Evaluators of education interventions are increasingly designing studies to detect impacts much smaller than the 0.20 standard deviations that Cohen (1988) characterized as "small." While the need to detect smaller impacts is based on compelling arguments that such impacts are substantively meaningful, the drive to detect smaller impacts…

The gold standard in making causal inference on program effects is a randomized trial. Most randomization designs in education randomize classrooms or schools rather than individual students. Such "clustered randomization" designs have one principal drawback: They tend to have limited statistical power or precision. This study aims to…

Social statistics may exaggerate the degree of hardship caused by labor market problems. Yet, in many ways social statistics underestimate the degree of hardship caused by extended unemployment, underemployment, and low wages. Therefore, new measures are needed to reassess long-term and cyclical labor market developments, the changing status of…

This presentation is an informal discussion of a questionnaire context effect which led to an erroneous conclusion in analysis of data from the Monitoring the Future project; an annual survey of high school seniors that has occurred since 1975, and that focuses heavily on their drug use and attitudes about drugs. In 1980, the researchers reported…