Testing with the Testers What can we learn from an ``audit study''? - Journées Louis-André Gérard

Romain Aeberhardt, Denis Fougère, Julien Pouget, Roland Rathelot

Description

Testing with the TestersWhat can we learn from an \audit study"?Journees Louis-Andre Gerard-Varet #8Romain Aeberhardt Denis FougereJulien Pouget Roland RathelotCREST-INSEE15 juin 2009Aeberhardt, Fougere, Pouget and Rathelot () Testing 15 juin 2009 1 / 28Plan1 Introduction2 The data3 Usual statistics { linear, parametric framework4 Conditional logit { non-linear, parametric framework5 Semi-parametric framework (NEW)6 Real interaction with the employer, statistical discriminationAeberhardt, Fougere, Pouget and Rathelot () Testing 15 juin 2009 2 / 28IntroductionPlan1 Introduction2 The data3 Usual statistics { linear, parametric framework4 Conditional logit { non-linear, parametric framework5 Semi-parametric framework (NEW)6 Real interaction with the employer, statistical discriminationAeberhardt, Fougere, Pouget and Rathelot () Testing 15 juin 2009 3 / 28Introduction2 main types of studies to measure discriminationDiscrimination on the labor market arises whenever an employer treatsdi erently, on average, individuals whose productive characteristics areequal but whose non productive characteristics such as gender or racedi er.Methods a la Blinder-Oaxaca: decomposition of a gap between anexplained part and an unexplained part.the unexplained part is not necessarily discrimination.Controlled experiments: \audit studies" / \testing"\C teris paribus ": \testers" are matched to be similarWith 2 \testers" (or more) for each job o er, it ...

Informations

• Publié par: Chiev
• Nombre de lectures: 16
• Langue: English

Extrait

rebedrahA,PregeouFot,`eugeTletoaRhtatdn0091uin2g15jstin

15 juin 2009

CREST-INSEE

RomainAeberhardtDenisFouge`re Julien Pouget Roland Rathelot

Testing with the Testers What can we learn from an “audit study”? Journe´esLouis-Andr´eG´erard-Varet#8

82/

15juting092/in20

1

Introduction

The data

2

82

Plan

Semi-parametric framework (NEW)

5

Real interaction with the employer, statistical discrimination

6

Usual statistics – linear, parametric framework

3

Conditional logit – non-linear, parametric framework

4

dtarrhbeAeTeslotatheandRgute,eoP`greF,uo

la n Pn Itnorudtcoi tdF,hrrare,euo`gAebe

5

Conditional logit – non-linear, parametric framework

6

Semi-parametric framework (NEW)

Real interaction with the employer, statistical discrimination

20093/28

Introduction

1

2

The data

3

Usual statistics – linear, parametric framework

4

Ttitse51gnniujugPoanetatdRlohe

e,Pog`erandRugetebhreAF,uoratdtingTeslotathe82

Discrimination on the labor market arises whenever an employertreats differently, on average, individuals whoseproductive characteristics are equalbut whose non productive characteristics such as gender or race differ. Methodsla`aBlinder-Oaxaca of a gap between an: decomposition explained part and an unexplained part. the unexplained part is not necessarily discrimination. Controlled experiments:“audit studies”/ “testi ” ng “Cæteris paribus are matched to be similar”: “testers” With 2 “testers” (or more) for each job offer, it is possible to control for unobserved heterogeneity at the firm level.

90/4ni0251uj ofstypesaint on 2m cuitrtdonI ontiriscnamiusaeidereidumots

haert,rdebATestotthelndRaegatP,uoe`eroFgu

Discrimination on the labor market arises whenever an employertreats differently, on average, individuals whoseproductive characteristics are equalbut whose non productive characteristics such as gender or race differ. Methodsa`alBlinder-Oaxaca: decomposition of a gap between an explained part and an unexplained part. the unexplained part is not necessarily discrimination. Controlled experiments:“audit studies”/ “testing” “Cæteris parib are”: “testers” matched to be similar us With 2 “testers” (or more) for each job offer, it is possible to control for unobserved heterogeneity at the firm level.

82/49002niuj51gni tnIudor mircsidenoitani2 n am tcoi eposniytdiesfstuasurtome

utst?”yd“ nam iduaPaofr’gexa–Elemppxremine(s0230e)t rontI C noitcud tubirtnoofthionser–Wepapnaewahctfnorelra uoegerP,gue`,toFTeelotRathtandrdhaerebA2niu5900nitsj51g8/2

Usual statistics: focus on implicit hypotheses (strong) meaning in terms of discrimination (not so clear) Less usual results: Information carried by the observations in terms of “discrimination” – unobserved heterogeneity at the firm level– Non-linear framework –“Conditional Logit” Semi-parametric set-identificationNEW–only the sign of the effect is identified and not its magnitude Use of the specificity of the data: Testers alternate the role of the potentially discriminated candidate Taking into account tester’s unobserved heterogeneity (Heck ’ man s critique)

epiremtnduti na a“ rfmoaenrnwelatcar–Whpape xe)3002(s’regaPfeoplamEx?–y”udst osnoehtfirtnitub tiuc Co onInodtr /59002ni

Usual statistics: focus on implicit hypotheses (strong) meaning in terms of discrimination (not so clear) Less usual results: Information carried by the observations in terms of “discrimination” – unobserved heterogeneity at the firm level– Non-linear framework –“Conditional Logit” Semi-parametric set-identificationNEW–only the sign of the effect is identified and not its magnitude Use of the specificity of the data: Testers alternate the role of the potentially discriminated candidate Taking into account tester’s unobserved heterogeneity (Heckman s ’ critique)

82Teslot15jutinggute,eoPtaehnaRduoF,re`ghrebtdraAe

juinng155/282009eholRdtaseittTe,erg`ouanetugPoebeAF,tdrahr

Usual statistics: focus on implicit hypotheses (strong) meaning in terms of discrimination (not so clear) Less usual results: Information carried by the observations in terms of “discrimination” – unobserved heterogeneity at the firm level– Non-linear framework –“Conditional Logit” Semi-parametric set-identificationNEW–only the sign of the effect is identified and not its magnitude Use of the specificity of the data: Testers alternate the role of the potentially discriminated candidate Taking into account tester’s unobserved heterogeneity (Heckman’s critique)

trInucod erag(2’splamfPeoemirtn)300epxe omanrnfreleacanw –?xEdu”ytitsa“du ontiburintCo onti tahW–repapehtfos

nalP aatedTh eAebe,erg`ou,FdtarrholehtaRdnateguoPng15juintTesti

Introduction

2

1

3

The data

4

Usual statistics – linear, parametric framework

0290/682

Semi-parametric framework (NEW)

6

Conditional logit – non-linear, parametric framework

5

Real interaction with the employer, statistical discrimination

in2015jutingTesolttaehnaRdgutePoe,erg`ou,FdtarhrebeA7/09

4 black “testers” and 3 white “testers” Students at the University of Milwaukee Black and White testers applied to different sets of jobs The black “testers” went to 200 interviews and the white ones to 150 Low-qualified jobs which require no more than a high-school level No competition between the “testers” Each “tester” played alternatively the role of the ex-offender or of the reference candidate This will allow us to take into account “tester effects and to answer ” Heckman’s critique Evidence of statistical discrimination using the fact that there was not always a real interview with the employer

28 Th ev a D ated pistwDeerkofheMaeg(rhaaP–)oH0230irCaanim ceR l ?dro

Real interaction with the employer, statistical discrimination

6

Semi-parametric framework (NEW)

5

Conditional logit – non-linear, parametric framework

4

Usual statistics – linear, parametric framework

aln ro P kmetrparaamewicfrscitsita,raenil–stalsuU berhardt,Foug`er,eoPgutenaRdtaehtloesTngtiju1502ni/890

Introduction

82

3

The data

2

1

eA