{"id":"W4406489459","doi":"10.1017/pan.2024.24","title":"Decoupling Visualization and Testing when Presenting Confidence Intervals","year":2025,"lang":"en","type":"article","venue":"Political Analysis","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Decoupling (probability); Confidence interval; Computer science; Visualization; Reliability engineering; Statistics; Data mining; Mathematics; Engineering; Control engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1062111,0.002418584,0.00236991,0.006940011,0.001613789,0.01249764,0.004849428,0.003447244,0.02879786],"category_scores_gemma":[0.5605375,0.00187583,0.002116257,0.005861734,0.006810508,0.01420281,0.01107805,0.008367457,0.005160507],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001800324,"about_ca_system_score_gemma":0.00339376,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007580756,"about_ca_topic_score_gemma":0.0008053109,"domain_scores_codex":[0.8422796,0.1329574,0.008906991,0.003621328,0.01138671,0.00084808],"domain_scores_gemma":[0.3473479,0.5793385,0.01856383,0.03379485,0.01836831,0.002586541],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0020198,0.0002349209,0.004275494,0.003365376,0.0004143656,0.001007521,0.01081727,0.01504918,0.004548828,0.4545658,0.07014492,0.4335566],"study_design_scores_gemma":[0.000493925,0.0003026504,0.001855735,0.001991465,0.0001606929,0.0007176203,0.001416836,0.08390572,0.009583262,0.7989698,0.1003046,0.0002977009],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003084457,0.0005301964,0.9802777,0.003784186,0.0006723094,0.0003139264,0.0004421391,0.006374656,0.004520281],"genre_scores_gemma":[0.1035383,0.0005402609,0.8868158,0.001465874,0.0008136524,0.001624961,0.0004033297,0.003481352,0.001316536],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8937889,"threshold_uncertainty_score":0.5617045,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5242550988197755,"score_gpt":0.599761551093115,"score_spread":0.07550645227333952,"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."}}