{"id":"W2054894396","doi":"10.1080/00220388.2010.514331","title":"Against Excessive Rhetoric in Impact Assessment: Overstating the Case for Randomised Controlled Experiments","year":2011,"lang":"en","type":"article","venue":"The Journal of Development Studies","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"Trent University","funders":"Link Foundation","keywords":"Causation; Causal inference; Argument (complex analysis); Impact evaluation; Impact assessment; Rhetoric; Inference; Randomized experiment; Psychology; Epistemology; Political science; Economics; Medicine; Law; Econometrics; Philosophy","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":[0.01846267,0.0001770498,0.0006216397,0.0002296471,0.0006302214,0.00007418837,0.0005003406,0.00002471402,0.0001169378],"category_scores_gemma":[0.002305126,0.0000663891,0.000184174,0.0003543987,0.00009065377,0.0003786774,0.0001090854,0.0001756014,0.000006141659],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003102059,"about_ca_system_score_gemma":0.0006180442,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007078101,"about_ca_topic_score_gemma":0.00004289518,"domain_scores_codex":[0.9963591,0.0006928478,0.001558125,0.0001222299,0.001020821,0.0002469135],"domain_scores_gemma":[0.9916626,0.005515439,0.001626157,0.0001932531,0.0009487904,0.0000537552],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.03350866,0.0008325285,0.04887073,0.00004245116,0.005402812,0.0003865107,0.8052596,0.003023446,0.001025649,0.0006517813,0.01426587,0.08672989],"study_design_scores_gemma":[0.2379991,0.001096888,0.1131352,0.0003738392,0.000395072,0.0004938009,0.6235535,0.007700729,0.003301023,0.009018997,0.002213167,0.0007187216],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9918014,0.001315339,0.002419354,0.0005656975,0.0006186601,0.001089441,0.000001294995,0.000003884992,0.002184866],"genre_scores_gemma":[0.9959008,0.0003663234,0.003103209,0.0002460673,0.00005849118,0.0001006448,3.158227e-7,0.000007146122,0.0002170195],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2044905,"threshold_uncertainty_score":0.6398831,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3628150657639925,"score_gpt":0.5344587604187655,"score_spread":0.171643694654773,"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."}}