{"id":"W4388222503","doi":"10.47004/wp.cem.2023.2223","title":"Powerful t-tests in the presence of nonclassical measurement error","year":2023,"lang":"en","type":"report","venue":"","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Economic and Social Research Council; Social Sciences and Humanities Research Council of Canada","keywords":"Statistics; Computer science; Psychology; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.004703571,0.0002422727,0.0006654383,0.0000888973,0.00002322148,0.00001249708,0.0004115398,0.0002089541,0.00008632421],"category_scores_gemma":[0.02083866,0.0001398335,0.0001352812,0.0002327058,0.000114565,0.0000301723,0.0001286215,0.0005021117,0.00001616226],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001569556,"about_ca_system_score_gemma":0.0005543867,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001002445,"about_ca_topic_score_gemma":0.0005380085,"domain_scores_codex":[0.9959027,0.0002981216,0.0007863499,0.0003627148,0.002338439,0.0003116442],"domain_scores_gemma":[0.9944943,0.003971614,0.0002948117,0.0006460559,0.000534749,0.00005842253],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00007474576,0.001317409,0.0001325566,0.004473863,0.0002409933,0.0004259795,0.001542466,0.00006069064,0.0003294557,0.5549118,0.376714,0.05977602],"study_design_scores_gemma":[0.0002751685,0.0001628965,0.0006330482,0.001025369,0.0001323051,0.00002414647,0.0003101207,0.0009579392,0.0001529812,0.9669458,0.0290054,0.0003748106],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000105518,0.0001298422,0.8216935,0.0005289323,0.0006369686,0.0009766842,0.00008929239,0.00007041896,0.1757688],"genre_scores_gemma":[0.04632651,0.0004993239,0.9195462,0.0001137832,0.0004520823,0.0002736035,0.00001988472,0.0002040568,0.03256453],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.412034,"threshold_uncertainty_score":0.9874092,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5882557153706481,"score_gpt":0.5432384687480378,"score_spread":0.04501724662261031,"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."}}