{"id":"W2589404650","doi":"10.29173/cais437","title":"Statistical Power and Effect Size in Informative Retrieval Experiments","year":2013,"lang":"en","type":"article","venue":"Proceedings of the Annual Conference of CAIS / Actes du congrès annuel de l ACSI","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Statistical hypothesis testing; Null hypothesis; Statistical power; Type I and type II errors; Null (SQL); Alternative hypothesis; Statistical analysis; Search engine indexing; Computer science; Statistics; Multiple comparisons problem; Mathematics; Artificial intelligence; Information retrieval; Data mining","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0006210958,0.0001920043,0.0003434471,0.0001363806,0.00007888347,0.002117623,0.001230805,0.0001047596,0.00004742556],"category_scores_gemma":[0.01026296,0.0001333278,0.00005990381,0.0004239217,0.0003134946,0.01602224,0.0007713394,0.0002622806,0.00001026409],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005243032,"about_ca_system_score_gemma":0.0001309367,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001233349,"about_ca_topic_score_gemma":9.111733e-7,"domain_scores_codex":[0.998374,0.00003037625,0.0005009043,0.000187326,0.0005500405,0.0003572882],"domain_scores_gemma":[0.9859596,0.0003408994,0.0003651145,0.0001504762,0.0130389,0.0001450351],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0006265088,0.0003760247,0.5271874,0.0007916343,0.0001137116,0.000004777082,0.261054,0.000002785566,0.0468851,0.1384579,0.003860241,0.0206399],"study_design_scores_gemma":[0.001404194,0.001019125,0.8870996,0.0001798547,0.00001433423,0.00002714753,0.002259762,0.002650202,0.1002878,0.003129423,0.001584509,0.0003439947],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9941393,0.00002100638,0.0002224514,0.0005511299,0.00007350634,0.000505158,0.00003080413,0.00002606973,0.0044306],"genre_scores_gemma":[0.9980258,0.0000121,0.001639988,0.0001569319,0.00000865772,0.00002380425,0.00000103771,0.000005849444,0.000125791],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3599122,"threshold_uncertainty_score":0.9989183,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01377638208287326,"score_gpt":0.2600525226492694,"score_spread":0.2462761405663962,"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."}}