{"id":"W2921710211","doi":"10.1186/s12874-019-0680-5","title":"A comparison of the polytomous Rasch analysis output of RUMM2030 and R (ltm/eRm/TAM/lordif)","year":2019,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":56,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; St Joseph's Health Centre; Western University","funders":"Canadian Institutes of Health Research","keywords":"Rasch model; Polytomous Rasch model; Likert scale; Computer science; Differential item functioning; Item response theory; Rating scale; Reliability (semiconductor); Consistency (knowledge bases); Ordinal data; Software; Statistics; Scale (ratio); Psychometrics; Psychology; Econometrics; Machine learning; Artificial intelligence; Mathematics","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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1692574,0.0001864777,0.001984377,0.002239747,0.0001629269,0.00004572248,0.002913674,0.0004334073,0.001955254],"category_scores_gemma":[0.7406399,0.0001016914,0.0004651567,0.01061742,0.001899767,0.00007453775,0.001868125,0.001133805,0.00004026009],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003225956,"about_ca_system_score_gemma":0.0006497951,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006328039,"about_ca_topic_score_gemma":0.0002790794,"domain_scores_codex":[0.944759,0.04443556,0.0019891,0.0009617411,0.006986684,0.0008678876],"domain_scores_gemma":[0.4040448,0.5913659,0.0008780507,0.001981238,0.001224222,0.0005057731],"domain_codex":null,"domain_gemma":"methods","domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001666513,0.00009399831,0.8534713,0.00005177219,0.0001507494,0.000002290388,0.0004493534,0.0000618959,0.001097907,0.001979607,0.001261983,0.1412125],"study_design_scores_gemma":[0.0009650953,0.0005357977,0.9495183,0.00006244741,0.0001124241,0.00001838661,0.004527106,0.01580043,0.002349313,0.02281171,0.003139711,0.0001593437],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8439105,0.001625037,0.1483466,0.001147522,0.000554735,0.0003517336,0.00000852014,0.0000148835,0.004040433],"genre_scores_gemma":[0.894804,0.00008831879,0.103386,0.00008189271,0.00009253022,0.00001145903,0.000001099368,0.00001078399,0.001523916],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5713825,"threshold_uncertainty_score":0.9989571,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9064755610915639,"score_gpt":0.6992995594836466,"score_spread":0.2071760016079173,"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."}}