Professor of Biostatistics
University of Pennsylvania's Perelman School of Medicine
My research focuses on the development and application of methods to improve epidemiologic and clinical research that uses real world data sources such as electronic health records (EHR) and medical claims data. Because these data sources were not created for research purposes, analyses based on real world data have many potential sources of bias including confounding, measurement error, missing data, and informative observation schemes. My research focuses on identifying study questions and study designs that can be validly implemented in real world data and developing statistical methods to overcome the challenges of using messy and imperfect data to answer these questions. This work has been applied across a broad range of research areas including health services research, cancer epidemiology, aging and dementia, and pharmacoepidemiology. In addition to my research, I am committed to improving the quality and validity of observational research by helping to train the next generation of statistical and clinical researchers. I have taught short courses on methods for analysis of EHR data and pharmacoepidemiology in a variety of venues for over a decade including the Joint Statistical Meetings, the Deming Conference on Applied Statistics, and the FDA.
Research website: https://www.med.upenn.edu/ehr-stats/
Professor of Biostatistics
University of Pennsylvania's Perelman School of Medicine
My research focuses on the development and application of methods to improve epidemiologic and clinical research that uses real world data sources such as electronic health records (EHR) and medical claims data. Because these data sources were not created for research purposes, analyses based on real world data have many potential sources of bias including confounding, measurement error, missing data, and informative observation schemes. My research focuses on identifying study questions and study designs that can be validly implemented in real world data and developing statistical methods to overcome the challenges of using messy and imperfect data to answer these questions. This work has been applied across a broad range of research areas including health services research, cancer epidemiology, aging and dementia, and pharmacoepidemiology. In addition to my research, I am committed to improving the quality and validity of observational research by helping to train the next generation of statistical and clinical researchers. I have taught short courses on methods for analysis of EHR data and pharmacoepidemiology in a variety of venues for over a decade including the Joint Statistical Meetings, the Deming Conference on Applied Statistics, and the FDA.
Research website: https://www.med.upenn.edu/ehr-stats/