Loading…
Correlation and efficiency of propensity score-based estimators for average causal effects
Propensity score-based estimators are commonly used to estimate causal effects in evaluation research. To reduce bias in observational studies, researchers might be tempted to include many, perhaps correlated, covariates when estimating the propensity score model. Taking into account that the propen...
Saved in:
Published in: | Communications in statistics. Simulation and computation 2017-01, Vol.46 (5), p.3458-3478 |
---|---|
Main Authors: | , |
Format: | Article |
Language: | English |
Subjects: | |
Citations: | Items that this one cites Items that cite this one |
Online Access: | Get full text |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
cited_by | cdi_FETCH-LOGICAL-c460t-e7cf3bec53cb9459fe824692fb0a4e189e85fd234caac00e411aec09dc409e343 |
---|---|
cites | cdi_FETCH-LOGICAL-c460t-e7cf3bec53cb9459fe824692fb0a4e189e85fd234caac00e411aec09dc409e343 |
container_end_page | 3478 |
container_issue | 5 |
container_start_page | 3458 |
container_title | Communications in statistics. Simulation and computation |
container_volume | 46 |
creator | Pingel, Ronnie Waernbaum, Ingeborg |
description | Propensity score-based estimators are commonly used to estimate causal effects in evaluation research. To reduce bias in observational studies, researchers might be tempted to include many, perhaps correlated, covariates when estimating the propensity score model. Taking into account that the propensity score is estimated, this study investigates how the efficiency of matching, inverse probability weighting, and doubly robust estimators change under the case of correlated covariates. Propositions regarding the large sample variances under certain assumptions on the data-generating process are given. The propositions are supplemented by several numerical large sample and finite sample results from a wide range of models. The results show that the covariate correlations may increase or decrease the variances of the estimators. There are several factors that influence how correlation affects the variance of the estimators, including the choice of estimator, the strength of the confounding toward outcome and treatment, and whether a constant or non-constant causal effect is present. |
doi_str_mv | 10.1080/03610918.2015.1094091 |
format | article |
fullrecord | <record><control><sourceid>proquest_swepu</sourceid><recordid>TN_cdi_swepub_primary_oai_DiVA_org_uu_271585</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1903488295</sourcerecordid><originalsourceid>FETCH-LOGICAL-c460t-e7cf3bec53cb9459fe824692fb0a4e189e85fd234caac00e411aec09dc409e343</originalsourceid><addsrcrecordid>eNqNkU1LxDAQhoMouH78BKHg1eqkSdfkpqyfIHhRD17CNDuRSLdZk9Zl_70pqx7F0zDDMy_zzsvYEYdTDgrOQEw5aK5OK-B1HmmZuy024bWoSskl32aTkSlHaJftpfQOAEJJNWGvsxAjtdj70BXYzQtyzltPnV0XwRXLGJbUJd-vi2RDpLLBRBlKvV9gH2IqXIgFflLENyosDgnbUYJsnw7YjsM20eF33WfPN9dPs7vy4fH2fnb5UFo5hb6kc-tEQ7YWttGy1o5UJae6cg2gJK40qdrNKyEtogUgyTmSBT232SYJKfbZyUY3rWg5NGYZ821xbQJ6c-VfLk2Ib2YYTHXOa1VnvPwHvhgM50LDyB9v-PyLjyE7N-9hiF12ZLgGIZWq9EjVG8rGkFIk96vLwYwpmZ-UzJiS-U4p711s9nyXP7nAVYjt3PS4bkN0ETvrkxF_S3wBwyOaoA</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1903488295</pqid></control><display><type>article</type><title>Correlation and efficiency of propensity score-based estimators for average causal effects</title><source>Taylor and Francis Science and Technology Collection</source><creator>Pingel, Ronnie ; Waernbaum, Ingeborg</creator><creatorcontrib>Pingel, Ronnie ; Waernbaum, Ingeborg</creatorcontrib><description>Propensity score-based estimators are commonly used to estimate causal effects in evaluation research. To reduce bias in observational studies, researchers might be tempted to include many, perhaps correlated, covariates when estimating the propensity score model. Taking into account that the propensity score is estimated, this study investigates how the efficiency of matching, inverse probability weighting, and doubly robust estimators change under the case of correlated covariates. Propositions regarding the large sample variances under certain assumptions on the data-generating process are given. The propositions are supplemented by several numerical large sample and finite sample results from a wide range of models. The results show that the covariate correlations may increase or decrease the variances of the estimators. There are several factors that influence how correlation affects the variance of the estimators, including the choice of estimator, the strength of the confounding toward outcome and treatment, and whether a constant or non-constant causal effect is present.</description><identifier>ISSN: 0361-0918</identifier><identifier>ISSN: 1532-4141</identifier><identifier>EISSN: 1532-4141</identifier><identifier>DOI: 10.1080/03610918.2015.1094091</identifier><language>eng</language><publisher>Philadelphia: Taylor & Francis</publisher><subject>62F10 ; 62G05 ; 62G35 ; central nervous system ; Doubly robust ; Estimators ; Inverse probability ; Matching ; Mathematical models ; Observational studies ; Observational study ; Robustness (mathematics) ; Statistics ; Statistik ; Studies</subject><ispartof>Communications in statistics. Simulation and computation, 2017-01, Vol.46 (5), p.3458-3478</ispartof><rights>2017 Taylor & Francis Group, LLC 2017</rights><rights>2017 Taylor & Francis Group, LLC</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c460t-e7cf3bec53cb9459fe824692fb0a4e189e85fd234caac00e411aec09dc409e343</citedby><cites>FETCH-LOGICAL-c460t-e7cf3bec53cb9459fe824692fb0a4e189e85fd234caac00e411aec09dc409e343</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>230,314,780,784,885,27924,27925</link.rule.ids><backlink>$$Uhttps://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-113905$$DView record from Swedish Publication Index$$Hfree_for_read</backlink><backlink>$$Uhttps://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-271585$$DView record from Swedish Publication Index$$Hfree_for_read</backlink></links><search><creatorcontrib>Pingel, Ronnie</creatorcontrib><creatorcontrib>Waernbaum, Ingeborg</creatorcontrib><title>Correlation and efficiency of propensity score-based estimators for average causal effects</title><title>Communications in statistics. Simulation and computation</title><description>Propensity score-based estimators are commonly used to estimate causal effects in evaluation research. To reduce bias in observational studies, researchers might be tempted to include many, perhaps correlated, covariates when estimating the propensity score model. Taking into account that the propensity score is estimated, this study investigates how the efficiency of matching, inverse probability weighting, and doubly robust estimators change under the case of correlated covariates. Propositions regarding the large sample variances under certain assumptions on the data-generating process are given. The propositions are supplemented by several numerical large sample and finite sample results from a wide range of models. The results show that the covariate correlations may increase or decrease the variances of the estimators. There are several factors that influence how correlation affects the variance of the estimators, including the choice of estimator, the strength of the confounding toward outcome and treatment, and whether a constant or non-constant causal effect is present.</description><subject>62F10</subject><subject>62G05</subject><subject>62G35</subject><subject>central nervous system</subject><subject>Doubly robust</subject><subject>Estimators</subject><subject>Inverse probability</subject><subject>Matching</subject><subject>Mathematical models</subject><subject>Observational studies</subject><subject>Observational study</subject><subject>Robustness (mathematics)</subject><subject>Statistics</subject><subject>Statistik</subject><subject>Studies</subject><issn>0361-0918</issn><issn>1532-4141</issn><issn>1532-4141</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2017</creationdate><recordtype>article</recordtype><recordid>eNqNkU1LxDAQhoMouH78BKHg1eqkSdfkpqyfIHhRD17CNDuRSLdZk9Zl_70pqx7F0zDDMy_zzsvYEYdTDgrOQEw5aK5OK-B1HmmZuy024bWoSskl32aTkSlHaJftpfQOAEJJNWGvsxAjtdj70BXYzQtyzltPnV0XwRXLGJbUJd-vi2RDpLLBRBlKvV9gH2IqXIgFflLENyosDgnbUYJsnw7YjsM20eF33WfPN9dPs7vy4fH2fnb5UFo5hb6kc-tEQ7YWttGy1o5UJae6cg2gJK40qdrNKyEtogUgyTmSBT232SYJKfbZyUY3rWg5NGYZ821xbQJ6c-VfLk2Ib2YYTHXOa1VnvPwHvhgM50LDyB9v-PyLjyE7N-9hiF12ZLgGIZWq9EjVG8rGkFIk96vLwYwpmZ-UzJiS-U4p711s9nyXP7nAVYjt3PS4bkN0ETvrkxF_S3wBwyOaoA</recordid><startdate>20170101</startdate><enddate>20170101</enddate><creator>Pingel, Ronnie</creator><creator>Waernbaum, Ingeborg</creator><general>Taylor & Francis</general><general>Taylor & Francis Ltd</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7TB</scope><scope>8FD</scope><scope>FR3</scope><scope>JQ2</scope><scope>KR7</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>ADTPV</scope><scope>AOWAS</scope><scope>D93</scope><scope>DF2</scope></search><sort><creationdate>20170101</creationdate><title>Correlation and efficiency of propensity score-based estimators for average causal effects</title><author>Pingel, Ronnie ; Waernbaum, Ingeborg</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c460t-e7cf3bec53cb9459fe824692fb0a4e189e85fd234caac00e411aec09dc409e343</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2017</creationdate><topic>62F10</topic><topic>62G05</topic><topic>62G35</topic><topic>central nervous system</topic><topic>Doubly robust</topic><topic>Estimators</topic><topic>Inverse probability</topic><topic>Matching</topic><topic>Mathematical models</topic><topic>Observational studies</topic><topic>Observational study</topic><topic>Robustness (mathematics)</topic><topic>Statistics</topic><topic>Statistik</topic><topic>Studies</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Pingel, Ronnie</creatorcontrib><creatorcontrib>Waernbaum, Ingeborg</creatorcontrib><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Mechanical & Transportation Engineering Abstracts</collection><collection>Technology Research Database</collection><collection>Engineering Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Civil Engineering Abstracts</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><collection>SwePub</collection><collection>SwePub Articles</collection><collection>SWEPUB Umeå universitet</collection><collection>SWEPUB Uppsala universitet</collection><jtitle>Communications in statistics. Simulation and computation</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Pingel, Ronnie</au><au>Waernbaum, Ingeborg</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Correlation and efficiency of propensity score-based estimators for average causal effects</atitle><jtitle>Communications in statistics. Simulation and computation</jtitle><date>2017-01-01</date><risdate>2017</risdate><volume>46</volume><issue>5</issue><spage>3458</spage><epage>3478</epage><pages>3458-3478</pages><issn>0361-0918</issn><issn>1532-4141</issn><eissn>1532-4141</eissn><abstract>Propensity score-based estimators are commonly used to estimate causal effects in evaluation research. To reduce bias in observational studies, researchers might be tempted to include many, perhaps correlated, covariates when estimating the propensity score model. Taking into account that the propensity score is estimated, this study investigates how the efficiency of matching, inverse probability weighting, and doubly robust estimators change under the case of correlated covariates. Propositions regarding the large sample variances under certain assumptions on the data-generating process are given. The propositions are supplemented by several numerical large sample and finite sample results from a wide range of models. The results show that the covariate correlations may increase or decrease the variances of the estimators. There are several factors that influence how correlation affects the variance of the estimators, including the choice of estimator, the strength of the confounding toward outcome and treatment, and whether a constant or non-constant causal effect is present.</abstract><cop>Philadelphia</cop><pub>Taylor & Francis</pub><doi>10.1080/03610918.2015.1094091</doi><tpages>21</tpages><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | ISSN: 0361-0918 |
ispartof | Communications in statistics. Simulation and computation, 2017-01, Vol.46 (5), p.3458-3478 |
issn | 0361-0918 1532-4141 1532-4141 |
language | eng |
recordid | cdi_swepub_primary_oai_DiVA_org_uu_271585 |
source | Taylor and Francis Science and Technology Collection |
subjects | 62F10 62G05 62G35 central nervous system Doubly robust Estimators Inverse probability Matching Mathematical models Observational studies Observational study Robustness (mathematics) Statistics Statistik Studies |
title | Correlation and efficiency of propensity score-based estimators for average causal effects |
url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T16%3A26%3A07IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_swepu&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Correlation%20and%20efficiency%20of%20propensity%20score-based%20estimators%20for%20average%20causal%20effects&rft.jtitle=Communications%20in%20statistics.%20Simulation%20and%20computation&rft.au=Pingel,%20Ronnie&rft.date=2017-01-01&rft.volume=46&rft.issue=5&rft.spage=3458&rft.epage=3478&rft.pages=3458-3478&rft.issn=0361-0918&rft.eissn=1532-4141&rft_id=info:doi/10.1080/03610918.2015.1094091&rft_dat=%3Cproquest_swepu%3E1903488295%3C/proquest_swepu%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c460t-e7cf3bec53cb9459fe824692fb0a4e189e85fd234caac00e411aec09dc409e343%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=1903488295&rft_id=info:pmid/&rfr_iscdi=true |