{"id":"W68437104","doi":"10.1007/978-3-319-07794-9_1","title":"Setting the Stage for Validity and Validation in Social, Behavioral, and Health Sciences: Trends in Validation Practices","year":2014,"lang":"en","type":"book-chapter","venue":"Social indicators research series","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":32,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Sketch; Psychology; Construct validity; Validity; Behavioural sciences; Test validity; External validity; Criterion validity; Applied psychology; Medical education; Psychometrics; Social psychology; Clinical psychology; Medicine; Computer science; Psychotherapist","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":[0.5192394,0.002182117,0.005588507,0.01575457,0.007506736,0.0271707,0.007715901,0.01041499,0.002773199],"category_scores_gemma":[0.6856157,0.002749977,0.003333254,0.01286332,0.03911835,0.03635259,0.02073497,0.03248907,0.002240147],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0140903,"about_ca_system_score_gemma":0.068666,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0159661,"about_ca_topic_score_gemma":0.0157086,"domain_scores_codex":[0.5662069,0.324198,0.03642204,0.01276123,0.05707717,0.003334576],"domain_scores_gemma":[0.1708592,0.6837725,0.01683628,0.03349587,0.08975058,0.005285553],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0002896992,0.0004994224,0.02391983,0.005466296,0.0004110688,0.0001837478,0.02505382,0.001383134,0.001855169,0.3446246,0.06289401,0.5334191],"study_design_scores_gemma":[0.0002093166,0.0005328401,0.03028122,0.04409214,0.0003439214,0.0006702842,0.02536032,0.009019169,0.005657018,0.7229177,0.1603318,0.0005841713],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02723331,0.2023611,0.367462,0.3525997,0.01139758,0.003112168,0.0008979384,0.001203135,0.0337332],"genre_scores_gemma":[0.1776428,0.05200474,0.7164549,0.03896585,0.003478921,0.005605035,0.0008776257,0.001392022,0.003578066],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4807606,"threshold_uncertainty_score":0.5928634,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8435949426545746,"score_gpt":0.6445421174829625,"score_spread":0.199052825171612,"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."}}