcome! I am a fifth-year Quantitative Methods Ph.D. candidate in the Department of Psychology and Human Development, and a National Science Foundation (NSF) graduate research fellow.
Throughout my graduate career, I have pursued multiple lines of methodological research. First, I have derived practical tools and useful insights pertaining to multilevel modeling. I have published and presented work which illuminates best practices for centering multicategorical predictors in multilevel models, and interpreting their effects. Currently in my NSF-funded work, I am studying approaches for diagnosing and mitigating the harmful effects of collinearity in multilevel data.
Second, I study intrinsically nonlinear regression models for social science. The goal of my dissertation is to reduce barriers to their use on multiple fronts. To reduce theoretical barriers, I present a novel framework for proceeding with each stage of the nonlinear modeling process in a theory-focused and substantively useful manner, including choosing a nonlinear function, parameterizing the chosen function, incorporating covariates, and including moderators. To reduce practical barriers, I am developing a Shiny app that will enable researchers to fit and interpret nonlinear regression models (with moderators) in a point-and-click environment.
Substantively, I am particularly interested in applying advanced statistical methods to questions in family, health, and developmental psychology. For example, using IRT methods, I developed and validated a novel self-report instrument to measure parents’ feelings of guilt regarding the food choices they make for their child. I have also served as a statistical consultant on a variety of applied projects spanning these content areas and more.