{"id":"https://openalex.org/W7225179948","doi":"https://doi.org/10.31234/osf.io/gwdyf_v1","title":"The Cost of Naive Imputation to a Derived Estimand: An Exact Law, with the Square as Lead Case","display_name":"The Cost of Naive Imputation to a Derived Estimand: An Exact Law, with the Square as Lead Case","publication_year":2026,"publication_date":"2026-11-03","ids":{"openalex":"https://openalex.org/W7225179948","doi":"https://doi.org/10.31234/osf.io/gwdyf_v1"},"language":"en","primary_location":{"id":"doi:10.31234/osf.io/gwdyf_v1","doi":"https://doi.org/10.31234/osf.io/gwdyf_v1","is_oa":false,"landing_page_url":"https://doi.org/10.31234/osf.io/gwdyf_v1","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5141138373","display_name":"Adam Y. Shavit","orcid":"https://orcid.org/0009-0008-1235-0995","observed_orcids":["https://orcid.org/0009-0008-1235-0995"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Adam Y. Shavit","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0008-1235-0995","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5141138373"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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/T10243","display_name":"Statistical Methods and Bayesian Inference","score":0.9976000189781189,"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/T10243","display_name":"Statistical Methods and Bayesian Inference","score":0.9976000189781189,"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/T10845","display_name":"Advanced Causal Inference Techniques","score":0.0007999999797903001,"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/T14374","display_name":"Statistical Methods in Epidemiology","score":9.999999747378752e-05,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/multiple-imputation","display_name":"multiple imputation","score":0.777999997138977},{"id":"https://openalex.org/keywords/missing-completely-at-random","display_name":"missing completely at random","score":0.8389999866485596},{"id":"https://openalex.org/keywords/attenuation","display_name":"attenuation","score":0.3140000104904175},{"id":"https://openalex.org/keywords/missing-data","display_name":"missing data","score":0.335999995470047},{"id":"https://openalex.org/keywords/regression-coefficients","display_name":"regression coefficients","score":0.3330000042915344}],"concepts":[{"id":"https://openalex.org/C58041806","wikidata":"https://www.wikidata.org/wiki/Q1660484","display_name":"Imputation (statistics)","level":3,"score":0.8263999819755554},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.7943999767303467},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.7455999851226807},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.6922000050544739},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.4553999900817871},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.4189999997615814},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3837999999523163},{"id":"https://openalex.org/C2988709989","wikidata":"https://www.wikidata.org/wiki/Q85784623","display_name":"Mean square","level":2,"score":0.3095000088214874},{"id":"https://openalex.org/C135598885","wikidata":"https://www.wikidata.org/wiki/Q1366302","display_name":"Row","level":2,"score":0.30660000443458557},{"id":"https://openalex.org/C122123141","wikidata":"https://www.wikidata.org/wiki/Q176623","display_name":"Random variable","level":2,"score":0.3018999993801117},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2994999885559082},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.2786000072956085},{"id":"https://openalex.org/C2780092901","wikidata":"https://www.wikidata.org/wiki/Q3433612","display_name":"Correlation coefficient","level":2,"score":0.2770000100135803},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.2694000005722046},{"id":"https://openalex.org/C73782692","wikidata":"https://www.wikidata.org/wiki/Q196372","display_name":"Random error","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.26829999685287476}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.31234/osf.io/gwdyf_v1","doi":"https://doi.org/10.31234/osf.io/gwdyf_v1","is_oa":false,"landing_page_url":"https://doi.org/10.31234/osf.io/gwdyf_v1","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2122610043","https://openalex.org/W7220305240","https://openalex.org/W7095822901","https://openalex.org/W3020592556","https://openalex.org/W7223098969","https://openalex.org/W2157734155","https://openalex.org/W2004874483","https://openalex.org/W2057777484","https://openalex.org/W2258524263","https://openalex.org/W2410377541"],"abstract_inverted_index":{"Multiple":[0],"imputation":[1,20,164,350],"is":[2,46,96,165,177,200,270,320,325],"validated":[3],"for":[4,61,318],"variables;":[5],"applied":[6],"researchers":[7],"report":[8],"functions":[9],"ofthem:":[10],"a":[11,13,15,27,58,82,109,128,132,141,185,212,222,274],"product,":[12],"square,":[14,146],"difference":[16,133],"of":[17,38,42,57,66,134,158,169,215,230],"correlations.":[18,135],"An":[19],"model":[21,366],"fitted":[22],"tothe":[23],"columns":[24],"cannot":[25],"carry":[26],"relationship":[28],"it":[29,374],"does":[30],"not":[31,55,127,271],"contain,":[32],"so":[33,295],"the":[34,43,67,71,94,97,103,113,115,148,156,159,170,198,209,218,225,245,251,263,267,279,304,354,364,368],"filled-in":[35,98,219],"rowsarrive":[36],"stripped":[37],"it.":[39],"The":[40,118,228],"direction":[41],"resulting":[44],"bias":[45,95],"established.":[47],"For":[48,136],"thenonlinear":[49],"terms":[50],"studied":[51],"here":[52],"we":[53,73],"are":[54],"aware":[56],"published":[59],"expression":[60],"its":[62,145,178,287,296],"size":[63,77],"asa":[64],"function":[65],"missing":[68,150,233,264,268],"rate,":[69],"and":[70,126,144,172,191,254,286,322,356,367],"literature":[72],"searched":[74],"reaches":[75],"that":[76,204,278],"bysimulation,":[78],"one":[79,88,193,256],"design":[80,171,190],"at":[81,152,154,290,332,338],"time.":[83],"We":[84],"derive":[85],"it,":[86],"as":[87,131],"law:":[89],"under":[90,162],"missingness":[91],"completelyat":[92],"random":[93,153],"rows'":[99],"failure":[100],"to":[101,175,192,232,237,308,336,353,375],"satisfy":[102],"analysis's":[104],"own":[105],"normalequations,":[106],"converted":[107],"into":[108],"coefficient":[110,206,211],"error":[111],"by":[112],"moments":[114],"analysis":[116],"sees.":[117],"lawreaches":[119],"any":[120],"derived":[121],"term":[122,161,282],"entering":[123],"those":[124],"equations,":[125],"ratio-and-transformestimand":[129],"such":[130],"an":[137,166],"outcome":[138,246],"regressed":[139],"on":[140],"standardnormal":[142],"predictor":[143,149],"with":[147,208,342],"completely":[151],"rate\u03c0,":[155],"attenuation":[157,231,305],"squared":[160,281],"naive":[163],"exact":[167],"rationalfunction":[168],"\u03c0.":[173],"Proportionality":[174],"\u03c0":[176],"first-order":[179,205],"term,":[180],"accurate":[181],"toone":[182],"part":[183,194],"in":[184,187,195,257],"thousand":[186],"our":[188],"baseline":[189],"ten":[196],"where":[197,244],"linearcoefficient":[199],"large.":[201],"One":[202],"minus":[203],"factors,":[207],"squaredlinear":[210],"common":[213],"factor":[214],"every":[216,291],"term:":[217],"rows":[220],"preserve":[221],"squareonly":[223],"through":[224],"linear":[226],"term.":[227],"ratio":[229],"fraction":[234,269],"runs":[235],"from0.570":[236],"1.000":[238,243],"across":[239],"nine":[240],"designs,":[241,259],"reaching":[242],"carries":[247],"no":[248,316,323,360],"linearinformation":[249],"about":[250],"incomplete":[252],"predictor,":[253],"exceeding":[255],"other":[258],"wherethe":[260],"loss":[261],"outruns":[262],"fraction.":[265],"Outrunning":[266],"reversingthe":[272],"coefficient:":[273],"global":[275],"bound":[276],"proves":[277],"completed":[280],"stays":[283],"strictlybetween":[284],"zero":[285],"true":[288,361],"value":[289],"rate":[292],"below":[293],"one,":[294],"sign":[297],"never":[298],"flips.":[299],"Undera":[300],"logistic":[301],"missing-at-random":[302],"mechanism":[303],"reduces":[306],"exactly":[307],"elevenselection":[309],"moments,":[310],"which":[311],"numerical":[312],"integration":[313],"(quadrature)":[314],"evaluates;":[315],"elementaryformula":[317],"them":[319],"derived,":[321],"impossibility":[324],"proved.":[326],"Nominal":[327],"95%":[328],"coverage":[329],"fallsfrom":[330],"0.912":[331],"N":[333,339],"=":[334,340],"50":[335],"0.003":[337],"800":[341],"40%":[343],"missing.":[344],"Of":[345],"four":[346],"strategies":[347],"compared,only":[348],"substantive-model-compatible":[349],"was":[351],"insensitive":[352],"mechanism,":[355],"afitted":[357],"version":[358],"using":[359],"parameters":[362],"\u2014":[363,372],"substantive":[365],"covariate":[369],"modelboth":[370],"estimated":[371],"recovers":[373],"within":[376],"three":[377],"Monte":[378],"Carlo":[379],"standard":[380],"errors.":[381]},"counts_by_year":[],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2026-11-04T00:00:00"}