{"id":"W4389265213","doi":"10.1002/jad.12280","title":"Comparing the reliability and validity of youth‐reported checklists and standardized interviews for categorical measurement of emotional and behavioral problems","year":2023,"lang":"en","type":"article","venue":"Journal of Adolescence","topic":"Child and Adolescent Psychosocial and Emotional Development","field":"Psychology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; Hamilton Health Sciences; McMaster Children's Hospital","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care","keywords":"Psychology; Categorical variable; Reliability (semiconductor); Test validity; Psychometrics; Validity; Clinical psychology; Developmental psychology; Applied psychology; Social psychology; Statistics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"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":[0.02221383,0.0003956668,0.0004024125,0.001750655,0.0003917194,0.0008118706,0.0008162332,0.0003862907,0.0005892453],"category_scores_gemma":[0.04999888,0.0004631609,0.0009910361,0.001409003,0.001076975,0.0006227864,0.001081258,0.0005538342,0.0001701117],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002120061,"about_ca_system_score_gemma":0.002519534,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.04956605,"about_ca_topic_score_gemma":0.08218058,"domain_scores_codex":[0.9847889,0.006601233,0.001590163,0.001238516,0.005236866,0.0005443052],"domain_scores_gemma":[0.9527462,0.01881263,0.01062933,0.003148516,0.01364403,0.001019307],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002737913,0.00006918699,0.9770518,0.0001183253,0.0004499614,0.00001681037,0.002291937,0.0003680335,0.0005432091,0.0001261804,0.000448919,0.01824185],"study_design_scores_gemma":[0.00003295107,0.0001920345,0.9975893,0.00006035965,0.00007642058,0.0000221131,0.0005648934,0.0007532996,0.0001928343,0.00004972915,0.0004559149,0.00001011174],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9944646,0.0004570622,0.002799075,0.00007844939,0.00004888182,0.0002570506,0.0005930114,0.00002326362,0.001278653],"genre_scores_gemma":[0.9952888,0.0001967492,0.002551355,0.00003217963,0.00001848682,0.0003642163,0.001281636,0.000009739816,0.0002567472],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04956605,"threshold_uncertainty_score":0.1174794,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1750240190954241,"score_gpt":0.3552990267796993,"score_spread":0.1802750076842752,"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."}}