Variance Estimation for the Regression Imputed Horvitz-Thompson Estimator

Imputation has found widespread use in surveys with missing data but can lead to incorrect inferences, e.g., invalid confidence intervals, unless care is exercised. This paper develops a procedure for valid variance estimation in surveys where regression imputation is used for the missing values. Th...

Full description

Saved in:
Bibliographic Details
Published in:Journal of official statistics 1994-12, Vol.10 (4), p.381
Main Authors: Deville, Jean-Claude, Särndal, Carl-Erik
Format: Article
Language:English
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page
container_issue 4
container_start_page 381
container_title Journal of official statistics
container_volume 10
creator Deville, Jean-Claude
Särndal, Carl-Erik
description Imputation has found widespread use in surveys with missing data but can lead to incorrect inferences, e.g., invalid confidence intervals, unless care is exercised. This paper develops a procedure for valid variance estimation in surveys where regression imputation is used for the missing values. The imputed values are derived from the fit of a multiple regression model, with a multivariate auxiliary variable as predictor. Features of this new procedure are: (i) it is based on single value imputation (as opposed to the computationally more demanding multiple imputation); (ii) the variance estimation is valid for an arbitrary probability sampling design and for an arbitrary response mechanism of the unconfounded type; and (iii) the calculation of the variance estimate can be carried out with the standard formulas programmed in the existing computer packages for survey data.
format article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_1266818759</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2858941601</sourcerecordid><originalsourceid>FETCH-LOGICAL-b499-8c104a2ebb8c415179b262d18f05adad9974ebaa9882cbbbf5710710dc6f06eb3</originalsourceid><addsrcrecordid>eNotjUtLw0AAhBexYKz9DwueF_aVfRylVBsoFCSIt7Kv2BSTjbsbD_56IxYGBuZjZm5ARTEmSDIhb0GFqaKIU_Z-B-5zvmDMNKOkAs2bSb0ZXYC7XPrBlD6OsIsJlnOAr-EjhZz_omaY5hI83Mf03Zcf1J7jMOUFXGsxPYBVZz5z2Fx9DdrnXbvdo8Pxpdk-HZDlWiPlCOaGBmuV46QmUlsqqCeqw7XxxmstebDGaKWos9Z2tSR4kXeiwyJYtgaP_7NTil9zyOV0iXMal8cToUIoomSt2S8L10o6</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1266818759</pqid></control><display><type>article</type><title>Variance Estimation for the Regression Imputed Horvitz-Thompson Estimator</title><source>Publicly Available Content Database</source><source>Social Science Premium Collection (Proquest) (PQ_SDU_P3)</source><source>Sociology Collection</source><source>Sociological Abstracts</source><creator>Deville, Jean-Claude ; Särndal, Carl-Erik</creator><creatorcontrib>Deville, Jean-Claude ; Särndal, Carl-Erik</creatorcontrib><description>Imputation has found widespread use in surveys with missing data but can lead to incorrect inferences, e.g., invalid confidence intervals, unless care is exercised. This paper develops a procedure for valid variance estimation in surveys where regression imputation is used for the missing values. The imputed values are derived from the fit of a multiple regression model, with a multivariate auxiliary variable as predictor. Features of this new procedure are: (i) it is based on single value imputation (as opposed to the computationally more demanding multiple imputation); (ii) the variance estimation is valid for an arbitrary probability sampling design and for an arbitrary response mechanism of the unconfounded type; and (iii) the calculation of the variance estimate can be carried out with the standard formulas programmed in the existing computer packages for survey data.</description><identifier>ISSN: 0282-423X</identifier><identifier>EISSN: 2001-7367</identifier><language>eng</language><publisher>Stockholm: Statistics Sweden (SCB)</publisher><ispartof>Journal of official statistics, 1994-12, Vol.10 (4), p.381</ispartof><rights>Copyright Statistics Sweden (SCB) Dec 1994</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.proquest.com/docview/1266818759?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>314,780,784,21392,21393,25751,27342,33609,33772,34528,37010,43731,44113,44588</link.rule.ids></links><search><creatorcontrib>Deville, Jean-Claude</creatorcontrib><creatorcontrib>Särndal, Carl-Erik</creatorcontrib><title>Variance Estimation for the Regression Imputed Horvitz-Thompson Estimator</title><title>Journal of official statistics</title><description>Imputation has found widespread use in surveys with missing data but can lead to incorrect inferences, e.g., invalid confidence intervals, unless care is exercised. This paper develops a procedure for valid variance estimation in surveys where regression imputation is used for the missing values. The imputed values are derived from the fit of a multiple regression model, with a multivariate auxiliary variable as predictor. Features of this new procedure are: (i) it is based on single value imputation (as opposed to the computationally more demanding multiple imputation); (ii) the variance estimation is valid for an arbitrary probability sampling design and for an arbitrary response mechanism of the unconfounded type; and (iii) the calculation of the variance estimate can be carried out with the standard formulas programmed in the existing computer packages for survey data.</description><issn>0282-423X</issn><issn>2001-7367</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>1994</creationdate><recordtype>article</recordtype><sourceid>ALSLI</sourceid><sourceid>BHHNA</sourceid><sourceid>HEHIP</sourceid><sourceid>M2R</sourceid><sourceid>M2S</sourceid><sourceid>PIMPY</sourceid><recordid>eNotjUtLw0AAhBexYKz9DwueF_aVfRylVBsoFCSIt7Kv2BSTjbsbD_56IxYGBuZjZm5ARTEmSDIhb0GFqaKIU_Z-B-5zvmDMNKOkAs2bSb0ZXYC7XPrBlD6OsIsJlnOAr-EjhZz_omaY5hI83Mf03Zcf1J7jMOUFXGsxPYBVZz5z2Fx9DdrnXbvdo8Pxpdk-HZDlWiPlCOaGBmuV46QmUlsqqCeqw7XxxmstebDGaKWos9Z2tSR4kXeiwyJYtgaP_7NTil9zyOV0iXMal8cToUIoomSt2S8L10o6</recordid><startdate>19941201</startdate><enddate>19941201</enddate><creator>Deville, Jean-Claude</creator><creator>Särndal, Carl-Erik</creator><general>Statistics Sweden (SCB)</general><scope>0-V</scope><scope>3V.</scope><scope>7U4</scope><scope>7XB</scope><scope>88J</scope><scope>8C1</scope><scope>8FE</scope><scope>8FG</scope><scope>8FK</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>ALSLI</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BFMQW</scope><scope>BGLVJ</scope><scope>BHHNA</scope><scope>CCPQU</scope><scope>DWI</scope><scope>DWQXO</scope><scope>FYUFA</scope><scope>GHDGH</scope><scope>GNUQQ</scope><scope>HCIFZ</scope><scope>HEHIP</scope><scope>L6V</scope><scope>M2R</scope><scope>M2S</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope><scope>Q9U</scope><scope>WZK</scope></search><sort><creationdate>19941201</creationdate><title>Variance Estimation for the Regression Imputed Horvitz-Thompson Estimator</title><author>Deville, Jean-Claude ; Särndal, Carl-Erik</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-b499-8c104a2ebb8c415179b262d18f05adad9974ebaa9882cbbbf5710710dc6f06eb3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>1994</creationdate><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Deville, Jean-Claude</creatorcontrib><creatorcontrib>Särndal, Carl-Erik</creatorcontrib><collection>ProQuest Social Sciences Premium Collection【Remote access available】</collection><collection>ProQuest Central (Corporate)</collection><collection>Sociological Abstracts (pre-2017)</collection><collection>ProQuest Central (purchase pre-March 2016)</collection><collection>Social Science Database (Alumni Edition)</collection><collection>Public Health Database (ProQuest Medical &amp; Health Databases)</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>ProQuest Central (Alumni) (purchase pre-March 2016)</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central</collection><collection>Social Science Premium Collection (Proquest) (PQ_SDU_P3)</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Continental Europe Database</collection><collection>Technology Collection</collection><collection>Sociological Abstracts</collection><collection>ProQuest One Community College</collection><collection>Sociological Abstracts</collection><collection>ProQuest Central</collection><collection>Health Research Premium Collection</collection><collection>Health Research Premium Collection (Alumni)</collection><collection>ProQuest Central Student</collection><collection>SciTech Premium Collection (Proquest) (PQ_SDU_P3)</collection><collection>Sociology Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Social Science Database (ProQuest)</collection><collection>Sociology Database</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection><collection>ProQuest Central Basic</collection><collection>Sociological Abstracts (Ovid)</collection><jtitle>Journal of official statistics</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Deville, Jean-Claude</au><au>Särndal, Carl-Erik</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Variance Estimation for the Regression Imputed Horvitz-Thompson Estimator</atitle><jtitle>Journal of official statistics</jtitle><date>1994-12-01</date><risdate>1994</risdate><volume>10</volume><issue>4</issue><spage>381</spage><pages>381-</pages><issn>0282-423X</issn><eissn>2001-7367</eissn><abstract>Imputation has found widespread use in surveys with missing data but can lead to incorrect inferences, e.g., invalid confidence intervals, unless care is exercised. This paper develops a procedure for valid variance estimation in surveys where regression imputation is used for the missing values. The imputed values are derived from the fit of a multiple regression model, with a multivariate auxiliary variable as predictor. Features of this new procedure are: (i) it is based on single value imputation (as opposed to the computationally more demanding multiple imputation); (ii) the variance estimation is valid for an arbitrary probability sampling design and for an arbitrary response mechanism of the unconfounded type; and (iii) the calculation of the variance estimate can be carried out with the standard formulas programmed in the existing computer packages for survey data.</abstract><cop>Stockholm</cop><pub>Statistics Sweden (SCB)</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 0282-423X
ispartof Journal of official statistics, 1994-12, Vol.10 (4), p.381
issn 0282-423X
2001-7367
language eng
recordid cdi_proquest_journals_1266818759
source Publicly Available Content Database; Social Science Premium Collection (Proquest) (PQ_SDU_P3); Sociology Collection; Sociological Abstracts
title Variance Estimation for the Regression Imputed Horvitz-Thompson Estimator
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-14T07%3A44%3A04IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Variance%20Estimation%20for%20the%20Regression%20Imputed%20Horvitz-Thompson%20Estimator&rft.jtitle=Journal%20of%20official%20statistics&rft.au=Deville,%20Jean-Claude&rft.date=1994-12-01&rft.volume=10&rft.issue=4&rft.spage=381&rft.pages=381-&rft.issn=0282-423X&rft.eissn=2001-7367&rft_id=info:doi/&rft_dat=%3Cproquest%3E2858941601%3C/proquest%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-b499-8c104a2ebb8c415179b262d18f05adad9974ebaa9882cbbbf5710710dc6f06eb3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=1266818759&rft_id=info:pmid/&rfr_iscdi=true