{"id":"W2507554215","doi":"10.1177/0033294116662659","title":"Significance Testing Needs a Taxonomy","year":2016,"lang":"en","type":"article","venue":"Psychological Reports","topic":"Forecasting Techniques and Applications","field":"Decision Sciences","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Statistical hypothesis testing; Statistical power; Statistical inference; Statistics; Psychology; Population; Type I and type II errors; Certainty; Exploratory data analysis; Econometrics; 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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002081804,0.0001149839,0.0001869814,0.0001129891,0.0001228093,0.00008941513,0.000419477,0.00008787701,0.0007642063],"category_scores_gemma":[0.01035365,0.00005478852,0.00008765059,0.001045237,0.000182876,0.0001067796,0.0001025283,0.00009001528,0.0003141114],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002208346,"about_ca_system_score_gemma":0.0000166944,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007244608,"about_ca_topic_score_gemma":7.168549e-7,"domain_scores_codex":[0.9978025,0.00005662764,0.0007300053,0.0005974039,0.0005454013,0.0002680855],"domain_scores_gemma":[0.9966837,0.001520767,0.0004366904,0.0009758157,0.0002394016,0.0001436561],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000007956691,0.000126829,0.06659041,5.243867e-7,0.000002590189,0.0001274907,0.00001103117,0.000002034254,0.01336394,0.005237024,0.05922043,0.8553097],"study_design_scores_gemma":[0.00009378672,0.0001687523,0.06307509,0.00002755679,0.000003595219,0.0005773735,0.00002409372,0.00003543159,0.001084893,0.3522871,0.5823967,0.0002256189],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4879278,0.00002999713,0.2552544,0.003836606,0.0003189271,0.0006058627,0.000005476504,0.0005958223,0.2514251],"genre_scores_gemma":[0.9539425,0.000001925114,0.04185625,0.0003232802,0.00009985861,0.0002865735,3.179752e-7,0.00000678535,0.003482532],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8550841,"threshold_uncertainty_score":0.9979826,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4659460032778048,"score_gpt":0.4511392690402991,"score_spread":0.01480673423750573,"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."}}