Dr. Lewis applies her in-depth and diverse formal training in mathematics and big data to create microsimulation models, develop innovative quantitative evaluation methods, and solve data challenges in administrative healthcare data. Her projects focus on policy evaluation (e.g., evaluation of the Section 1115 Demonstration Waiver for Arkansas’s Medicaid expansion program), data integrity validation (e.g., estimation of hash ID collision rates in the Arkansas All-Payer Claims Database), and healthcare cost forecasting. Many of these data science projects involve advanced statistical methods such as multilevel modeling, machine learning, microsimulation, latent variable modeling, and geospatial analysis.
She previously was employed at the U.S. Department of the Treasury, where she developed and implemented various term structure models used for simulation, decomposition analysis, and evaluation of key metrics such as inflation expectation, term premia, expected short rate, and risk measures.
She received a doctorate in mathematics from the University of Maryland and published five peer-reviewed manuscripts while pursuing her doctoral degree. Her doctoral thesis focused on the modeling of crystal surfaces at nano- and micro-scale and free boundary partial differential equations derived as continuum limits of large ordinary differential equation systems.
She obtained a bachelor’s degree in mathematics from the University of California, Berkeley, where she graduated summa cum laude. Honors she has received include a Graduate Dean’s Award, Gold Medal in Teaching Excellence, and Monroe H. Martin Graduate Research Fellowship from the University of Maryland, as well as a Highest Honors Degree, Dorothea Klumpke Roberts Prize, and Highest Distinction in General Scholarship from the University of California, Berkeley.