Mathematica and its partner, Group Health Cooperative, evaluated the effects of CPC on cost, quality, utilization, and patient and provider experience. We also provided rapid cycle (quarterly) feedback to participating practices, CMS, and CMS’s regional partners.
- Bayesian statistics
- Program and policy evaluation
- Scalability analysis
- Delivery System Reforms
- Population Health
Mariel Finucane is an expert in using Bayesian hierarchical modeling and tree-based methods to study social policies. Her most recent work has focused on healthcare, in areas such as primary care delivery, inpatient harm prevention, and hospital readmission reductions. Her team’s analyses provide intuitive, flexible inference and heightened precision when examining subgroup effects while maintaining a rigorous statistical standard.
Finucane has served as the lead Bayesian statistician on a number of large-scale evaluations for the Centers for Medicare & Medicaid Services, including evaluations of Primary Care First, the Transforming Clinical Practice Initiative, Comprehensive Primary Care, Comprehensive Primary Care Plus, Partnership for Patients, and Independence at Home.
Finucane has published widely about statistical methods, primary care, and population health, including first-author papers in the Journal of the American Statistical Association, Statistical Science, Statistical Methods in Medical Research, and Journal of Evaluation. She was also the first author of an article in the Lancet on global trends in body mass index that has been cited more than 4,000 times. Finucane holds a Ph.D. in biostatistics from the Harvard School of Public Health.
Evaluation of the Comprehensive Primary Care Initiative
Partnership for Patients
Mathematica conducted a formative evaluation and an impacts evaluation of this initiative. The formative evaluation included assessing and providing feedback on the progress of hospital engagement networks and their participating hospitals, and on the campaign overall, and suggesting ways to improve....
The BASIE (BAyeSian Interpretation of Estimates) Framework for Interpreting Findings from Impact Evaluations
This webinar lays out a Bayesian framework for interpreting impact estimates without the pitfalls of relying only on p-values.
Mathematica Organizes the American Causal Inference Conference’s 2022 Data Challenge
Mathematica is proud to organize this year’s American Causal Inference Conference’s 2022 Data Challenge competition, which launches on February 15 when the simulated data sets are posted on the data challenge website. Submissions are due April 15, and results will be announced at ACIC 2022 on May 24-25.