{"id":"W2161564801","doi":"10.1109/ccece.2002.1013027","title":"Evaluation of several Efron bootstrap methods to estimate error measures for software metrics","year":2003,"lang":"en","type":"article","venue":"","topic":"Software Reliability and Analysis Research","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Statistics; Kurtosis; Confidence interval; Statistic; Nonparametric statistics; CDF-based nonparametric confidence interval; Skewness; Computer science; Robust confidence intervals; Software quality; Sample size determination; Context (archaeology); Sample (material); Population; Mathematics; Software","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01394753,0.0001226949,0.0002584713,0.0003747497,0.000102425,0.00008586913,0.000574355,0.0000729721,0.00005640526],"category_scores_gemma":[0.0160502,0.0001023626,0.0001690311,0.001530526,0.00003128646,0.0002512113,0.00008729976,0.00008038637,0.000009750231],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000128487,"about_ca_system_score_gemma":0.0003827963,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004847262,"about_ca_topic_score_gemma":0.00002252276,"domain_scores_codex":[0.996573,0.000888643,0.0003362253,0.0004306019,0.001458136,0.000313376],"domain_scores_gemma":[0.9962649,0.001063348,0.00007174634,0.000593393,0.001858923,0.0001477019],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001470845,0.0002087424,0.0018675,0.00008907882,0.0001277924,4.298244e-7,0.0003875938,0.07791221,0.001326225,0.0118013,0.00114063,0.9051238],"study_design_scores_gemma":[0.0007505499,0.0002811434,0.003656952,0.00001862482,0.0001617908,0.000003217972,0.00004798494,0.8964159,0.04708711,0.04703687,0.004238274,0.0003016125],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003841833,0.0002285003,0.9945294,0.0002643111,0.0001115969,0.0005210532,0.000002911542,0.00009423128,0.0004061634],"genre_scores_gemma":[0.1393432,0.000002471339,0.8603284,0.0000684562,0.000008821082,0.00007697015,0.000001724647,0.000006837836,0.0001630528],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9048222,"threshold_uncertainty_score":0.992238,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.186371257642096,"score_gpt":0.4842736465247925,"score_spread":0.2979023888826965,"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."}}