Comment on "Examining the effect of counter-narratives about physics on women's physics career intentions"

Abstract

A paper evaluating the effects of lessons intended to encourage high school students to continue physics studies made some important errors. One was to underestimate the width of confidence intervals by failing to use standard cluster randomization analysis. Another was to use a missing-data imputation program that inappropriately assumes that data are missing at random, leading to potential bias in estimating the effect. The last was to omit discussion of how the treatment used was likely to produce substantial social desirability survey response bias, eroding external validity.