{"id":"W4413214703","doi":"10.15695/jstem/v8i1.05","title":"Testing the Efficacy of Educational Interventions on Matched Student Samples: A Primer for Propensity Score Matching in R","year":2025,"lang":"en","type":"article","venue":"The Journal of STEM Outreach","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"National Institutes of Health","keywords":"Propensity score matching; Matching (statistics); Psychological intervention; Primer (cosmetics); Psychology; Internal medicine; Statistics; Computer science; Medicine; Mathematics; Chemistry","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":[0.00194143,0.0001093667,0.0003052254,0.0001249507,0.00009438924,0.00002217397,0.0004435533,0.00003233878,0.000006677266],"category_scores_gemma":[0.0009127718,0.00005733811,0.0001369842,0.000204977,0.00006271999,0.00008645399,0.00009132201,0.0002861847,6.181739e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00013343,"about_ca_system_score_gemma":0.0001298805,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003266652,"about_ca_topic_score_gemma":0.00002821641,"domain_scores_codex":[0.99869,0.0001752754,0.0007247252,0.00007494413,0.0002105518,0.0001245196],"domain_scores_gemma":[0.992811,0.005909131,0.0006877845,0.0002559271,0.0003176365,0.00001858193],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.002101476,0.009938288,0.2269681,0.003169967,0.001472463,0.000006495036,0.04189168,0.002069955,0.04366203,0.6118597,0.004991625,0.05186822],"study_design_scores_gemma":[0.001523744,0.0005899815,0.3484522,0.009614717,0.0004073645,0.00004673931,0.005110171,0.00003743538,0.01037019,0.6236252,0.00003757302,0.0001846346],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9728361,0.0001142308,0.0243418,0.001436981,0.00007593011,0.0008079775,0.000006632484,0.00001240067,0.0003679473],"genre_scores_gemma":[0.9847957,0.000005200687,0.0149079,0.00004668014,0.00003977361,0.00002209786,8.720151e-7,0.00001154264,0.0001702072],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1214842,"threshold_uncertainty_score":0.233818,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3755214620628621,"score_gpt":0.4685429570865438,"score_spread":0.09302149502368173,"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."}}