Peter Peduzzi, PhD

Dr. Peduzzi’s primary research interest involves the design, conduct, and analysis of multi-site randomized clinical trials with a particular focus on pragmatic clinical trials. Recent research has focused on issues related to the design and analysis complex clustered randomized trials with recurrent events in the presence of a semi-competing risk of death. Other research is focused on the design of patient preference clinical trials and hybrid Bayesian-frequentist trial designs.

Specialized Terms: Pragmatic Clinical trials; Patient Preference Clinical Trials; Biostatistics; Aging

A major area of current research focus is on the design and analysis of complex clustered randomized clinical trials with time to event outcomes in the presence of a semi-competing risk of death. In particular, we are investigating the estimation of the cluster design effect for these types of complex designs, which has implications for sample size, interim monitoring and power. Because there are no closed form estimates for the design effect, approaches being considered are centered on variance inflation factors and simulation studies. Recently completed work on the analysis of complex cluster randomized trials has focused on the development of a joint model for recurrent events and a semi-competing risk in the presence of multi-level clustering. Future research in this area will include extensions to different types of recurrent events. Another area of current research activity involves patient preference clinical trial designs. Methods have been developed for binary outcomes and future work will include time to event outcomes. This work is being funded by a PCORI methods grant. Plans are in progress to hold a symposium on the design and analysis of patient preference clinical trials involving methodologists and clinical investigators, e.g., those involved in palliative care and end of life research. Past methods work has been in the area of hybrid Bayesian-frequentist designs. In particular, selection of the effect size for sample size determination for a continuous response in a superiority clinical trial using a hybrid classical and Bayesian procedure.