{"id":"W3217612029","doi":"10.1002/cjs.11719","title":"Let's practice what we preach: Planning and interpreting simulation studies with design and analysis of experiments","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Optimal Experimental Design Methods","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University; Acadia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Robustness (evolution); Fractional factorial design; Factorial experiment; Computer science; Taguchi methods; Main effect; Design of experiments; Variance (accounting); Factorial analysis; Variety (cybernetics); Population; Management science; Industrial engineering; Mathematics; Statistics; Machine learning; Engineering; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"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":[0.00358772,0.0001037857,0.000396335,0.0007928727,0.0002520759,0.0002627194,0.000182635,0.00001805646,0.0000678349],"category_scores_gemma":[0.004183091,0.0000836818,0.00002713477,0.0006633748,0.0001876106,0.0007355289,0.00005496738,0.0001627356,1.539983e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001460925,"about_ca_system_score_gemma":0.0002691595,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001614826,"about_ca_topic_score_gemma":0.00006287695,"domain_scores_codex":[0.9975403,0.000877375,0.000597727,0.0001748058,0.0006605743,0.0001492446],"domain_scores_gemma":[0.9912415,0.007047172,0.0008417166,0.0001213877,0.0005047246,0.0002434623],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005497463,0.00003335438,0.01693217,0.00001261832,0.001636156,0.0005051038,0.09310037,0.8260044,0.0007368031,0.000651216,0.0007750325,0.05906302],"study_design_scores_gemma":[0.0009855083,0.002732836,0.005633576,0.000244526,0.001532978,0.0002883701,0.4712835,0.509687,0.0009039092,0.003251263,0.003075802,0.0003807156],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07720426,0.01793844,0.9041408,0.0002328049,0.0002043941,0.0001471538,0.00006605688,0.000001956339,0.00006417879],"genre_scores_gemma":[0.6350933,0.00006148465,0.3647212,0.00008845341,0.000006552015,0.000001768844,9.493067e-7,0.000006430319,0.00001977229],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5578891,"threshold_uncertainty_score":0.5007853,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2990031300577587,"score_gpt":0.4902431970378035,"score_spread":0.1912400669800448,"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."}}