arXiv subjects

Matthijs Oosterveen

Publications and source records attributed to Matthijs Oosterveen.

4 recordsLinked to original sources

arXiv2025

Policy-relevant causal effect estimation using instrumental variables with interference

Many policy evaluations using instrumental variable (IV) methods include individuals who interact with each other, potentially violating the standard IV assumptions. This paper defines and partially identifies direct and spillover effects with a clear policy-relevant interpretation under relatively mild assumptions on interference. Our framework accommodates both spillovers from the instrument to treatment and from treatment to outcomes and allows for multiple peers. By generalizing monotone treatment response and selection assumptions, we derive informative bounds on policy-relevant effects without restricting the type or direction of interference. The results extend IV estimation to more realistic social contexts, informing program evaluation and treatment scaling when interference is present.

econ.EM↗

arXiv2025

Teacher bias or measurement error?

Subjective teacher evaluations play a key role in shaping students' educational trajectories. Previous studies have shown that students of low socioeconomic status (SES) receive worse subjective evaluations than their high SES peers, even when they score similarly on objective standardized tests. This is often interpreted as evidence of teacher bias. Measurement error in test scores challenges this interpretation. We discuss how both classical and non-classical measurement error in test scores generate a biased coefficient of the conditional SES gap, and consider three empirical strategies to address this bias. Using administrative data from the Netherlands, where secondary school track recommendations are pivotal teacher judgments, we find that measurement error explains 35 to 43% of the conditional SES gap in track recommendations.

econ.EM↗

arXiv2025

The quality of school track assignment decisions by teachers

This paper analyzes the effects of educational tracking and the quality of track assignment decisions. We motivate our analysis using a model of optimal track assignment under uncertainty. This model generates predictions about the average effects of tracking at the margin of the assignment process. In addition, we recognize that the average effects do not measure noise in the assignment process, as they may reflect a mix of both positive and negative tracking effects. To test these ideas, we develop a flexible causal approach that separates, organizes, and partially identifies tracking effects of any sign or form. We apply this approach in the context of a regression discontinuity design in the Netherlands, where teachers issue track recommendations that may be revised based on test score cutoffs, and where in some cases parents can overrule this recommendation. Our results indicate substantial tracking effects: between 40% and 100% of reassigned students are positively or negatively affected by enrolling in a higher track. Most tracking effects are positive, however, with students benefiting from being placed in a higher, more demanding track. While based on the current analysis we cannot reject the hypothesis that teacher assignments are unbiased, this result seems only consistent with a significant degree of noise. We discuss that parental decisions, whether to follow or deviate from teacher recommendations, may help reducing this noise.

econ.GN↗

arXiv2023

Instrument-based estimation of full treatment effects with movers

The effect of the full treatment is a primary parameter of interest in policy evaluation, while often only the effect of a subset of treatment is estimated. We partially identify the local average treatment effect of receiving full treatment (LAFTE) using an instrumental variable that may induce individuals into only a subset of treatment (movers). We show that movers violate the standard exclusion restriction, necessary conditions on the presence of movers are testable, and partial identification holds under a double exclusion restriction. We identify movers in four empirical applications and estimate informative bounds on the LAFTE in three of them.

econ.EM↗