Heterogeneous Choice Treatment Effects on Academic Achievement

In Simple Words

Winning a ticket to a preferred destination only improves academic health if the destination was picked for academic reasons. If a family selects a destination primarily for non-academic features like peer demographics, attending that destination may offer no academic boost or even lead to score drops.

Research question

Evaluating public school choice via randomized lotteries often yields zero average treatment effects, masking critical underlying variation in student academic outcomes. Understanding why subgroup outcomes differ requires linking causal impacts directly to parental choice preferences and trade-offs.

Participants

N = 3,065 human students in randomized marginal lottery priority groups within Charlotte-Mecklenburg Schools, North Carolina (2,591 with complete baseline data).

Study Design

Instrumental variables (IV) estimation using oversubscribed school lottery outcomes as instruments for attending first-choice schools, interacted with estimated parental weights on test scores.

Results

Average treatment effect of attending a first-choice school across all lottery applicants is -0.005 standard deviations. Interacting attendance with test-score weight yields a positive coefficient of 0.090 with p=0.007. Students at the 95th percentile of academic preference gain approximately 0.10 standard deviations in End of Grade test scores, while disadvantaged minority students prioritizing school racial composition experience test score declines.

Takeaway

Use posterior estimates of individual choice parameters as instrumental variable interactions in randomized trial evaluations to uncover hidden treatment heterogeneity.

Read alongside the research

Plain-English glossary

Original explanations, informed by the references below. Examples are illustrations, not data from the studies above. The research text stays unchanged.

Baseline

The starting measurements in a study. Researchers use these to compare what participants were like at the start with what happens later.

ExampleBefore a training programme starts, researchers measure workers’ earnings. That first measurement is the baseline.

GET-IT glossary · Baseline characteristics ↗Read more about baseline →

Related findings

• Academic Grade-Incentivized Curriculum Compliance →Education

  Linking software progress to a real school report card acts like a mandatory gate on a turnstile. Students must complete digital quizzes and modules because their software performance directly impacts their overall grade in an established class like computer science.

• Academic Remediation Inefficacy in Postsecondary Persistence →Education

  Standard developmental remediation is like forcing aspiring drivers to complete months of classroom parking simulations before letting them drive on real roads. Because the simulations take time and money without moving drivers closer to their destination, most drivers become discouraged and quit driving before ever reaching the main highway.

• Administrative Algorithmic Dropout Targeting →Education

  Instead of waiting for students to start failing classes, administrators analyze prior middle school report cards and standardized admission test scores before the academic year begins to calculate an individual risk score. This functions like a health screening questionnaire at a hospital lobby that flags patients with elevated blood pressure before an acute cardiac event takes place.

• Advisor-Financial Role Separation →Education

  Separating counseling from financial auditing is like having an attorney represent a client in court while a separate bank manager evaluates the client's loan application. Because the attorney does not decide on loan approvals, the client can openly share personal struggles with their lawyer without fearing financial penalty.