Adaptive Experimental Design Using the Propensity Score

Many social experiments are run in multiple waves or replicate earlier social experiments. In principle, the sampling design can be modified in later stages or replications to allow for more efficient estimation of causal effects. We consider the design of a two-stage experiment for estimating an av...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of business & economic statistics Jg. 29; H. 1; S. 96 - 108
Hauptverfasser: Hahn, Jinyong, Hirano, Keisuke, Karlan, Dean
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Alexandria Taylor & Francis 01.01.2011
American Statistical Association
Taylor & Francis Ltd
Schlagworte:
ISSN:0735-0015, 1537-2707
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Many social experiments are run in multiple waves or replicate earlier social experiments. In principle, the sampling design can be modified in later stages or replications to allow for more efficient estimation of causal effects. We consider the design of a two-stage experiment for estimating an average treatment effect when covariate information is available for experimental subjects. We use data from the first stage to choose a conditional treatment assignment rule for units in the second stage of the experiment. This amounts to choosing the propensity score, the conditional probability of treatment given covariates. We propose to select the propensity score to minimize the asymptotic variance bound for estimating the average treatment effect. Our procedure can be implemented simply using standard statistical software and has attractive large-sample properties.
AbstractList Many social experiments are run in multiple waves or replicate earlier social experiments. In principle, the sampling design can be modified in later stages or replications to allow for more efficient estimation of causal effects. We consider the design of a two-stage experiment for estimating an average treatment effect when covariate information is available for experimental subjects. We use data from the first stage to choose a conditional treatment assignment rule for units in the second stage of the experiment. This amounts to choosing the propensity score, the conditional probability of treatment given covariates. We propose to select the propensity score to minimize the asymptotic variance bound for estimating the average treatment effect. Our procedure can be implemented simply using standard statistical software and has attractive large-sample properties. [PUBLICATION ABSTRACT]
Many social experiments are run in multiple waves or replicate earlier social experiments. In principle, the sampling design can be modified in later stages or replications to allow for more efficient estimation of causal effects. We consider the design of a two-stage experiment for estimating an average treatment effect when covariate information is available for experimental subjects. We use data from the first stage to choose a conditional treatment assignment rule for units in the second stage of the experiment. This amounts to choosing the propensity score, the conditional probability of treatment given covariates. We propose to select the propensity score to minimize the asymptotic variance bound for estimating the average treatment effect. Our procedure can be implemented simply using standard statistical software and has attractive large-sample properties.
Author Hirano, Keisuke
Hahn, Jinyong
Karlan, Dean
Author_xml – sequence: 1
  givenname: Jinyong
  surname: Hahn
  fullname: Hahn, Jinyong
– sequence: 2
  givenname: Keisuke
  surname: Hirano
  fullname: Hirano, Keisuke
– sequence: 3
  givenname: Dean
  surname: Karlan
  fullname: Karlan, Dean
BackLink http://www.econis.eu/PPNSET?PPN=663669987$$DView this record in ZBW - Deutsche Zentralbibliothek für Wirtschaftswissenschaften
BookMark eNp1kL1PwzAQxS0EEm1hZkJE7Clnp_EHWwXlQ0ICCZgtx3HAVbCD7QL970kJMCBxyw33e-_u3hhtO-8MQgcYphgLfrKsTJwSADEFjineQiNcFiwnDNg2GgEryhwAl7toHOMS-uIlHSE2r1WX7JvJFh-dCfbFuKTa7NxE--Syx2jdU5aeTXYXfGdctGmd3WsfzB7aaVQbzf53n6DHi8XD2VV-c3t5fTa_yfWMiJRXhosZKasa96tLKKjQTU0rWjegBS5qUukCcwIVE4I2hJAZqFrUlBoDlap4MUHHg28X_OvKxCSXfhVcv1JyzGYUGNlARwNktHc2yq7_Q4W1pLSgVAjOeqIcCB18jME0UtukkvUuBWVbiUFuQpSbEOUmRPkVYq87-aP78f5fcTgoljH58IuTkgMwTvr56TC3rvHhRb370NYyqXXrQxOU0_39xX_mn-WKkiw
CitedBy_id crossref_primary_10_1016_j_apgeog_2016_04_003
crossref_primary_10_1073_pnas_2008740118
crossref_primary_10_1287_mnsc_2023_00492
crossref_primary_10_1016_j_jairtraman_2018_07_003
crossref_primary_10_1093_ectj_utac008
crossref_primary_10_1162_rest_a_01089
crossref_primary_10_1177_09622802251327689
crossref_primary_10_1007_s42973_023_00138_1
crossref_primary_10_1162_rest_a_00716
crossref_primary_10_1287_mnsc_2023_03209
crossref_primary_10_1016_j_jeconom_2022_08_010
crossref_primary_10_1007_s00362_014_0581_y
crossref_primary_10_1093_restud_rdac083
crossref_primary_10_3982_QE1323
crossref_primary_10_1093_ectj_utz020
crossref_primary_10_1016_j_socec_2016_05_005
crossref_primary_10_1007_s10683_011_9275_7
crossref_primary_10_1109_TAC_2016_2612946
crossref_primary_10_1016_j_jeconom_2024_105793
crossref_primary_10_1002_wics_1614
Cites_doi 10.1287/mnsc.1050.0504
10.1093/biomet/70.1.41
10.1111/1468-0262.00442
10.1257/aer.98.3.1040
10.2307/2284578
10.1016/0304-4076(86)90038-2
10.2307/2998560
10.2307/2342192
10.2307/2983640
10.1214/ss/1177009939
10.1257/aer.97.5.1774
10.1257/aer.91.2.103
ContentType Journal Article
Copyright 2011 American Statistical Association 2011
2011 American Statistical Association
Copyright American Statistical Association Jan 2011
Copyright_xml – notice: 2011 American Statistical Association 2011
– notice: 2011 American Statistical Association
– notice: Copyright American Statistical Association Jan 2011
DBID AAYXX
CITATION
OQ6
DOI 10.1198/jbes.2009.08161
DatabaseName CrossRef
ECONIS
DatabaseTitle CrossRef
DatabaseTitleList


DeliveryMethod fulltext_linktorsrc
Discipline Economics
Statistics
Mathematics
EISSN 1537-2707
EndPage 108
ExternalDocumentID 2212077431
663669987
10_1198_jbes_2009_08161
25800782
10711499
Genre Research Article
Feature
GroupedDBID -~X
.7F
.QJ
0BK
0R~
29K
2AX
30N
4.4
5GY
7WY
85S
8FL
AAENE
AAGDL
AAHIA
AAIKC
AAJMT
AALDU
AAMIU
AAMNW
AAOAC
AAPUL
AAQRR
AAWIL
ABAWQ
ABBHK
ABCCY
ABFAN
ABFIM
ABJNI
ABKVW
ABLIJ
ABLJU
ABPAQ
ABPEM
ABQDR
ABTAI
ABXSQ
ABXUL
ABXYU
ABYRZ
ABYWD
ABYYQ
ACDIW
ACGFO
ACGFS
ACHJO
ACHQT
ACMTB
ACNCT
ACTCW
ACTIO
ACTMH
ACUHF
ACVFL
ACXJH
ADCVX
ADGDI
ADGTB
ADMHG
ADODI
ADULT
AEISY
AELLO
AENEX
AEOZL
AEPSL
AEUPB
AEYOC
AFFNX
AFRVT
AFVYC
AGCQS
AGDLA
AGLNM
AGMYJ
AHAJD
AHDZW
AIHAF
AIJEM
AIYEW
AKBRZ
AKBVH
AKOOK
ALMA_UNASSIGNED_HOLDINGS
ALQZU
ALRMG
APTMU
AQRUH
AQTUD
ASMEE
AVBZW
AWYRJ
BKOMP
BLEHA
CBXGM
CCCUG
CHNMF
CS3
D-I
D0L
DGEBU
DKSSO
DQDLB
DSRWC
DU5
EBS
EBU
ECEWR
EJD
E~A
E~B
F5P
GTTXZ
H13
HQ6
HZ~
H~P
IPNFZ
IPSME
J.P
JAA
JAAYA
JBMMH
JBU
JBZCM
JENOY
JHFFW
JKQEH
JLEZI
JLXEF
JMS
JPL
JPPEU
JST
K60
K6~
KYCEM
M4Z
MS~
NA5
NY~
O9-
P2P
RIG
RNANH
ROSJB
RTWRZ
S-T
SA0
SJN
SNACF
TASJS
TBQAZ
TDBHL
TEJ
TFL
TFT
TFW
TN5
TOXWX
TTHFI
TUROJ
U5U
UT5
UU3
WZA
YK4
YQT
ZCA
ZGOLN
~S~
ADYSH
AFSUE
ALIPV
AMPGV
07G
1OL
3R3
8FI
8FJ
8G5
8H~
8R4
8R5
AAIKQ
AAKBW
AAYXX
ABUWG
ACAGQ
ACGEE
ADBBV
ADXHL
AEUMN
AFFHD
AFFVI
AFKRA
AGLEN
AGROQ
AHMOU
AHQJS
AKVCP
ALCKM
AMATQ
AMEWO
AMXXU
AQUVI
AZQEC
BCCOT
BENPR
BEZIV
BPHCQ
BPLKW
BVXVI
C06
CCPQU
CITATION
CRFIH
DMQIW
DWIFK
DWQXO
EOH
FEDTE
FRNLG
FYUFA
GIFXF
GNUQQ
GROUPED_ABI_INFORM_RESEARCH
GUQSH
HECYW
HF~
HGD
HVGLF
H~9
IVXBP
LJTGL
LPU
M0C
M0T
M2O
MVM
NUSFT
PADUT
PHGZM
PHGZT
PJZUB
PPXIY
PQBIZ
PQBZA
PQQKQ
PROAC
Q2X
QCRFL
RNS
S0X
TAQ
TFMCV
UB9
UKHRP
YYP
ZY4
ABTAH
OQ6
YCJ
ID FETCH-LOGICAL-c429t-be89425bd101550369cfd6b6df0c913d2bc31820b7996f22240ad9d66ee0bab83
IEDL.DBID TFW
ISICitedReferencesCount 31
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000286407200009&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0735-0015
IngestDate Mon Jul 14 10:16:13 EDT 2025
Sat Mar 08 16:09:00 EST 2025
Tue Nov 18 22:26:30 EST 2025
Sat Nov 29 08:20:44 EST 2025
Thu May 29 08:44:35 EDT 2025
Mon Oct 20 23:44:40 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 1
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c429t-be89425bd101550369cfd6b6df0c913d2bc31820b7996f22240ad9d66ee0bab83
Notes SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 14
PQID 817460728
PQPubID 3244
PageCount 13
ParticipantIDs crossref_citationtrail_10_1198_jbes_2009_08161
proquest_journals_817460728
informaworld_taylorfrancis_310_1198_jbes_2009_08161
crossref_primary_10_1198_jbes_2009_08161
econis_primary_663669987
jstor_primary_25800782
PublicationCentury 2000
PublicationDate 1/1/2011
20110101
2011-01-00
2011
PublicationDateYYYYMMDD 2011-01-01
PublicationDate_xml – month: 01
  year: 2011
  text: 1/1/2011
  day: 01
PublicationDecade 2010
PublicationPlace Alexandria
PublicationPlace_xml – name: Alexandria
PublicationTitle Journal of business & economic statistics
PublicationYear 2011
Publisher Taylor & Francis
American Statistical Association
Taylor & Francis Ltd
Publisher_xml – name: Taylor & Francis
– name: American Statistical Association
– name: Taylor & Francis Ltd
References p_16
Sukhatme P. V. (p_17) 1935; 2
p_2
p_1
p_13
p_6
p_14
p_15
p_8
p_7
p_10
p_9
References_xml – ident: p_15
  doi: 10.1287/mnsc.1050.0504
– ident: p_14
  doi: 10.1093/biomet/70.1.41
– ident: p_7
  doi: 10.1111/1468-0262.00442
– ident: p_9
  doi: 10.1257/aer.98.3.1040
– ident: p_16
  doi: 10.2307/2284578
– ident: p_2
  doi: 10.1016/0304-4076(86)90038-2
– ident: p_6
  doi: 10.2307/2998560
– ident: p_13
  doi: 10.2307/2342192
– volume: 2
  start-page: 253
  year: 1935
  ident: p_17
  publication-title: Journal of the Royal Statistical Society
  doi: 10.2307/2983640
– ident: p_1
  doi: 10.1214/ss/1177009939
– ident: p_8
  doi: 10.1257/aer.97.5.1774
– ident: p_10
  doi: 10.1257/aer.91.2.103
SSID ssj0000856
Score 2.2828493
Snippet Many social experiments are run in multiple waves or replicate earlier social experiments. In principle, the sampling design can be modified in later stages or...
SourceID proquest
econis
crossref
jstor
informaworld
SourceType Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 96
SubjectTerms Asymptotic methods
Conditional probabilities
Design efficiency
Design of experiments
Economic statistics
Efficiency bound
Estimating techniques
Estimators
Experiment design
Experimental design
Fundraising
Hunger
Probability
Propensity score
Sample size
Software
Statistical discrepancies
Statistical variance
Studies
Title Adaptive Experimental Design Using the Propensity Score
URI https://www.tandfonline.com/doi/abs/10.1198/jbes.2009.08161
https://www.jstor.org/stable/25800782
http://www.econis.eu/PPNSET?PPN=663669987
https://www.proquest.com/docview/817460728
Volume 29
WOSCitedRecordID wos000286407200009&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAWR
  databaseName: Taylor and Francis Online Journals
  customDbUrl:
  eissn: 1537-2707
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000856
  issn: 0735-0015
  databaseCode: TFW
  dateStart: 19830101
  isFulltext: true
  titleUrlDefault: https://www.tandfonline.com
  providerName: Taylor & Francis
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1JS8NAFH6UUlAPLlWxbuTgwUs0i5m8wVNRiwctBSt6C5kNFIliq7_feZPFuvSikEMCM0mYefnmfcPL9wEccIuMIk9T32J_4ttz43OuAwuGKNNIWjhUzrXkKh0O8f6ej1pwWv8LQ2WVxKFNKRThsJo-7lxUDiQcjx-FnlRKkxg66mNzeirnGw_uPlEYnXOrjeDEp8SgkvX5pf-XFalDNPRh8k24tC5W_AHYbhUarPzr_VdhuUo-vX4ZLWvQ0kUXFup_kyddWLpuVFzt1SJloqWQ8zqkfZW_EDZ6FzOmAN65qwDxXOWBZ_t6I9rdL6jSw7shicwNuB1cjM8u_cp1wZd2bZr6QiO3H7JQoaMvMePSKCaYMoHkYawiIWNSfReppUomopQgV1wxpnUgcoHxJrSL50JvgYc6lIHJE42BOMEwEAyVCSUKwyKlkPfgqB75TFaS5OSM8ZQ5asIxo6Eip0yeuaHqwWHT4aVU45jfdKucyqahza0Ys-wy7UE8O7nZ1O2NmNLIJIvn3nDTxUBzvyhBl2D1YKcOiqwCgEmGlumxII1w-08P24HFcvOajl1oT1_f9B505Lud9dd9F-kfQ9X9kA
linkProvider Taylor & Francis
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LS8NAEB5EBfXgu7Q-c_DgJZqH3cyCF9GWirUIVvS2ZF-gSC22-vvd2ST1fVHIIYHNhuzOfjvfMPsNwB53yCjzLAsd9jdDd29Dzk3kwBBVligHh9pXLelmvR7e3fGrKTiuzsJQWiVxaFsIRXispsVNwehihXM8fJBmVEpNYkzcZ4bq0hH16rdv33EYfe1WZ8PNkFyDUtjnhw4-7UmzRETvR1-kS6t0xW-Q7feh9tL__mAZFkv_MzgpDGYFpsxgFeaq48mjVVi4nAi5uqd5ckYLLec1yE50PiR4DFof6gIEZz4JJPDJB4F7N7iiAP-Akj2Ca1LJXIebdqt_2gnLwguhctvTOJQGuVvLUseewaSMK6uZZNpGisepTqRKSfhdZo4t2YS8glxzzZgxkcwlpjWYHjwNTB0CNLGKbN40GMkjjCPJUNtYobQs0Rp5Aw6qoReqVCWn4hiPwrMTjoKGioplcuGHqgH7kxeGhSDH703rxVxOGjr3ijFHMLMGpB9nV4x9eMQWtUxE-muHNW8Ek_6SJnofqwGblVWIEgNGAh3ZY1GW4MafPrYLc53-ZVd0z3sXmzBfxLLp2oLp8fOL2YZZ9eos4HnHm_0bLOYBwg
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LS8QwEB5ExcfBt7g-e_DgpdqHTSd4WtRFcV0WVPQWmhcosi7u6u83k7br-6LQQwtJSpLJl_nC5BuAXe6QURZ5Hjrsz0L3bkPOTeTAEFWeKAeH2mctaeedDt7d8e4YHNV3YSiskji0LYUiPFbT4u5rWy5wjgcP0gwqpUmMifpMOKc5I5O-bt2-wzD61K3OhLOQPINK1-eHBj5tSZPEQ-8HX5RL62jFb4jtt6HW_L86sABzlfcZNEtzWYQx01uC6fpy8mAJZi9HMq7ua4Zc0VLJeRnypi76BI7B6YesAMGJDwEJfOhB4OoGXTre71GoR3BFGpkrcNM6vT4-C6u0C6Fym9MwlAa5W8lSx56_pIwrq5lk2kaKx6lOpEpJ9l3mjivZhHyCQnPNmDGRLCSmqzDee-qZNQjQxCqyRWYwkocYR5KhtrFCaVmiNfIG7NcjL1SlSU6pMR6F5yYcBQ0Vpcrkwg9VA_ZGFfqlHMfvRdfKqRwVdM4VY45e5g1IP06uGPrDEVtmMhHprw2uehsYtZdk6D2sBmzURiEqBBgIdFSPRXmC63_62Q5MdU9aon3eudiAmfIgm55NGB8-v5gtmFSvzgCet73RvwEspAB0
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Adaptive+experimental+design+using+the+propensity+score&rft.jtitle=Journal+of+business+%26+economic+statistics&rft.au=Hahn%2C+Jinyong&rft.au=Hirano%2C+Keisuke&rft.au=Karlan%2C+Dean&rft.date=2011&rft.pub=American+Statistical+Association&rft.issn=0735-0015&rft.volume=29&rft.issue=1&rft.spage=96&rft.epage=108&rft_id=info:doi/10.1198%2Fjbes.2009.08161&rft.externalDocID=663669987
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0735-0015&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0735-0015&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0735-0015&client=summon