Get Updates via Email Get Updates Get our RSS Feed
  Follow Mathematica on Twitter  Share/Save/Bookmark

John DekeJohn Deke
Senior Researcher

John Deke is a senior researcher with more than 10 years of experience in the design and analysis of data from rigorous evaluations based on diverse designs, including random assignment, regression discontinuity, and propensity score matching.

Some recent examples of his work include a clustered randomized controlled trial (RCT) evaluating mandatory random student drug testing, a clustered RCT evaluating four supplemental reading comprehension curricula, and an evaluation of supplemental educational services based on a regression discontinuity design (RDD).

Beyond his work on individual evaluations, Deke has also contributed to the development of evidence standards for the U.S. Department of Education’s What Works Clearinghouse (WWC). Specifically, he has led the development of the attrition standard for RCTs and was instrumental in the development of standards for RDDs. He currently leads the WWC Statistical and Technical Analysis Team, which is responsible for the continued refinement of WWC evidence standards.

 

Deke has led two methodological studies as part of Mathematica’s contract to provide analytic and technical support to the Regional Education Laboratories. The first study examined the statistical precision gains from adjusting for different types of pre-test measures in clustered RCTs in education. The second study examines the potential for control-group contamination in RCTs that rely on within-school, as opposed to between-school, random assignment.

 

Deke holds a Ph.D. in economics from the University of Illinois at Urbana-Champaign.

Less Detail More Detail

Staff Profile


  • Areas of Expertise
  • Key Projects
  • Publications
  • Design and analysis of data from rigorous evaluations based on diverse designs
  • Random assignment, regression discontinuity, and propensity score matching
  • Study of the Potential for Contamination in Random Assignment Evaluations
  • Study of Alternatives to Administering Baseline Tests in School-Level Random Assignment Evaluations
  • What Works Clearinghouse