Two Canadian researchers conducted a new analysis of data from Project STAR, Tennessee’s highly influential class size experiment. Their study has been published by the National Bureau of Economic Research (NBER).
They are the first to analyze the Project STAR data, while accounting for the contamination of the experimental research protocol.
By grade three over 50% of the subjects who participated in kindergarten left the STAR sample and approximately 10% of the remaining subjects switch class type annually. To the best of our knowledge, an examination of the data as the result of a sequence of contaminated treatment interventions has not been explored.
The researchers concluded,
We find benefits from small class attendance initially in all cognitive subject areas in kindergarten and the first grade. We do not find any statistically significant dynamic benefits from continuous treatment versus never attending small classes in either the second or third grade.
