This biostatistical research tool set includes a series of guidance documents developed by the Collaboratory Biostatistics and Study Design Core. These documents, which focus on detailed aspects of statistical design for conducting pragmatic clinical trials, provide a synthesis of current developments, discuss possible future directions, and, where appropriate, make recommendations for application to pragmatic clinical research.

• Key Issues in Extracting Usable Data from Electronic Health Records for Pragmatic Clinical Trials
• The Intraclass Correlation Coefficient
• Unequal Cluster Sizes in Cluster-Randomized Clinical Trials
• Pair-Matching vs Stratification in Cluster-Randomized Trials
• Frailty Models in Cluster-Randomized Trials
• Small-Sample Robust Variance Correction for Generalized Estimating Equations for Use in Cluster-Randomized Trials

In 2019, NIH Health Care Systems Research Collaboratory held a comprehensive workshop to explore and discuss statistical issues encountered with embedded pragmatic clinical trials (ePCTs). The Workshop Summary describes panel discussions with the principal investigators and statisticians of NIH Collaboratory Trials and the challenges and solutions encountered during the design and analysis of their trials.

The 4 panel discussions covered the following topics:

• Measurement and Data: Outcomes, Exposures, and Subgroups Based on EHR Data
• To Cluster or Not to Cluster?
• Choosing a Parallel Group or Stepped-Wedge Design
• Unique Complications

This Workshop Summary also provides lessons learned and recommends tools to help others design and analyze future ePCTs. For more on the design and analysis of pragmatic clinical trials, see the tools provided by the Biostatistics and Study Design Core.

The Biostatistics and Study Design Core wishes to thank David M. Murray, PhD, Director, Office of Disease Prevention, National Institutes of Health, for his invaluable input into the creation of the research tools.