{"id":"W2093103144","doi":"10.1080/00223980009600857","title":"Searching for Reliable Relationships With Statistics Packages: An Empirical Example of the Potential Problems","year":2000,"lang":"en","type":"article","venue":"The Journal of Psychology","topic":"Statistics Education and Methodologies","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Overconfidence effect; Reliability (semiconductor); Psychology; Sample size determination; Statistics; Statistical hypothesis testing; Sample (material); Statistical inference; Empirical research; Econometrics; Statistical analysis; Computer science; Social psychology; Mathematics","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":[0.4830225,0.002554723,0.002645055,0.009181262,0.006486093,0.009413261,0.005393662,0.007773751,0.004912249],"category_scores_gemma":[0.8640533,0.00255171,0.001922725,0.01342102,0.02541053,0.01631152,0.007337177,0.01294227,0.001983893],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003699603,"about_ca_system_score_gemma":0.007745034,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00294834,"about_ca_topic_score_gemma":0.001792138,"domain_scores_codex":[0.3331103,0.5615408,0.02558727,0.01408665,0.0644767,0.001198215],"domain_scores_gemma":[0.02876255,0.8868324,0.02263019,0.0386765,0.02249637,0.0006019172],"domain_codex":"methods","domain_gemma":"methods","domain_candidate":"methods","domain_consensus":"methods","study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001887526,0.000992462,0.04988381,0.005766161,0.001406384,0.003302034,0.114442,0.006082876,0.003694764,0.3898053,0.07201475,0.350722],"study_design_scores_gemma":[0.0008974695,0.001276834,0.02585354,0.005555529,0.000544308,0.006436069,0.0176116,0.04834944,0.008858112,0.7922313,0.09128571,0.00110006],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06363015,0.005365511,0.8315191,0.07697847,0.001774157,0.001257034,0.00044735,0.002686354,0.01634196],"genre_scores_gemma":[0.4498438,0.001374045,0.5299729,0.01181235,0.001165841,0.003072219,0.0001772832,0.001413615,0.001168008],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5169774,"threshold_uncertainty_score":0.6375253,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3906082108956295,"score_gpt":0.4940742793185277,"score_spread":0.1034660684228982,"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."}}