{"id":"W4403601250","doi":"10.1016/j.jad.2024.10.070","title":"Oops, we missed a spot: Comparing data substitution methods for non-random missing survey data in a longitudinal study","year":2024,"lang":"en","type":"article","venue":"Journal of Affective Disorders","topic":"Urban, Neighborhood, and Segregation Studies","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto; Hospital for Sick Children; Holland Bloorview Kids Rehabilitation Hospital; SickKids Foundation","funders":"Canadian Institutes of Health Research; Garry Hurvitz Centre for Brain and Mental Health; Ontario Ministry of Health and Long-Term Care; Ministry of Health, Ontario","keywords":"Missing data; Longitudinal data; Substitution (logic); Statistics; Survey data collection; Psychology; Computer science; Econometrics; Data mining; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":[],"domain":null,"study_design":"observational","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"}],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3167052,0.001714629,0.003430545,0.002343795,0.001709395,0.003574031,0.00620574,0.004283227,0.005316939],"category_scores_gemma":[0.5261263,0.002179165,0.008325867,0.002698028,0.003300503,0.006261554,0.005791498,0.005623288,0.0005916455],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002006501,"about_ca_system_score_gemma":0.004406367,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01301026,"about_ca_topic_score_gemma":0.01068128,"domain_scores_codex":[0.5320427,0.4515113,0.005023554,0.005987178,0.004226165,0.00120904],"domain_scores_gemma":[0.2102008,0.7574483,0.009685295,0.0165131,0.004925175,0.001227307],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0882245,0.003357553,0.2293217,0.008265236,0.07359054,0.0007301757,0.01702973,0.04662044,0.000812089,0.0364539,0.01097376,0.4846205],"study_design_scores_gemma":[0.02217276,0.02169431,0.1209603,0.005666423,0.03419725,0.001112678,0.01444336,0.6859182,0.002127748,0.07677279,0.01386557,0.00106862],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5461136,0.01301546,0.4255578,0.005321378,0.0024165,0.003105447,0.001567244,0.0006524327,0.00225015],"genre_scores_gemma":[0.7846428,0.002219363,0.2032535,0.001682477,0.0003584934,0.004162773,0.0008624376,0.0005642325,0.002253918],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6832948,"threshold_uncertainty_score":0.8426241,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2567685730487015,"score_gpt":0.4830400637844783,"score_spread":0.2262714907357768,"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."}}