{"id":"W4283313359","doi":"10.2196/35797","title":"Strategies and Lessons Learned During Cleaning of Data From Research Panel Participants: Cross-sectional Web-Based Health Behavior Survey Study","year":2022,"lang":"en","type":"article","venue":"JMIR Formative Research","topic":"Survey Methodology and Nonresponse","field":"Social Sciences","cited_by":35,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Center for Advancing Translational Sciences; University of South Carolina; South Carolina Clinical and Translational Research Institute, Medical University of South Carolina; National Cancer Institute; National Institutes of Health; Moffitt Cancer Center; Medical University of South Carolina","keywords":"Checklist; Data quality; The Internet; Survey data collection; Web application; Quality (philosophy); Psychology; Data science; Computer science; Medical education; World Wide Web; Medicine; Business; Marketing","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4618208,0.002730286,0.00274717,0.007348115,0.006791695,0.008795485,0.009235739,0.003930132,0.003254721],"category_scores_gemma":[0.4831236,0.003164473,0.003699032,0.006152896,0.004757067,0.009556727,0.009722537,0.007354232,0.002408259],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006213982,"about_ca_system_score_gemma":0.02832662,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01258581,"about_ca_topic_score_gemma":0.03419209,"domain_scores_codex":[0.4413028,0.4835104,0.03617996,0.009713744,0.0239747,0.005318472],"domain_scores_gemma":[0.4038301,0.3896337,0.02787786,0.06639054,0.1015032,0.01076468],"domain_codex":"methods","domain_gemma":"methods","domain_candidate":"methods","domain_consensus":"methods","study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0007143505,0.003738514,0.08990645,0.01182417,0.0007372359,0.002397824,0.3028846,0.002712976,0.004846477,0.005639706,0.03250853,0.5420892],"study_design_scores_gemma":[0.001527605,0.006301255,0.1774952,0.03268687,0.001783155,0.003988791,0.4057339,0.02193123,0.02197761,0.04364932,0.2811883,0.001736818],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2019723,0.007138032,0.6086717,0.05886045,0.003322978,0.1030204,0.002352352,0.00263442,0.01202728],"genre_scores_gemma":[0.1355752,0.002787443,0.784674,0.009337528,0.0008942282,0.06378964,0.0007818398,0.0004146806,0.001745499],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5381793,"threshold_uncertainty_score":0.6636708,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8942829336120554,"score_gpt":0.6843921430569075,"score_spread":0.2098907905551478,"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."}}