I coined the term computational health economics several years ago when I found myself otherwise needing a full sentence to encapsulate the work I do in applied statistics, policy, and health economics. This label has been useful given there are not many scholars working at this intersection.

Computational health economics brings statistical advances for big data and data science to answer critical questions in health economics.

My methodological and applied research currently focuses on algorithmic fairness in risk adjustment and the generalizability of computational health economics tools. Much of my ongoing work is funded by my NIH Director's New Innovator Award.


NIH Makes $8.5M Investment in Promising Projects

Deep Dive: Machine Learning Tools Search Vast Oceans of Data for Insights on Health Economics

Sherri Rose Awarded Harvard Data Science Initiative Grant


S. Bergquist, T. Layton, T. McGuire, S. Rose (2018). Intervening on the data to improve the performance of health plan payment methods. [NBER Working Paper]

S. Rose (2018). Stacked propensity score functions for observational cohorts with oversampled exposed subjects. [arXiv]

S. Rose, T. McGuire (2018). Limitations of p-values and R-squared for stepwise regression building: A fairness demonstration in health policy risk adjustment, The American Statistician. [arXiv]

S. Rose (2018). Robust machine learning variable importance analyses of medical conditions for health care spending, Health Services Research. [PDF]

A. Shrestha, S. Bergquist, E. Montz, S. Rose (2018). Mental health risk adjustment with clinical categories and machine learning, Health Services Research. [PDF]

S. Rose, S. Bergquist, T. Layton (2017). Computational health economics for identification of unprofitable health care enrollees, Biostatistics. [Link][Code]

S. Rose (2016). A machine learning framework for plan payment risk adjustment, Health Services Research. [Link]