{"id":"https://openalex.org/W4297443003","doi":"https://doi.org/10.48550/arxiv.2209.11400","title":"Feature selection in stratification estimators of causal effects: lessons from potential outcomes, causal diagrams, and structural equations","display_name":"Feature selection in stratification estimators of causal effects: lessons from potential outcomes, causal diagrams, and structural equations","publication_year":2022,"publication_date":"2022-09-23","ids":{"openalex":"https://openalex.org/W4297443003","doi":"https://doi.org/10.48550/arxiv.2209.11400"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2209.11400","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.11400","pdf_url":"https://arxiv.org/pdf/2209.11400","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2209.11400","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108809898","display_name":"P. Richard Hahn","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hahn, P. Richard","raw_affiliation_strings":["Arizona State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063644444","display_name":"Andrew Herren","orcid":"https://orcid.org/0000-0003-4109-6611","observed_orcids":["https://orcid.org/0000-0003-4109-6611"]},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Herren, Andrew","raw_affiliation_strings":["Arizona State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I55732556"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10845","display_name":"Advanced Causal Inference Techniques","score":1.0,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10845","display_name":"Advanced Causal Inference Techniques","score":1.0,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10136","display_name":"Statistical Methods and Inference","score":0.0,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/feature-selection","display_name":"feature selection","score":0.7429999709129333},{"id":"https://openalex.org/keywords/average-causal-effect","display_name":"average causal effect","score":0.9020000100135803},{"id":"https://openalex.org/keywords/discrete-covariates","display_name":"discrete covariates","score":0.9649999737739563},{"id":"https://openalex.org/keywords/potential-outcomes","display_name":"potential outcomes","score":0.9089999794960022},{"id":"https://openalex.org/keywords/causal-diagrams","display_name":"causal graphs","score":0.9950000047683716},{"id":"https://openalex.org/keywords/structural-equations","display_name":"structural equations","score":0.7089999914169312},{"id":"https://openalex.org/keywords/additive-error","display_name":"additive error","score":0.5730000138282776},{"id":"https://openalex.org/keywords/causal-effect-estimation","display_name":"causal effect estimation","score":0.5849999785423279}],"concepts":[{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.7286451458930969},{"id":"https://openalex.org/C119043178","wikidata":"https://www.wikidata.org/wiki/Q320723","display_name":"Covariate","level":2,"score":0.7222378253936768},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.6147269606590271},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.6132168769836426},{"id":"https://openalex.org/C192943249","wikidata":"https://www.wikidata.org/wiki/Q1893382","display_name":"Stratification (seeds)","level":5,"score":0.5956035256385803},{"id":"https://openalex.org/C163504300","wikidata":"https://www.wikidata.org/wiki/Q2364925","display_name":"Causal structure","level":2,"score":0.5464011430740356},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.5430397987365723},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.46669939160346985},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.44767582416534424},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4103812575340271},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.35293322801589966},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.35236698389053345},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18116214871406555},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C88548481","wikidata":"https://www.wikidata.org/wiki/Q2397491","display_name":"Seed dormancy","level":4,"score":0.0},{"id":"https://openalex.org/C3527866","wikidata":"https://www.wikidata.org/wiki/Q162267","display_name":"Dormancy","level":3,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C100701293","wikidata":"https://www.wikidata.org/wiki/Q193838","display_name":"Germination","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2209.11400","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.11400","pdf_url":"https://arxiv.org/pdf/2209.11400","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2209.11400","doi":"https://doi.org/10.48550/arxiv.2209.11400","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2209.11400","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2209.11400","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.11400","pdf_url":"https://arxiv.org/pdf/2209.11400","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G5608840136","display_name":"RTG: Data-Oriented Mathematical and Statistical Sciences","funder_award_id":"1502640","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2161504683","https://openalex.org/W4386620154","https://openalex.org/W4389961576","https://openalex.org/W4294555408","https://openalex.org/W4372260129","https://openalex.org/W4378718308","https://openalex.org/W1153243621","https://openalex.org/W4299782962","https://openalex.org/W4386839885","https://openalex.org/W3036459125"],"abstract_inverted_index":{"What":[0],"is":[1],"the":[2,17,25,35],"ideal":[3],"regression":[4],"(if":[5],"any)":[6],"for":[7,24,52],"estimating":[8],"average":[9],"causal":[10,54,59],"effects?":[11],"We":[12],"study":[13],"this":[14],"question":[15],"in":[16],"setting":[18],"of":[19,28],"discrete":[20],"covariates,":[21],"deriving":[22],"expressions":[23],"finite-sample":[26],"variance":[27],"various":[29],"stratification":[30],"estimators.":[31],"This":[32],"approach":[33],"clarifies":[34],"fundamental":[36],"statistical":[37],"phenomena":[38],"underlying":[39],"many":[40],"widely-cited":[41],"results.":[42],"Our":[43],"exposition":[44],"combines":[45],"insights":[46],"from":[47],"three":[48],"distinct":[49],"methodological":[50],"traditions":[51],"studying":[53],"effect":[55],"estimation:":[56],"potential":[57],"outcomes,":[58],"diagrams,":[60],"and":[61],"structural":[62],"models":[63],"with":[64],"additive":[65],"errors.":[66]},"counts_by_year":[],"updated_date":"2026-09-30T09:27:27.532063","created_date":"2025-10-10T00:00:00"}