Evaluating the effects of job training programs on wages through principal stratification

Zhang, Junni L.; Rubin, Donald B.; Mealli, Fabrizia

doi:10.1016/s0731-9053(07)00005-9

Cited by 57 publications

(66 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We follow the approach by Lee (2009) and Zhang et al (2008) who employ monotonicity assumptions that lead to a trimming procedure that tightens the HM bounds. More formally, let the potential values of employment be denoted by S i (0) and S i (1) when i is assigned to control and treatment, respectively.…”

Section: Bounds On Average Treatment Effectsmentioning

confidence: 99%

“…Lee (2009) and Zhang et al (2008) focus on the average treatment effect of a program on wages for individuals who would be employed regardless of treatment status, i.e., the EE stratum. This stratum is the only one for which wages are observed under both treatment arms, and thus fewer assumptions are required to construct bounds for its effects.…”

Section: Bounds On Average Treatment Effectsmentioning

confidence: 99%

“…Both Lee (2009) and Zhang et al (2008) employed this assumption. In the context of JC, Assumption B is plausible because one of the program's stated goals is to increase the employability of participants.…”

Section: Bounds Adding An Individual-level Monotonicity Assumptionmentioning

confidence: 99%

“…1 We focus on estimating bounds on the population of individuals who would be employed regardless of participation in JC, as previously done in Lee (2009) and Zhang et al (2008), among others. The main reason is that wages are non-missing under both treatment arms for this group of individuals, thus requiring fewer assumptions to construct bounds on their effect.…”

Section: Introductionmentioning

confidence: 99%

“…Thus, in the main analysis to be presented below, we consider a sample that excludes this group. Lastly, Assumption B can be falsified by the data, as it gives rise to the following testable implication (Zhang et al, 2008;Imai, 2008): P r(S = 0|T = 0) − P r(S = 0|T = 1) ≥ 0. We employ this testable implication in our empirical analysis below.…”

mentioning

confidence: 99%

See 4 more Smart Citations

Bounds on Average and Quantile Treatment Effects of Job Corps Training on Wages

Blanco¹,

Flores²,

Flores‐Lagunes³

2013

J. Human Resources

View full text Add to dashboard Cite

We assess the effectiveness of Job Corps (JC), the largest job training program targeting disadvantaged youth in the United States, by constructing nonparametric bounds for the average and quantile treatment effects of the program on wages. Our preferred estimates point toward convincing evidence of positive effects of JC on wages both at the mean and throughout the wage distribution. For the different demographic groups analyzed, the statistically significant estimated average effects are bounded between 4.6 and 12 percent, while the quantile treatment effects are bounded between 2.7 and 11.7 percent.

show abstract

Section: Bounds On Average Treatment Effectsmentioning

confidence: 99%

Section: Bounds On Average Treatment Effectsmentioning

confidence: 99%

Section: Bounds Adding An Individual-level Monotonicity Assumptionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

See 3 more Smart Citations

Bounds on Average and Quantile Treatment Effects of Job Corps Training on Wages

Blanco¹,

Flores²,

Flores‐Lagunes³

2013

J. Human Resources

View full text Add to dashboard Cite

show abstract

Sharp IV Bounds on Average Treatment Effects on the Treated and Other Populations Under Endogeneity and Noncompliance

Huber

Lafférs

Mellace

2015

J of Applied Econometrics

View full text Add to dashboard Cite

Summary In the presence of an endogenous binary treatment and a valid binary instrument, causal effects are point identified only for the subpopulation of compliers, given that the treatment is monotone in the instrument. With the exception of the entire population, causal inference for further subpopulations has been widely ignored in econometrics. We invoke treatment monotonicity and/or dominance assumptions to derive sharp bounds on the average treatment effects on the treated, as well as on other groups. Furthermore, we use our methods to assess the educational impact of a school voucher program in Colombia and discuss testable implications of our assumptions. Copyright © 2015 John Wiley & Sons, Ltd.

show abstract

Unobserved selection heterogeneity and the gender wage gap

Machado¹

2017

J of Applied Econometrics

View full text Add to dashboard Cite

Summary Selection correction methods usually make assumptions about selection itself. In the case of gender wage gap estimation, those assumptions are especially tenuous because of high female nonparticipation and because selection could be different in different parts of the labor market. This paper proposes an estimator for the wage gap that allows for arbitrary and unobserved heterogeneity in selection. It applies to the subpopulation of “always employed” women, which is similar to men in labor force characteristics. Using CPS data from 1976 to 2005, I show that the gap has narrowed substantially from a −0.521 to a −0.263 log wage point differential for this population.

show abstract

Evaluating the effects of job training programs on wages through principal stratification

Cited by 57 publications

References 24 publications

Bounds on Average and Quantile Treatment Effects of Job Corps Training on Wages

Bounds on Average and Quantile Treatment Effects of Job Corps Training on Wages

Sharp IV Bounds on Average Treatment Effects on the Treated and Other Populations Under Endogeneity and Noncompliance

Unobserved selection heterogeneity and the gender wage gap

Contact Info

Product

Resources

About