Research Interests

Methodology for causal inference, machine learning, and prediction in observational studies and clinical trials.

Dissertation

Sherri’s dissertation research focuses on causal inference for biased sampling designs, specifically case-control studies. Her work with advisor Dr. Mark van der Laan uses the prevalence probability in case-control weights to estimate causal parameters not previously available for case-control studies. The procedure, Case-Control Weighted Targeted Maximum Likelihood Estimation (TMLE), is both efficient and double robust. Case-Control Weighted TMLE is most effectively implemented when used in conjunction with machine learning, such as super learning. The Case-Control Weighted TMLE procedure can also be adapted for specific types of case-control study designs, such as individually matched, frequency matched, nested case-control, and incidence-density. Case-control weighting methodology also has applications in prediction for case-control studies.