{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3926879,0.002537998,0.003455858,0.005316621,0.004524206,0.01379283,0.009743472,0.01253255,0.02041689],"category_scores_gemma":[0.5513165,0.003276187,0.005013735,0.003188598,0.01102969,0.01580975,0.01472064,0.02450058,0.03072638],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.009510858,"about_ca_system_score_gemma":0.03631271,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00471622,"about_ca_topic_score_gemma":0.007482599,"domain_scores_codex":[0.7099651,0.227385,0.02022525,0.007391277,0.02999306,0.005040185],"domain_scores_gemma":[0.3736375,0.2894179,0.02594687,0.03682421,0.2503266,0.02384693],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002705515,0.0001864011,0.0006626252,0.004320999,0.0001888105,0.0002663638,0.009276407,0.0004641039,0.001202652,0.01114033,0.7714138,0.2006069],"study_design_scores_gemma":[0.000404625,0.0004357702,0.002295562,0.01713944,0.0001738104,0.0004623724,0.006844816,0.0007951609,0.001491634,0.04751332,0.9220939,0.0003495048],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"methods","genre_scores_codex":[0.003231341,0.01721501,0.2091704,0.6382353,0.07596797,0.02869644,0.001827643,0.003110501,0.02254545],"genre_scores_gemma":[0.03160134,0.02096251,0.5628442,0.2375419,0.02324886,0.08756224,0.002517411,0.004439138,0.02928242],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6073121,"threshold_uncertainty_score":0.748924,"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."}}