{"id":"W2273367618","doi":"10.6000/2292-2598.2015.03.04.2","title":"Utility and Validity of Authentic Assessments and Conventional Tests for International Early Childhood Intervention Purposes: Evidence from U.S. National Social Validity Research","year":2016,"lang":"en","type":"article","venue":"Journal of Intellectual Disability - Diagnosis and Treatment","topic":"Early Childhood Education and Development","field":"Social Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Psychology; Intervention (counseling); External validity; Test validity; Criterion validity; Internal validity; Applied psychology; Construct validity; Clinical psychology; Social psychology; Psychometrics; Statistics; Mathematics; Psychiatry","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1221905,0.0008222449,0.00112183,0.007163219,0.002174057,0.004283676,0.002413198,0.001715822,0.002510728],"category_scores_gemma":[0.3096383,0.0005702584,0.001622988,0.009727268,0.00685617,0.004973538,0.004845368,0.002271323,0.000472218],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003389434,"about_ca_system_score_gemma":0.005785458,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01206319,"about_ca_topic_score_gemma":0.0210089,"domain_scores_codex":[0.8838454,0.05290938,0.01103554,0.00771086,0.04274813,0.001750654],"domain_scores_gemma":[0.5864652,0.2526777,0.05818435,0.02490733,0.07339244,0.004372885],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0005253021,0.000820326,0.802565,0.002295409,0.0008101306,0.00006574087,0.01534845,0.0003956629,0.0001851676,0.007082374,0.005433057,0.1644733],"study_design_scores_gemma":[0.0001043388,0.001025566,0.9458115,0.009108804,0.000642231,0.0002683649,0.01777325,0.002895015,0.001023863,0.00520321,0.01598398,0.000159975],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8694943,0.03719281,0.01378904,0.007187979,0.001170079,0.001912346,0.003226085,0.00008327512,0.06594399],"genre_scores_gemma":[0.9823239,0.005622506,0.008848653,0.001004577,0.0001514578,0.0006976405,0.000999301,0.00003351412,0.000318531],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1221905,"threshold_uncertainty_score":0.6462126,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2696021189989222,"score_gpt":0.4676630951801826,"score_spread":0.1980609761812603,"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."}}