{"id":"W4415917403","doi":"10.1038/s41598-025-20032-7","title":"Using item response theory as a methodology to impute categorical missing values","year":2025,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Center for Advancing Translational Sciences; U.S. National Library of Medicine; National Institutes of Health","keywords":"Missing data; Categorical variable; Imputation (statistics); Probabilistic logic; Item response theory; Statistical model; Regression; Binary data","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1591825,0.002206308,0.003621044,0.008980258,0.00176625,0.005002297,0.005806305,0.002953739,0.00920235],"category_scores_gemma":[0.3292478,0.001344669,0.005299388,0.01715548,0.003742596,0.005024129,0.004930283,0.007314717,0.004655192],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002761021,"about_ca_system_score_gemma":0.005045457,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002040533,"about_ca_topic_score_gemma":0.002464933,"domain_scores_codex":[0.750842,0.207063,0.0116893,0.008947213,0.02025688,0.001201651],"domain_scores_gemma":[0.6879266,0.2174926,0.02074298,0.04310902,0.02977205,0.0009567008],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006342373,0.001029122,0.08147846,0.009625638,0.006929666,0.000449513,0.006912713,0.0256023,0.002725318,0.1514438,0.04088911,0.6722801],"study_design_scores_gemma":[0.0006699149,0.00373359,0.07804273,0.008319308,0.0023002,0.002405308,0.007110016,0.1321566,0.01306854,0.6048644,0.1460114,0.001318046],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005850492,0.0008968239,0.9839213,0.001264643,0.0002830912,0.002133511,0.001921252,0.0006891274,0.003039793],"genre_scores_gemma":[0.1155934,0.001587818,0.860524,0.002282456,0.000272637,0.01398444,0.00362807,0.0003721585,0.001755079],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1591825,"threshold_uncertainty_score":0.8418475,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5962277551925372,"score_gpt":0.5607249096711437,"score_spread":0.03550284552139349,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}