{"id":"W3023872451","doi":"10.3386/w15200","title":"Estimating Treatment Effects from Contaminated Multi-Period Education Experiments: The Dynamic Impacts of Class Size Reductions","year":2009,"lang":"en","type":"preprint","venue":"National Bureau of Economic Research","topic":"School Choice and Performance","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Attrition; Randomized experiment; Treatment effect; Treatment and control groups; Randomized controlled trial; Class (philosophy); Class size; Sample size determination; Cognition; Econometrics; Psychology; Statistics; Medicine; Computer science; Mathematics; Mathematics education; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.07872558,0.0008040572,0.002570439,0.001101656,0.0007378074,0.002233363,0.002378606,0.002639173,0.004397929],"category_scores_gemma":[0.2676703,0.001220748,0.002083252,0.0009974659,0.003452816,0.002615439,0.002269645,0.003501563,0.0003550556],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001618669,"about_ca_system_score_gemma":0.001746011,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001705714,"about_ca_topic_score_gemma":0.001277377,"domain_scores_codex":[0.9516705,0.03860305,0.001060649,0.004387993,0.003608697,0.0006692118],"domain_scores_gemma":[0.531869,0.4177347,0.0174083,0.03023451,0.002015212,0.0007382794],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.01622772,0.004847072,0.08253196,0.001946579,0.006169107,0.0004555144,0.001707082,0.3077573,0.01065926,0.2069616,0.003051884,0.3576849],"study_design_scores_gemma":[0.004407151,0.01041109,0.08704575,0.0004214392,0.002767666,0.000344843,0.0003916283,0.451833,0.01480216,0.4169516,0.01028509,0.0003386385],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2712398,0.001033208,0.7207382,0.0009328569,0.0002449052,0.001733039,0.0006829986,0.0004363564,0.002958742],"genre_scores_gemma":[0.8155394,0.0004648066,0.1767466,0.001000512,0.0001741547,0.002760984,0.000690814,0.0001001953,0.002522697],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.07872558,"threshold_uncertainty_score":0.4163457,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1751288391480212,"score_gpt":0.5404940067765601,"score_spread":0.3653651676285389,"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."}}