Browsing by Author "Maurel, Arnaud"

Skills are central to many questions in labor economics ranging from the causes of rising wage inequality to understanding how individuals make decisions about their career. However, skills are typically measured incompletely in standard datasets, so an important empirical challenge in labor economics is to develop methods to measure or control for these unobserved variables. This dissertation builds a range of methodologies to deal with unobserved skills in models in labor economics and explores how the evolution of workers' skills has contributed to long-term trends in wage inequality.

Chapter 2 develops an approach to estimating workers’ skills from panel data and examines how changes in skills and occupational sorting patterns have contributed to rising wage inequality in the United States since the 1980s. The methodology uses repeated measurements of individuals’ labor market outcomes over time to reveal their underlying skills. Estimating a model of occupational choice using panel data from the Survey of Income and Program Participation (SIPP), I find that (1) as tasks in high-skill jobs have become increasingly complex, the distribution of workers' ability to perform those tasks has become more dispersed, (2) workers' ability to perform low-skill work tasks has become more homogeneous, and (3) workers have increasingly sorted into occupations by skill level, which has increased wage inequality.

Chapter 3 builds a related panel data methodology that can accommodate a more general class of models in which individuals can have imperfect information about their abilities. In particular, in addition to unobserved heterogeneity known to individuals, the methodology in this chapter also allows for initially unpredictable heterogeneity that may be revealed over time.

Chapter 4 develops a complementary approach to assessing the sensitivity of estimates of causal effects to omitted variable bias. In the canonical example of omitted variable bias, the presence of unobserved ability creates a bias in estimates of the causal effect of education on wages. This chapter provides an approach to quantifying the size of this bias by reasoning about the importance of unobserved ability compared to other included variables. In contrast to existing methods for sensitivity analysis in this setting, the approach also allows the research to explicitly reason about correlation between the omitted variable and observed controls.

This dissertation presents two essays in labor economics. In the first essay, I study employer learning in a labor market with dynamic statistical discrimination on the basis of time-varying worker characteristics such as marital status. In the second essay, I explore the relationship between workplace flexibility and worker and occupation characteristics. These essays provide insights into the information frictions in the labor market and the cost of providing job amenities.

Social networks affect a broad class of economic activities. The three chapters of my dissertation study social networks from two different lines of research. The first line of research examines the formation process of a social network. In Chapter 2, I introduce a new identification strategy and a semiparametric estimator for the formation process of an undirected network with additive agent-specific fixed effects. In Chapter 3, I analyze the formation process of a directed network with a broader type of unobserved heterogeneity. This heterogeneity is modeled as interactive fixed effects. The second line of my research complements the first approach by exploring the influence that network structures have on different economic activities. In Chapter 4, I recover the endogenous and exogenous social effects in a high-dimensional panel data model with an unobserved network structure.

This dissertation is an empirical study of school choice under various perspectives. Chapter 2 looks at school choice from the application perspective. It focuses on assignment mechanisms used by school districts to allocate available seats to students. Chapters 3 and 4 turn to the admission perspective, investigating the consequences of school choice on students' outcomes. Chapter 3 studies the effects on students' academic performance of admission to one type of selective schools, namely elite schools. Chapter 4 explores the mechanisms underlying these effects. The empirical analysis in each chapter of this dissertation is supported by administrative data from Tunisia.

With school choice comes the necessity to devise rules to decide who gets to enroll in a school or academic program when more students express the willingness to attend than the school's capacity allows. Centralized assignment mechanisms based on the deferred acceptance algorithm (DA) are used by school districts around the world to assign students to schools.

Theoretical analyses of the DA consider that students are allowed to list all the alternatives of the choice set in their application rankings. However, in virtually all places where these mechanisms are implemented, students are restricted to list only a small number of choices. As a consequence, students need to take their admission chances into account, and be strategic in their choice.

In Tunisia, high school graduates are assigned to university programs using a sequential variant of the DA. Chapter 2 use data on this Tunisian mechanism to empirically examine the effect of enabling students to update their expectations about their admissions probabilities.

The sequential implementation induces quasi-experimental variation in the information available to students about remaining vacancies, and allows for the identification of students' preferences and expected admission probabilities.

When students cannot revise their expectations, and relative to a benchmark situation in which students are given perfect information about which programs would admit them, their average indirect utility is decreased by the equivalent of a 41km-increase in the distance home-university ---40\% of the median distance traveled by students in the data. While easy to implement, the sequential implementation of the DA procedure reduces this expected utility loss by 67\% in Tunisia. The increase in expected welfare is driven by a decrease in the share of students rejected by all their listed choices. Gains disproportionately accrue to low-ability and low-SES students. Counterfactuals suggest that a better targeting of low-priority students by the information provision would increase welfare gains.

Underlying school choice is the idea that giving students and their family more freedom in their schooling decisions can improve academic outcomes.

Although documented in many papers, the impact of attending a better school on future achievement is unclear and varies greatly depending on the context. Chapter 3 examines the impact of being admitted to a high school with high achieving peers in Tunisia, particularly on post-secondary choices. The admission mechanism creates admission cutoffs that we exploit in a sharp regression discontinuity (RD) design. However, despite the validity of the RD design, sample selection and measurement error induce the standard RDD identification argument to fail, and the naive RD techniques to produce biased estimates. Chapter 3 proposes bounds for the local average and quantile treatment effects. Results suggest that admission to an elite high school increases students' end-of-high-school performance, and the selectivity level of post-secondary programs students in the higher end of the distribution get assigned to.

Chapter 4 investigates one type of mechanisms possibly driving the effect of selective high schools on students' outcomes: the change in educational inputs induced by admission to an elite school. To explore this mechanism, we link the students database to data on schools infrastructures and teachers. Allowing effects of admission to an elite high school to vary across the twelve Tunisian elite high school institutions, we evaluate the link between the magnitude of the treatment effects on students' outcomes, and the intensity with which treatment modifies various dimensions of the school environment. Results suggest that, although average teachers' quality and student monitoring are increased by admission to an elite high school, the higher peer achievement seems to be the main mediator of treatment effects on students' outcomes.

Extremal quantile index is a concept that the quantile index will drift to zero (or one)

as the sample size increases. The three chapters of my dissertation consists of three

applications of this concept in three distinct econometric problems. In Chapter 2, I

use the concept of extremal quantile index to derive new asymptotic properties and

inference method for quantile treatment effect estimators when the quantile index

of interest is close to zero. In Chapter 3, I rely on the concept of extremal quantile

index to achieve identification at infinity of the sample selection models and propose

a new inference method. Last, in Chapter 4, I use the concept of extremal quantile

index to define an asymptotic trimming scheme which can be used to control the

convergence rate of the estimator of the intercept of binary response models.