{"id":"W423015428","doi":"10.1016/j.joi.2015.05.001","title":"Modelling count response variables in informetric studies: Comparison among count, linear, and lognormal regression models","year":2015,"lang":"en","type":"article","venue":"Journal of Informetrics","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University","funders":"Capital Medical University","keywords":"Count data; Statistics; Negative binomial distribution; Poisson regression; Akaike information criterion; Mathematics; Regression analysis; Linear regression; Poisson distribution; Overdispersion; Log-normal distribution; Generalized linear model; Binomial regression; Regression diagnostic; Econometrics; Polynomial regression; Population","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":["bibliometrics"],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006002615,0.0002562066,0.0007645148,0.004770265,0.00009594231,0.0001751355,0.0008552774,0.0001769419,5.245337e-7],"category_scores_gemma":[0.002962127,0.0001922174,0.0001054542,0.006009157,0.0001019414,0.005555848,0.0004168262,0.0006421939,0.00000123582],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006156411,"about_ca_system_score_gemma":0.0004255455,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004123575,"about_ca_topic_score_gemma":0.000008155375,"domain_scores_codex":[0.996476,0.0001051539,0.001605737,0.0001951677,0.001231582,0.0003863743],"domain_scores_gemma":[0.9949323,0.001200263,0.001505047,0.0003761934,0.001714299,0.0002719241],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003411088,0.0000925449,0.01488059,0.00003487435,0.00006781059,0.00004908803,0.003022848,0.9637439,0.000006136033,0.001512195,0.0007795466,0.01546937],"study_design_scores_gemma":[0.0009498698,0.000508794,0.0004374191,0.0002065637,0.0000256892,0.00007024848,0.0009411998,0.9887267,0.0002075702,0.005726562,0.001970956,0.0002283904],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1738014,0.003715484,0.8218133,0.00005970649,0.0001602452,0.0001123533,0.000001118719,0.00004238317,0.0002940542],"genre_scores_gemma":[0.68673,0.002247306,0.3108272,0.00009233856,0.00004273399,0.000002947163,7.02843e-7,0.00001018971,0.000046579],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5129287,"threshold_uncertainty_score":0.7838399,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.103223804081119,"score_gpt":0.3570945740796192,"score_spread":0.2538707699985002,"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."}}