{"id":"W4311804723","doi":"10.1167/jov.22.14.4432","title":"Bar graphs of mean values produce inflated and variable estimates of effect size","year":2022,"lang":"en","type":"article","venue":"Journal of Vision","topic":"Mental Health Research Topics","field":"Psychology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Statistics; Bar (unit); Range (aeronautics); Mathematics; Variable (mathematics); Variation (astronomy); Psychology; Physics; Materials science; Astrophysics; Mathematical analysis","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":[],"category_scores_codex":[0.1056258,0.002659792,0.002104077,0.007208904,0.001035733,0.004019934,0.003164207,0.002291954,0.008541738],"category_scores_gemma":[0.4575257,0.002042641,0.001617079,0.004950597,0.007760458,0.007411105,0.0053934,0.005377823,0.002164812],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001802085,"about_ca_system_score_gemma":0.0008120203,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001017253,"about_ca_topic_score_gemma":0.001299902,"domain_scores_codex":[0.8593956,0.08998564,0.007801342,0.01735693,0.02449345,0.0009671925],"domain_scores_gemma":[0.3336836,0.5545299,0.04360309,0.05100781,0.01630804,0.0008676204],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.003879982,0.0005606856,0.08551016,0.01306058,0.009486797,0.001092145,0.02551704,0.01622443,0.03928405,0.1606316,0.08697847,0.5577741],"study_design_scores_gemma":[0.001259199,0.002689075,0.251906,0.004408259,0.002465488,0.001969923,0.006722292,0.05172122,0.05172674,0.5240678,0.09998641,0.001077697],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1201093,0.005840317,0.8243335,0.004370368,0.003072449,0.001615884,0.003958818,0.009426724,0.02727266],"genre_scores_gemma":[0.6680825,0.001207547,0.3158773,0.004110883,0.0007677377,0.00335872,0.001369643,0.003051964,0.002173681],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8943743,"threshold_uncertainty_score":0.5586091,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02251226341529515,"score_gpt":0.4074854762189859,"score_spread":0.3849732128036907,"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."}}