Post-instrument covariates are often included as controls in instrumental variable (IV) analyses to address a violation of the exclusion restriction. However, we show that such analyses are subject to biases unless strong assumptions hold. Using linear constant-effects models, we present asymptotic bias formulas for three estimators (with and…

Quasi-experiments are common in studies that estimate the effect of instructional interventions on student performance outcomes. In this type of research, the nature of the experimental design, the choice in assessment, the selection of comparison groups, and the statistical methods used to analyze the comparison data dictate the validity of…

Background: The connection between childhood violence exposure and antisocial behavior in adolescence has received much attention and has important implications for understanding and preventing criminal behavior. However, there are a limited number of well-designed prospective studies that can suggest a causal relationship, and little is known…

Compared the involvement of black males and females in delinquency and examined the explanatory value of variables drawn from three traditional theories of delinquency (social control, structural strain, and differential association) for understanding delinquency among blacks. Results show that only two variables, attachment to school and…