{"id":"W2161220067","doi":"10.1177/0013164404272499","title":"Can Percentiles Replace Raw Scores in the Statistical Analysis of Test Data?","year":2005,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; Carleton University","funders":"","keywords":"Percentile; Raw score; Statistics; Nonparametric statistics; Percentile rank; Statistical power; Raw data; Mathematics; Statistical hypothesis testing; Test (biology); Statistical analysis; Econometrics","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":[],"consensus_categories":[],"category_scores_codex":[0.001566971,0.0001000399,0.0002312795,0.00006734143,0.00005675368,0.00001652086,0.0002440835,0.00003721711,0.0003733293],"category_scores_gemma":[0.0036299,0.00005904876,0.00002970287,0.0002404552,0.0001382579,0.00003667681,0.00003458016,0.0001261109,0.000001738204],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002985641,"about_ca_system_score_gemma":0.00002740788,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002443417,"about_ca_topic_score_gemma":0.0002600079,"domain_scores_codex":[0.9984859,0.0002157754,0.0003550275,0.0003291736,0.0004632236,0.0001509233],"domain_scores_gemma":[0.9967351,0.00263152,0.0000800757,0.0003944303,0.0000947977,0.00006410906],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.0001160035,0.005457987,0.03301648,0.00006903438,0.0002482361,0.000002879379,0.001612336,0.0001374205,0.0004350853,0.8912671,0.01393395,0.05370356],"study_design_scores_gemma":[0.0002758304,0.0001252069,0.5989844,0.00002677823,0.0002709099,0.000004813936,0.0002477313,0.001455747,0.000008755646,0.3970121,0.001459504,0.0001282335],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3943751,0.001078649,0.553256,0.04266171,0.0002746659,0.001044305,0.001239428,0.00003248477,0.006037647],"genre_scores_gemma":[0.8288139,0.00003387722,0.1706268,0.0003458647,0.00006971044,0.00002608662,0.0000441534,0.000003393402,0.00003626478],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5659679,"threshold_uncertainty_score":0.4345592,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4758787201349256,"score_gpt":0.5112399896517614,"score_spread":0.03536126951683582,"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."}}