{"id":"W2154068546","doi":"10.1162/rest.2009.11453","title":"Estimating Treatment Effects from Contaminated Multiperiod Education Experiments: The Dynamic Impacts of Class Size Reductions","year":2010,"lang":"en","type":"article","venue":"The Review of Economics and Statistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":68,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Attrition; Treatment and control groups; Treatment effect; Randomized experiment; Sample size determination; Randomized controlled trial; Class size; Class (philosophy); Econometrics; Cognition; Average treatment effect; Statistics; Mathematics; Psychology; Computer science; Medicine; Propensity score matching; Mathematics education; Artificial intelligence","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":[0.08723218,0.0008639157,0.00269528,0.001318507,0.0009239589,0.002358198,0.002613731,0.002787467,0.004342807],"category_scores_gemma":[0.2971478,0.001118045,0.002164934,0.001279784,0.004066643,0.003127725,0.002541119,0.003719036,0.0003545472],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00203755,"about_ca_system_score_gemma":0.002193301,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002288138,"about_ca_topic_score_gemma":0.001694277,"domain_scores_codex":[0.9399362,0.04905633,0.001293949,0.004864697,0.004151717,0.0006971119],"domain_scores_gemma":[0.4699262,0.4715364,0.02122817,0.03413286,0.002455354,0.0007209835],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.007667327,0.002585714,0.06449816,0.002082441,0.005883469,0.0005059632,0.001542711,0.2415532,0.005448391,0.3522376,0.003435333,0.3125597],"study_design_scores_gemma":[0.002092197,0.004148744,0.04052762,0.0004396713,0.002288626,0.0002953358,0.0003379407,0.3536495,0.007597625,0.5782222,0.01016973,0.0002308026],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.132895,0.001635103,0.8588195,0.001309215,0.0002734728,0.001217136,0.0005098943,0.0004040765,0.002936669],"genre_scores_gemma":[0.7876437,0.0008781048,0.2040569,0.001325296,0.0002385308,0.002435507,0.0006405344,0.0001071845,0.002674289],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9127678,"threshold_uncertainty_score":0.4613334,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03765709014787755,"score_gpt":0.3925355550934054,"score_spread":0.3548784649455278,"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."}}