Presenter: Sirui Wan
To determine whether scaling decisions might induce fadeout of cognitive impacts in early education interventions, we reanalyze a well-known RCT of an early mathematics intervention which showed substantial fadeout in the two years following the end of the intervention. We examine how various order-preserving transformations of the scale affect the relative mathematics achievement of the control and experimental groups by age. Although fadeout was generally robust, we can eliminate fadeout by treating variation in achievement near the norm for first-graders as important and as unimportant elsewhere. Adopting this perspective would have substantial implications for interpreting the effects of educational interventions.