About

Biostatistician with 20 years of experience in the design and analysis of epidemiological studies, focusing on the relationship between exposure and subsequent development of disease. Implemented a statistical method to handle missing data in longitudinal studies. Compared exposure-disease associations using self-report vs. hospitalization data.

Core competencies include SAS (20+ years), SQL (in database, via PROC SQL), R, regression (linear, logistic, conditional logistic, multinomial, ordinal, Poisson, negative binomial, mixed models, generalized estimating equations, trajectory analysis), survival analysis (Kaplan-Meier curves, log-rank tests, Cox Proportional Hazards (extensive experience), non-proportional hazards approaches (familiarity)), power and sample size calculations (via closed-form equations and/or Monte Carlo simulation), causal inference methods (propensity score, causal mediation), missing data methods (Multiple Imputation, Inverse Probability Weighting), randomized trials (public health), factor analysis/principle component analysis, data management (PROC TRANSPOSE, MACROS, data linkage between multiple sources), supervising, mentoring (statistical methodology (e.g., Cox Proportional Hazards, Dual Trajectory Analysis), SAS/R programming, interpretation of results, creation of 1:1 matched dataset for Case-Control study, manuscript preparation) and training.