Use prospective longitudinal designs with propensity score equating on comprehensive baseline covariates to estimate causal effects of early grade retention¶

Strategy · All strategies
Evidence · 2 claims (1 for, 1 mixed) · 1 study (1 causal), q3 · 1 of 1 report an effect size · 2 claims rest on one study

Description¶

The article recommends estimating retention effects with prospective studies that measure a comprehensive set of confounders before the retention decision, then equate retained and promoted groups via propensity scores. Here, 65 grade-1 covariates spanning child, family, school, and home-school levels were used, and the authors note the procedure "as mimicking the randomized experiment, achieving balance between the groups". Extensive tracking and multiple imputation addressed attrition and missing outcomes.

Design Implications¶

Context¶

Requirements¶

• Covariates must be assessed before retention occurs and cover variables associated with both retention and the outcome
• Intensive participant tracking procedures to minimize differential attrition over long follow-ups

Constraints¶

• Unmeasured covariates could still bias estimates if they predict both treatment and outcome over and above the measured set
• Prospective studies are expensive to conduct because retention most commonly occurs in early elementary grades

Target Learners¶

• academically at-risk elementary students in grades 1-5

Target Learning Goals¶

• estimating causal effects of grade retention on long-term educational attainment such as high school completion

Claims¶

• Uncontrolled estimates of retention effects on dropout are larger than propensity-adjusted estimates, suggesting confounding inflates naive associations [+M]
• Retention in grades 1-5 increases the odds of dropping out of high school rather than graduating, above propensity to be retained [~M]

Related Strategies¶

Examples¶

-

Key Sources¶

• Hughes, J. N., West, S. G., Kim, H., & Bauer, S. S. (2018). Effect of Early Grade Retention on School Completion: A Prospective Study. Journal of Educational Psychology, 110(7), 974-991. https://doi.org/10.1037/edu0000243