My methodological research focuses on Bayesian nonparametric approaches to a variety of problems including multiple testing, density estimation, and supervised learning. More specifically, I aim to address key questions related to assumptions in parametric approaches by envisioning new, flexible solutions that are computationally efficient and widely available. My work has been published in journals like Statistics and Computing, and Computational Statistics and Data Analysis.
My future work in supervised learning includes a nonparametric classification schema which has been submitted to Advances in Classification and Data Analysis. I am currently working with collaborators to extend this methodology for prediction and feature selection using Householder reflections to make the approaches computationally efficient. Due to the success of these approaches in applications to real data, I'm currently working on implementing these methods into R packages which would make these theoretical approaches widely available.
I also complete many collaborations by providing simulation techniques to other statisticians and quantitative expertise to those in other sciences including Sociology, Psychology, Biology and the Medical field. These interdisciplinary collaborations involve translating qualitative hypotheses to a quantitative, actionable solutions through careful experimental design and model building. These solutions provide precise estimates and compelling evidence for such impactful theories about the world. These works have been published in top journals of statistical simulation, sociology, psychology, biology and Medicine.
2012–2016 Ph.D Statistics, University of South Carolina, Columbia, SC.
2012–2014 MS Statistics, University of South Carolina, Columbia, SC.
2007–2011 BA Mathematics, Quinnipiac University, Hamden, CT.
2007–2011 BS Computer Science, Quinnipiac University, Hamden, CT.
Research + Teaching
Please download a copy of my CV
, teaching dossier
, diversity statement
and research dossier