logo   Edinburgh School of Economics


Motherhood Timing and the Child Penalty: Bounding the Returns to Delay (Joint with Aniko Biro and Andreas Steinhauer), May 2019

We use administrative data from Austria to analyze labor market returns to delaying motherhood. We exploit delays due to pregnancy loss to provide bounds on the returns that account for imperfect instruments and selection into the sample for mothers that suffer a loss. Our results suggest small effects of delay on earnings, employment, and firm quality- in contrast with the prior literature. The lower bounds suggest little difference in earnings trajectories around the first birth. This raises the possibility that much of the return may come from delaying the "child penalty" rather than changing how the career responds to children.


A Correction for Regression Discontinuity Designs with Group-Specific Mismeasurement of the Running Variable (Joint with Otavio Bartalotti and Quentin Brummet), Accepted at Journal of Business and Economic Statistics

IZA Working Paper Version, April 2019

When the running variable in a regression discontinuity (RD) design is measured with error, identification of the local average treatment effect of interest will typically fail. While the form of this measurement error varies across applications, in many cases the measurement error structure is heterogeneous across different groups of observations. We develop a novel measurement error correction procedure capable of addressing heterogeneous mismeasurement structures by leveraging auxiliary information. We also provide adjusted asymptotic variance and standard errors that take into consideration the variability introduced by the estimation of nuisance parameters, and honest confidence intervals that account for potential misspecification. Simulations provide evidence that the proposed procedure corrects the bias introduced by heterogeneous measurement error and achieves empirical coverage closer to nominal test size than "naive" alternatives. Two empirical illustrations demonstrate that correcting for measurement error can either reinforce the results of a study or provide a new empirical perspective on the data.

Revisiting the Effects of Unemployment Insurance Extensions on Unemployment: A Measurement Error-Corrected Regression Discontinuity Approach (Joint with Otavio Bartalotti and Quentin Brummet), American Economic Journal: Economic Policy, Vol 12(2) (2020) .

IZA Working Paper Version, April 2018

This study documents two potential biases in recent analyses of UI benefit extensions using boundary-based identification: bias from using county-level aggregates and bias from across-border policy spillovers. To examine the first bias, the analysis uses a regression discontinuity approach that accounts for measurement error in county-level aggregates. These results suggest much smaller effects than previous studies, casting doubt on the applicability of border-based designs. The analysis then shows substantial spillover effects of UI benefit duration on across-border work patterns, consistent with increased tightness in high-benefit states and providing evidence against a dominant vacancy reduction response to UI extensions.

A Simple Diagnostic to Investigate Instrument Validity and Heterogeneous Effects when using a Single Instrument. Labour Economics, Vol 42 (2016)

Preprint Version, June 2016

Many studies that use instrumental variables are based on a first stage linear in the instrument. Using only linear first stages may miss important information about effect heterogeneity and instrument validity. Analyzing fifteen studies using linear first stages, we find ten with significant nonlinearities. Six of these ten have statistically different second stage estimates. Additional analysis is necessary when results are sensitive to first stage choice. We provide a framework to reconcile these differences by determining those patterns of heterogeneity that are consistent with instrument validity. If these patterns violate economic reasoning, then the validity of the instrument is questioned.

Class-size Reduction Policies and the Quality of Entering Teachers. Labour Economics, Vol 36 (2015)

Preprint Version, June 2015

Class-size reduction (CSR) policies have typically failed to produce large achievement gains. One common explanation is that CSR forces schools to hire low-quality teachers. Prior studies of this hypothesis have been hindered by poor data. Using different data, we find that hiring quality did fall with state-wide CSR. However, this drop was temporary due to attrition by the lowest performers. Furthermore, the drop was similar for schools classified as treated and control for prior evaluations of CSR. Therefore, differences in the quality of incoming teachers cannot explain the estimated performance of CSR. This is consistent with hiring spillovers in connected markets.

How Do Principals Assign Students to Teachers? Finding Evidence in Administrative Data and the Implications for Value-Added. Journal of Policy Analysis and Management, Vol 34(1) (2015). (Joint with Cassandra Guarino, Mark Reckase, & Jeff Wooldridge)

Preprint Version

The federal government’s Race to the Top competition has promoted the adoption of test-based performance measures as a component of teacher evaluations throughout many states, but the validity of these measures has been controversial among researchers and widely contested by teachers’ unions. A key concern is the extent to which nonrandom sorting of students to teachers may bias the results and lead to a misclassification of teachers as high or low performing. In light of this, it is important to assess the extent to which evidence of sorting can be found in the large administrative data sets used for VAM estimation. Using a large longitudinal data set from an anonymous state, we find evidence that a nontrivial amount of sorting exists—particularly sorting based on prior test scores—and that the extent of sorting varies considerably across schools, a fact obscured by the types of aggregate sorting indices developed in prior research. We also find that VAM estimation is sensitive to the presence of nonrandom sorting. There is less agreement across estimation approaches regarding a particular teacher’s rank in the distribution of estimated effectiveness when schools engage in sorting.

What Can We Learn About Effective Mathematics Teaching? A Framework for Estimating Causal Effects using Longitudinal Survey Data. Journal of Research on Educational Effectiveness, Vol 6(2), (2013). (Joint with with Cassandra Guarino, Anna Bargagliotti, and William Mason)

This study investigates the impact of teacher characteristics and instructional strategies on the mathematics achievement of students in kindergarten and first grade and tackles the question of how best to use longitudinal survey data to elicit causal inference in the face of potential threats to validity due to nonrandom assignment to treatment. We develop a step-by-step approach to selecting a modeling and estimation strategy and find that teacher certification and courses in methods of teaching mathematics have a slightly negative effect on student achievement in kindergarten, whereas postgraduate education has a positive effect in first grade. Various teaching modalities, such as working with counting manipulatives, using math worksheets, and completing problems on the chalkboard, have positive effects on achievement in kindergarten, and pedagogical practices relating to explaining problem solving and working on problems from textbooks have positive effects on achievement in first grade. We show that the conclusions drawn depend on the estimation and modeling choices made and that several prior studies of teacher effects using longitudinal survey data likely neglected important features needed to establish causal inference.