{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.216507,0.003170587,0.004261416,0.005690524,0.001653992,0.005830301,0.004870388,0.003580332,0.01785567],"category_scores_gemma":[0.5365052,0.002392549,0.007444591,0.007543145,0.006785017,0.004748549,0.006868024,0.008983103,0.005836214],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002008131,"about_ca_system_score_gemma":0.007110793,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004832294,"about_ca_topic_score_gemma":0.003108884,"domain_scores_codex":[0.7566175,0.2171468,0.007905611,0.007553924,0.009931084,0.00084512],"domain_scores_gemma":[0.4933018,0.4444153,0.01458299,0.03800296,0.008710288,0.000986596],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001587458,0.0004651991,0.02317691,0.007406429,0.008116609,0.00110535,0.004406236,0.03772061,0.002038994,0.4731328,0.05769674,0.3831467],"study_design_scores_gemma":[0.001648036,0.0008240328,0.007930721,0.003228061,0.001592814,0.0008094891,0.000791924,0.2162021,0.004345024,0.6583006,0.1038652,0.0004619197],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001339031,0.0004622445,0.9914832,0.0012133,0.0002433183,0.001454269,0.0006631651,0.001894317,0.001247216],"genre_scores_gemma":[0.01445153,0.0003996861,0.9743295,0.000505238,0.0001068313,0.00867542,0.0003138432,0.0007006563,0.0005171817],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.216507,"threshold_uncertainty_score":0.9661863,"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."}}