AUGMENTED MINIMAX LINEAR ESTIMATION
Many statistical estimands can expressed as continuous linear functionals of a conditional expectation function. This includes the average treatment effect under unconfoundedness and generalizations for continuous-valued and personalized treatments. In this paper, we discuss a general approach to es...
Gespeichert in:
| Veröffentlicht in: | The Annals of statistics 2021-12, Vol.49 (6), p.3206-3227 |
|---|---|
| Hauptverfasser: | , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 3227 |
|---|---|
| container_issue | 6 |
| container_start_page | 3206 |
| container_title | The Annals of statistics |
| container_volume | 49 |
| creator | Hirshberg, David A. Wager, Stefan |
| description | Many statistical estimands can expressed as continuous linear functionals of a conditional expectation function. This includes the average treatment effect under unconfoundedness and generalizations for continuous-valued and personalized treatments. In this paper, we discuss a general approach to estimating such quantities: we begin with a simple plug-in estimator based on an estimate of the conditional expectation function, and then correct the plugin estimator by subtracting a minimax linear estimate of its error. We show that our method is semiparametrically efficient under weak conditions and observe promising performance on both real and simulated data. |
| doi_str_mv | 10.1214/21-AOS2080 |
| format | Article |
| fullrecord | <record><control><sourceid>jstor_proqu</sourceid><recordid>TN_cdi_proquest_journals_2618164591</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><jstor_id>27170952</jstor_id><sourcerecordid>27170952</sourcerecordid><originalsourceid>FETCH-LOGICAL-c281t-23ffe50039512a579fe207b5f8aa9c28f53e48b33797e71165f22014eab5bd3</originalsourceid><addsrcrecordid>eNo90M1Lw0AQBfBFFKzVi3eh0JsQnZnNfh1DjTXQJmAieFuSugsWNXW3PfjfG0nx9HjwYwYeY9cId0iY3hMmWVUTaDhhE0KpE22kPGUTAAOJ4DI9ZxcxbgFAmJRP2Dx7Wa7zsskfZuuiLNbZ62xVlHn2PMvrZqhNUZWX7My3H9FdHXPK6se8WTwlq2pZLLJVsiGN-4S4904AcCOQWqGMdwSqE163rRmIF9yluuNcGeUUohSeCDB1bSe6Nz5l8_HqLvTfBxf3dtsfwtfw0JJEjTIVBgd1O6pN6GMMzttdeP9sw49FsH8TWEJ7nGDANyPexn0f_iUpVGAE8V_MWlG3</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2618164591</pqid></control><display><type>article</type><title>AUGMENTED MINIMAX LINEAR ESTIMATION</title><source>Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals</source><source>Project Euclid Complete</source><creator>Hirshberg, David A. ; Wager, Stefan</creator><creatorcontrib>Hirshberg, David A. ; Wager, Stefan</creatorcontrib><description>Many statistical estimands can expressed as continuous linear functionals of a conditional expectation function. This includes the average treatment effect under unconfoundedness and generalizations for continuous-valued and personalized treatments. In this paper, we discuss a general approach to estimating such quantities: we begin with a simple plug-in estimator based on an estimate of the conditional expectation function, and then correct the plugin estimator by subtracting a minimax linear estimate of its error. We show that our method is semiparametrically efficient under weak conditions and observe promising performance on both real and simulated data.</description><identifier>ISSN: 0090-5364</identifier><identifier>EISSN: 2168-8966</identifier><identifier>DOI: 10.1214/21-AOS2080</identifier><language>eng</language><publisher>Hayward: Institute of Mathematical Statistics</publisher><subject>Continuity (mathematics) ; Estimating techniques ; Estimation ; Mathematics ; Minimax technique ; Plugs ; Simulation ; Statistics</subject><ispartof>The Annals of statistics, 2021-12, Vol.49 (6), p.3206-3227</ispartof><rights>Institute of Mathematical Statistics, 2021</rights><rights>Copyright Institute of Mathematical Statistics Dec 2021</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c281t-23ffe50039512a579fe207b5f8aa9c28f53e48b33797e71165f22014eab5bd3</citedby><cites>FETCH-LOGICAL-c281t-23ffe50039512a579fe207b5f8aa9c28f53e48b33797e71165f22014eab5bd3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,776,780,27903,27904</link.rule.ids></links><search><creatorcontrib>Hirshberg, David A.</creatorcontrib><creatorcontrib>Wager, Stefan</creatorcontrib><title>AUGMENTED MINIMAX LINEAR ESTIMATION</title><title>The Annals of statistics</title><description>Many statistical estimands can expressed as continuous linear functionals of a conditional expectation function. This includes the average treatment effect under unconfoundedness and generalizations for continuous-valued and personalized treatments. In this paper, we discuss a general approach to estimating such quantities: we begin with a simple plug-in estimator based on an estimate of the conditional expectation function, and then correct the plugin estimator by subtracting a minimax linear estimate of its error. We show that our method is semiparametrically efficient under weak conditions and observe promising performance on both real and simulated data.</description><subject>Continuity (mathematics)</subject><subject>Estimating techniques</subject><subject>Estimation</subject><subject>Mathematics</subject><subject>Minimax technique</subject><subject>Plugs</subject><subject>Simulation</subject><subject>Statistics</subject><issn>0090-5364</issn><issn>2168-8966</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><recordid>eNo90M1Lw0AQBfBFFKzVi3eh0JsQnZnNfh1DjTXQJmAieFuSugsWNXW3PfjfG0nx9HjwYwYeY9cId0iY3hMmWVUTaDhhE0KpE22kPGUTAAOJ4DI9ZxcxbgFAmJRP2Dx7Wa7zsskfZuuiLNbZ62xVlHn2PMvrZqhNUZWX7My3H9FdHXPK6se8WTwlq2pZLLJVsiGN-4S4904AcCOQWqGMdwSqE163rRmIF9yluuNcGeUUohSeCDB1bSe6Nz5l8_HqLvTfBxf3dtsfwtfw0JJEjTIVBgd1O6pN6GMMzttdeP9sw49FsH8TWEJ7nGDANyPexn0f_iUpVGAE8V_MWlG3</recordid><startdate>20211201</startdate><enddate>20211201</enddate><creator>Hirshberg, David A.</creator><creator>Wager, Stefan</creator><general>Institute of Mathematical Statistics</general><scope>AAYXX</scope><scope>CITATION</scope><scope>JQ2</scope></search><sort><creationdate>20211201</creationdate><title>AUGMENTED MINIMAX LINEAR ESTIMATION</title><author>Hirshberg, David A. ; Wager, Stefan</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c281t-23ffe50039512a579fe207b5f8aa9c28f53e48b33797e71165f22014eab5bd3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Continuity (mathematics)</topic><topic>Estimating techniques</topic><topic>Estimation</topic><topic>Mathematics</topic><topic>Minimax technique</topic><topic>Plugs</topic><topic>Simulation</topic><topic>Statistics</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Hirshberg, David A.</creatorcontrib><creatorcontrib>Wager, Stefan</creatorcontrib><collection>CrossRef</collection><collection>ProQuest Computer Science Collection</collection><jtitle>The Annals of statistics</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Hirshberg, David A.</au><au>Wager, Stefan</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>AUGMENTED MINIMAX LINEAR ESTIMATION</atitle><jtitle>The Annals of statistics</jtitle><date>2021-12-01</date><risdate>2021</risdate><volume>49</volume><issue>6</issue><spage>3206</spage><epage>3227</epage><pages>3206-3227</pages><issn>0090-5364</issn><eissn>2168-8966</eissn><abstract>Many statistical estimands can expressed as continuous linear functionals of a conditional expectation function. This includes the average treatment effect under unconfoundedness and generalizations for continuous-valued and personalized treatments. In this paper, we discuss a general approach to estimating such quantities: we begin with a simple plug-in estimator based on an estimate of the conditional expectation function, and then correct the plugin estimator by subtracting a minimax linear estimate of its error. We show that our method is semiparametrically efficient under weak conditions and observe promising performance on both real and simulated data.</abstract><cop>Hayward</cop><pub>Institute of Mathematical Statistics</pub><doi>10.1214/21-AOS2080</doi><tpages>22</tpages></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0090-5364 |
| ispartof | The Annals of statistics, 2021-12, Vol.49 (6), p.3206-3227 |
| issn | 0090-5364 2168-8966 |
| language | eng |
| recordid | cdi_proquest_journals_2618164591 |
| source | Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals; Project Euclid Complete |
| subjects | Continuity (mathematics) Estimating techniques Estimation Mathematics Minimax technique Plugs Simulation Statistics |
| title | AUGMENTED MINIMAX LINEAR ESTIMATION |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-26T00%3A18%3A05IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-jstor_proqu&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=AUGMENTED%20MINIMAX%20LINEAR%20ESTIMATION&rft.jtitle=The%20Annals%20of%20statistics&rft.au=Hirshberg,%20David%20A.&rft.date=2021-12-01&rft.volume=49&rft.issue=6&rft.spage=3206&rft.epage=3227&rft.pages=3206-3227&rft.issn=0090-5364&rft.eissn=2168-8966&rft_id=info:doi/10.1214/21-AOS2080&rft_dat=%3Cjstor_proqu%3E27170952%3C/jstor_proqu%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2618164591&rft_id=info:pmid/&rft_jstor_id=27170952&rfr_iscdi=true |