{"id":"W2612009109","doi":"","title":"WORKSHOP: Keeping up with The Standards: How to Design and Evaluate Reliability and Validity Studies","year":2015,"lang":"en","type":"article","venue":"ITC 2016 Conference","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Facilitator; Context (archaeology); Psychology; Reliability (semiconductor); Internal validity; Validity; Standards for Educational and Psychological Testing; External validity; Construct validity; Applied psychology; Presentation (obstetrics); Quality (philosophy); Psychometrics; Social psychology; Clinical psychology; Medicine; Higher education; Education theory; Political science","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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03344255,0.0001720968,0.0004076062,0.0001248414,0.0002578949,0.0005455052,0.0005007699,0.0000514881,0.00001867407],"category_scores_gemma":[0.200476,0.00007935135,0.00002183185,0.0007834493,0.0004255303,0.0002630999,0.000397454,0.0001631217,0.000007800534],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004973812,"about_ca_system_score_gemma":0.0002888148,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002703579,"about_ca_topic_score_gemma":0.00002619643,"domain_scores_codex":[0.9958131,0.001634576,0.0002732321,0.0006472954,0.001336075,0.0002956933],"domain_scores_gemma":[0.9415124,0.05352207,0.0003257971,0.001037943,0.003254365,0.0003474494],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0008649618,0.00003518998,0.06090876,0.00003140091,0.00009743033,0.00001455367,0.01339037,0.0007208069,0.0002061473,0.0008619975,0.1651787,0.7576897],"study_design_scores_gemma":[0.006195587,0.004137324,0.1689964,0.001212714,0.0003019306,0.0001473426,0.1459347,0.03297914,0.001509021,0.4797201,0.1564362,0.002429539],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.496532,0.001502291,0.4876419,0.01266455,0.00041177,0.000470725,0.000009304247,0.00004487746,0.0007225571],"genre_scores_gemma":[0.9565805,0.0001881148,0.04183149,0.000278768,0.00005153591,0.00002754693,1.00984e-7,0.000006471372,0.001035538],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7552601,"threshold_uncertainty_score":0.9952743,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8179560533686604,"score_gpt":0.5321420139146238,"score_spread":0.2858140394540366,"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."}}