Testing for sample selection in the Milwaukee school choice experiment

Dan D. Goldhaber, Dominic J. Brewer, Eric R. Eide, Daniel I. Rees

Research output: Contribution to journalArticle

Abstract

We examine data collected from the Milwaukee Parental Choice Program to determine whether students with unobserved characteristics correlated with achievement are more likely to apply to the voucher program. We first estimate probit models for application to the choice program, and then math and reading achievement models. By comparing students randomly rejected from the program with students who did not apply, we can test whether applicants and non-applicants have unobservable characteristics that are correlated both with the choice of school sector and with the included explanatory variables. We do not find strong evidence that students who apply to participate in the Milwaukee choice program have unmeasured characteristics, such as motivation, which systematically differ from non-applicants [JEL C12, I21].

Original languageEnglish (US)
Pages (from-to)259-267
Number of pages9
JournalEconomics of Education Review
Volume18
Issue number2
StatePublished - Apr 1999

Fingerprint

school choice
experiment
student
applicant
Sample selection
Choice experiment
School choice
Testing
school
evidence

Keywords

  • Milwaukee
  • School choice
  • Selection
  • Vouchers

ASJC Scopus subject areas

  • Economics and Econometrics
  • Education

Cite this

Testing for sample selection in the Milwaukee school choice experiment. / Goldhaber, Dan D.; Brewer, Dominic J.; Eide, Eric R.; Rees, Daniel I.

In: Economics of Education Review, Vol. 18, No. 2, 04.1999, p. 259-267.

Research output: Contribution to journalArticle

Goldhaber, DD, Brewer, DJ, Eide, ER & Rees, DI 1999, 'Testing for sample selection in the Milwaukee school choice experiment', Economics of Education Review, vol. 18, no. 2, pp. 259-267.
Goldhaber, Dan D. ; Brewer, Dominic J. ; Eide, Eric R. ; Rees, Daniel I. / Testing for sample selection in the Milwaukee school choice experiment. In: Economics of Education Review. 1999 ; Vol. 18, No. 2. pp. 259-267.
@article{1b4392b4cc7c4cb0aed61750da399e8b,
title = "Testing for sample selection in the Milwaukee school choice experiment",
abstract = "We examine data collected from the Milwaukee Parental Choice Program to determine whether students with unobserved characteristics correlated with achievement are more likely to apply to the voucher program. We first estimate probit models for application to the choice program, and then math and reading achievement models. By comparing students randomly rejected from the program with students who did not apply, we can test whether applicants and non-applicants have unobservable characteristics that are correlated both with the choice of school sector and with the included explanatory variables. We do not find strong evidence that students who apply to participate in the Milwaukee choice program have unmeasured characteristics, such as motivation, which systematically differ from non-applicants [JEL C12, I21].",
keywords = "Milwaukee, School choice, Selection, Vouchers",
author = "Goldhaber, {Dan D.} and Brewer, {Dominic J.} and Eide, {Eric R.} and Rees, {Daniel I.}",
year = "1999",
month = "4",
language = "English (US)",
volume = "18",
pages = "259--267",
journal = "Economics of Education Review",
issn = "0272-7757",
publisher = "Elsevier Limited",
number = "2",

}

TY - JOUR

T1 - Testing for sample selection in the Milwaukee school choice experiment

AU - Goldhaber, Dan D.

AU - Brewer, Dominic J.

AU - Eide, Eric R.

AU - Rees, Daniel I.

PY - 1999/4

Y1 - 1999/4

N2 - We examine data collected from the Milwaukee Parental Choice Program to determine whether students with unobserved characteristics correlated with achievement are more likely to apply to the voucher program. We first estimate probit models for application to the choice program, and then math and reading achievement models. By comparing students randomly rejected from the program with students who did not apply, we can test whether applicants and non-applicants have unobservable characteristics that are correlated both with the choice of school sector and with the included explanatory variables. We do not find strong evidence that students who apply to participate in the Milwaukee choice program have unmeasured characteristics, such as motivation, which systematically differ from non-applicants [JEL C12, I21].

AB - We examine data collected from the Milwaukee Parental Choice Program to determine whether students with unobserved characteristics correlated with achievement are more likely to apply to the voucher program. We first estimate probit models for application to the choice program, and then math and reading achievement models. By comparing students randomly rejected from the program with students who did not apply, we can test whether applicants and non-applicants have unobservable characteristics that are correlated both with the choice of school sector and with the included explanatory variables. We do not find strong evidence that students who apply to participate in the Milwaukee choice program have unmeasured characteristics, such as motivation, which systematically differ from non-applicants [JEL C12, I21].

KW - Milwaukee

KW - School choice

KW - Selection

KW - Vouchers

UR - http://www.scopus.com/inward/record.url?scp=0005556428&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0005556428&partnerID=8YFLogxK

M3 - Article

VL - 18

SP - 259

EP - 267

JO - Economics of Education Review

JF - Economics of Education Review

SN - 0272-7757

IS - 2

ER -