{"id":"W3184478963","doi":"10.1007/s10651-021-00512-5","title":"Markov regression model for analyzing big data to predict trajectories of repeated categorical outcomes: an application to $$\\hbox {PM}_{2.5}$$ air pollution data","year":2021,"lang":"en","type":"article","venue":"Environmental and Ecological Statistics","topic":"Air Quality Monitoring and Forecasting","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of New Brunswick; University of Prince Edward Island","funders":"","keywords":"Big data; Categorical variable; Air quality index; Markov chain; Air pollution; Computer science; Statistics; Econometrics; Data mining; Meteorology; Geography; 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":[],"consensus_categories":[],"category_scores_codex":[0.0004457995,0.0001700175,0.0002596926,0.00002009796,0.0002428717,0.00001996656,0.0004157746,0.00009680798,0.00006144455],"category_scores_gemma":[0.0003260541,0.0001371502,0.0000190622,0.0001122543,0.0001244743,0.0001741352,0.001311384,0.000100612,0.00001340222],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001547024,"about_ca_system_score_gemma":0.00001010234,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008507045,"about_ca_topic_score_gemma":0.0001204684,"domain_scores_codex":[0.9982252,0.00007661941,0.0003834347,0.0007714578,0.0002662967,0.0002769859],"domain_scores_gemma":[0.9987371,0.0001585928,0.0001110219,0.0007401034,0.000004802302,0.0002483685],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003222541,0.001647369,0.5413734,0.00007998913,0.00007266965,0.00002306072,0.001172078,0.04610305,0.04334658,0.0002228606,0.006135205,0.3595015],"study_design_scores_gemma":[0.0003068419,0.0003266405,0.6651827,0.000009060951,0.00006273236,0.000005172112,0.0003115913,0.3312341,0.0003847175,0.0007171335,0.00120271,0.0002566109],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4999941,0.00001234873,0.4957134,0.0002537118,0.00008689019,0.000281375,0.003619339,0.00002384224,0.00001507378],"genre_scores_gemma":[0.9123342,0.00002538863,0.08455108,0.0001575308,0.00007059949,0.00002756775,0.002647116,0.00001230992,0.0001742161],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4123401,"threshold_uncertainty_score":0.5592822,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.102188745144181,"score_gpt":0.3142721415315576,"score_spread":0.2120833963873766,"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."}}