{"id":"W2043112308","doi":"10.2466/03.pr0.107.5.535-546","title":"Scale Validation via Quantifying Item Validity Using the <i> D <sub>m</sub> </i> Index","year":2010,"lang":"en","type":"article","venue":"Psychological Reports","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Criterion validity; Psychology; Construct validity; Scale (ratio); Index (typography); Statistics; External validity; Test validity; Item response theory; Psychometrics; Computer science; Social psychology; Mathematics; Clinical psychology","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":[],"category_scores_codex":[0.02111587,0.0002731829,0.0004810908,0.0002916621,0.000635134,0.0004986913,0.0008683054,0.000348524,0.0002544633],"category_scores_gemma":[0.1012718,0.000133774,0.0002885555,0.002709373,0.0003290789,0.000317578,0.0002920229,0.0009766524,0.00005749325],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002491044,"about_ca_system_score_gemma":0.00002882728,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000028135,"about_ca_topic_score_gemma":0.00001267699,"domain_scores_codex":[0.9938626,0.0009451171,0.001528334,0.001254661,0.001822969,0.0005863607],"domain_scores_gemma":[0.977937,0.01807046,0.001376284,0.001931456,0.0004445692,0.0002402465],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0000216485,0.000130569,0.5325415,0.00000205325,0.000006960691,0.0001269883,0.00005414,0.00006720002,0.2340052,0.00003257365,0.001232116,0.2317791],"study_design_scores_gemma":[0.0002378813,0.0001136883,0.8446349,0.00001657783,0.00002745216,0.002654077,0.0001654311,0.002774783,0.04441171,0.09866341,0.005851483,0.000448591],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8746978,0.00003247923,0.1157329,0.0004696797,0.004889506,0.0002847233,0.000001779363,0.0001505178,0.003740544],"genre_scores_gemma":[0.9874748,0.00001135802,0.0115114,0.0004946729,0.0004287364,0.00001627262,0.000002465536,0.00001730321,0.00004296118],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3120934,"threshold_uncertainty_score":0.9062986,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6332346981021989,"score_gpt":0.5183237432852831,"score_spread":0.1149109548169158,"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."}}