Donna Spiegelman, ScD

Donna Spiegelman was appointed the Susan Dwight Bliss Professor of Biostatistics at the Yale School of Public Health in 2018; she is also Professor of Statistics and Data Science at Yale University.

Dr. Spiegelman founded and directs the Yale Center for Methods in Implementation and Prevention Science (CMIPS) and she also leads the Global Oncology program at Yale Cancer Center.

As one of the few people in the world with a joint doctorate in biostatistics and epidemiology, she can freely speak the languages of both disciplines and switches between these two professional cultures, playing the role of interlocutor for each. She is interested in problems arising in epidemiology that require resolution, at least in part, through biostatistics.

The emerging field of implementation science is among Dr. Spiegelman's major areas of interest. This field examines barriers to the implementation of evidence-based interventions, as well as the factors that facilitate uptake of these tools. She founded CMIPS to develop tools for implementation science as well as to further the field's deployment to improve public health. The Center comprises 4 tenure-track full-time faculty members in biostatistics, social science and health economics; many additional faculty at YSPH and YSM; and PhD students, post-doctoral fellows, and master's degree students.

With colleagues at CMIPS, she studies the design and conduct of implementation studies and pragmatic trials. Topics include stepped-wedge and cluster randomized trials; positive spillover effects; two-stage designs; causal inference for large-scale public health interventions, including causal mediation analysis; correction for biases related to non-adherence and measurement error; and external generalizability; among others. CMIPS also focuses on developing methodsfor learning health care systems.

One of CMIPS' primary goals is to develop new statistical methods for implementation science. One such innovation is the Learn as You Go (LAGO) design, which allows researchers to repeatedly adapt ongoing trials in response to new trial data. Such designs help to prevent “failed trials." They can also optimize combination treatment regimens and inform cost-effective health promotion programs. Other biostatistical methods Dr. Spiegelman has developed relate to a wide range of topics, including meta-analysis, measurement error and misclassification, gene-environment and other interactions, smoothing, study design, and population-attributable risk.

Before coming to Yale, she served as professor, mentor, and expert statistician at the Harvard T.H. Chan School of Public Health for nearly 30 years.