null Robert Platt, PhD
statistical methods • causal inference • perinatal epidemiology • pharmacoepidemiology • high-dimensional data • data science
My research focuses on research methods for epidemiologic research. Many statistical tools were not designed to address challenges of modern epidemiology. We would like to infer causation in complex problems, and we deal regularly with "big data" (large administrative databases of health care utilization). Traditional statistical methods can give biased results in these situations. My team develops methods to address these problems, and implements and evaluates these new methods in research problems in perinatal epidemiology and in drug safety.
Gabrielle Simoneau, Erica E. M. Moodie, Jagtar S. Nijjar, Robert W. Platt & the Scottish Early Rheumatoid Arthritis Inception Cohort Investigators(2020) Estimating Optimal Dynamic Treatment Regimes With Survival Outcomes, Journal of the American Statistical Association, 115:531, 1531-1539, DOI: 10.1080/01621459.2019.1629939.
Karim ME, Pang M, Platt RW. "Can We Train Machine Learning Methods to Outperform the High-dimensional Propensity Score Algorithm?" Epidemiology. 2018 Mar;29(2):191-198.
Filion KB, Azoulay L, Platt RW, et al. A Multicenter Observational Study of Incretin-based Drugs and Heart Failure.N Engl J Med. 2016 Mar 24;374(12):1145-54.
Pang M, Schuster T, Filion KB, Eberg M, Platt RW “Targeted Maximum Likelihood Estimation for Pharmacoepidemiological Research: A Real-World Example Using the Clinical Practice Research Datalink”. Epidemiology, 2016 Jul;27(4):570-7.
Schnitzer M.E., Moodie E.E.M., Platt, R.W., “Targeted maximum likelihood estimation for marginal time-dependent treatment effects under density misspecification “Biostatistics. 2013 Jan; 14(1):1-14.