{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003064164,0.00007854306,0.0001955242,0.0000504382,0.0001803971,0.00001185246,0.0003276186,0.00005693491,0.0001614948],"category_scores_gemma":[0.001120829,0.00003854423,0.00004108586,0.0001209537,0.000207484,0.00004761246,0.00001159722,0.0003673505,0.00000247268],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001449511,"about_ca_system_score_gemma":0.0001105415,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000016569,"about_ca_topic_score_gemma":0.00003434216,"domain_scores_codex":[0.9982114,0.000930399,0.0004315335,0.00007820107,0.0001908196,0.0001576124],"domain_scores_gemma":[0.9960744,0.002903571,0.0004094031,0.0003271699,0.0002382536,0.00004724713],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.005373892,0.002900475,0.01603026,0.0005120019,0.0008554928,0.00001495209,0.0634537,0.00969047,0.006649657,0.2532889,0.5731753,0.06805489],"study_design_scores_gemma":[0.001111181,0.0009289658,0.03322179,0.00005838582,0.0002294238,0.0004573632,0.001614693,0.0003763407,0.0002020408,0.9487107,0.01298928,0.00009988217],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2979727,0.00005320279,0.6981764,0.002361326,0.0004145991,0.0003054985,0.00004402507,0.000009006177,0.0006632275],"genre_scores_gemma":[0.2315282,0.0001447627,0.7663199,0.0003529215,0.0001915939,0.000007822021,0.000004299474,0.00002970282,0.001420764],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6954218,"threshold_uncertainty_score":0.1768254,"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."}}