Repeated Measure Designs are Superior for (Most) Experimental Survey Research Applications

• In Event: Proposals for and Applications of New Experimental Designs

Brief Overview

We revisit recent evidence on repeated measure designs vs. post-only designs in survey experiments. In a series of experiments (total N = 13,163), we find that repeated measures slightly attenuate treatment effects but offer large gains to precision.

Authors

• Andrew Trexler, Duke University

• Diana Jordan, Duke University

• Trent Ollerenshaw, University of Houston