{"id":"W4386833686","doi":"10.1017/xps.2023.24","title":"Assessing the Validity of Prevalence Estimates in Double List Experiments","year":2023,"lang":"en","type":"article","venue":"Journal of Experimental Political Science","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"American Political Science Association","keywords":"Identification (biology); Variance (accounting); Estimator; Econometrics; Computer science; Population; Frontier; Social desirability bias; Psychology; Sensitivity (control systems); Data science; Statistics; Social psychology; Mathematics; Geography; Social desirability; Economics; Sociology; Engineering; Demography","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":[0.003648471,0.00009393346,0.0002054635,0.0001859597,0.0001364007,0.000120666,0.0005163929,0.00003299245,0.00003984105],"category_scores_gemma":[0.001655479,0.00006108593,0.00006799134,0.0006217284,0.0006883231,0.000635689,0.0001394097,0.0001445857,0.000003365071],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001934432,"about_ca_system_score_gemma":0.000155543,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007596066,"about_ca_topic_score_gemma":5.51505e-7,"domain_scores_codex":[0.9981202,0.00007520371,0.0005552907,0.0001289054,0.0007038928,0.0004165262],"domain_scores_gemma":[0.9983706,0.0009085186,0.0002446042,0.0001856199,0.0001418358,0.0001488166],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00004816633,0.0008813792,0.05415542,0.0001314676,0.00001278224,0.00002767146,0.002741676,0.00003433024,0.6245624,0.3165368,0.0005914433,0.000276422],"study_design_scores_gemma":[0.0002592798,0.000118065,0.02307722,0.0002133537,0.000005410199,0.00003098845,0.001644924,0.001209995,0.9305559,0.04280374,0.000004776774,0.00007638336],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9972208,0.00004497997,0.0008490566,0.0002084959,0.0001837192,0.00009564263,0.000001437545,0.00003294455,0.001362897],"genre_scores_gemma":[0.9890437,0.000003291379,0.01084856,0.00002956502,0.00004010827,0.000005757631,1.96148e-7,0.000006778663,0.00002207438],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3059935,"threshold_uncertainty_score":0.2536155,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3289888980853183,"score_gpt":0.5234984095083213,"score_spread":0.1945095114230029,"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."}}