{"id":"W2974998223","doi":"10.1080/00273171.2019.1660605","title":"New Recommendations on the Use of R-Squared Differences in Multilevel Model Comparisons","year":2019,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":96,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Set (abstract data type); Mean squared error; Measure (data warehouse); Multilevel model; Computer science; Class (philosophy); Confusion; Data mining; Statistics; Mathematics; Artificial intelligence; Psychology","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":[0.001012488,0.0002019067,0.000392461,0.0003596708,0.0001129262,0.00007191022,0.0005792105,0.0001539666,0.0004624518],"category_scores_gemma":[0.00109614,0.0001405288,0.00007515679,0.000459418,0.0001273646,0.000286912,0.0002800643,0.0009658849,0.00006070297],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000185054,"about_ca_system_score_gemma":0.0001860536,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003337477,"about_ca_topic_score_gemma":0.0004362407,"domain_scores_codex":[0.9973423,0.000523974,0.0005311266,0.0003664297,0.0007194459,0.000516762],"domain_scores_gemma":[0.9947316,0.003904714,0.0001452487,0.0008042339,0.0003062147,0.0001079645],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000840949,0.005816566,0.08593088,0.0001294472,0.00006213273,0.00001781788,0.01096387,0.001544579,0.08654626,0.7056209,0.03717807,0.06534856],"study_design_scores_gemma":[0.003450614,0.001644672,0.08137008,0.001664932,0.00005187881,0.000002840176,0.002869871,0.5402603,0.04209518,0.3240141,0.001379948,0.001195539],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9148601,0.00000373999,0.08191853,0.0009828269,0.00005802219,0.001669555,0.0000923396,0.0001065909,0.0003083267],"genre_scores_gemma":[0.8461451,0.000008022908,0.1517225,0.00001497995,0.000009021197,0.0001245179,0.00001088672,0.0000301417,0.001934816],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5387158,"threshold_uncertainty_score":0.5730599,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8895675119762272,"score_gpt":0.598556855129321,"score_spread":0.2910106568469062,"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."}}