{"id":"W2792032639","doi":"10.1177/0049124117747302","title":"Optimizing Count Responses in Surveys: A Machine-learning Approach","year":2018,"lang":"en","type":"article","venue":"Sociological Methods & Research","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; Social Science Research Institute, Duke University; University of British Columbia; University of Victoria","keywords":"Censoring (clinical trials); Count data; Poisson distribution; Computer science; Bayesian probability; Multinomial distribution; Machine learning; Statistics; Artificial intelligence; Mathematics","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01565797,0.001161781,0.002279224,0.001931137,0.0007381362,0.001345627,0.002757507,0.002098599,0.001966983],"category_scores_gemma":[0.05148483,0.0009447563,0.001328933,0.002055735,0.001643475,0.002182085,0.002185471,0.002057486,0.0004598632],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00159986,"about_ca_system_score_gemma":0.001726013,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002559317,"about_ca_topic_score_gemma":0.00209059,"domain_scores_codex":[0.9868499,0.0105595,0.0003779721,0.001113612,0.0008537297,0.0002453226],"domain_scores_gemma":[0.9675589,0.0270902,0.001781939,0.001826639,0.001395924,0.0003464219],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000194806,0.0001833446,0.00485536,0.0002907224,0.0002157013,0.00006652307,0.0002144601,0.761117,0.0009189674,0.06865047,0.001770993,0.1615217],"study_design_scores_gemma":[0.00001926636,0.0000449317,0.0003299147,0.00001817406,0.00001151277,0.00001100473,0.00001740687,0.9683514,0.0003197057,0.03034217,0.0005246112,0.000009822913],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005736902,0.00009839907,0.9934266,0.0001598167,0.00001008474,0.00007439717,0.00003607238,0.0001490472,0.0003087214],"genre_scores_gemma":[0.1976903,0.0002212452,0.799514,0.0002295151,0.00008822711,0.0007534893,0.0003358338,0.00009989253,0.00106742],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.984342,"threshold_uncertainty_score":0.0828082,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6338353326777821,"score_gpt":0.602291176727981,"score_spread":0.03154415594980109,"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."}}