{"id":"https://openalex.org/W2150073804","doi":"https://doi.org/10.1093/bioinformatics/btu527","title":"Cross-validation under separate sampling: strong bias and how to correct it","display_name":"Cross-validation under separate sampling: strong bias and how to correct it","publication_year":2014,"publication_date":"2014-08-13","ids":{"openalex":"https://openalex.org/W2150073804","doi":"https://doi.org/10.1093/bioinformatics/btu527","mag":"2150073804","pmid":"https://pubmed.ncbi.nlm.nih.gov/25123902"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btu527","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btu527","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/30/23/3349/48932478/bioinformatics_30_23_3349.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/30/23/3349/48932478/bioinformatics_30_23_3349.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026990034","display_name":"Ulisses Braga-Neto","orcid":"https://orcid.org/0000-0002-1210-2173"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ulisses M. Braga-Neto","raw_affiliation_strings":["1 Department of Electrical and Computer Engineering, 2Center for Bioinformatics and Genomic Systems Engineering and 3Department of Statistics, Texas A&M University, College Station, TX, 77843, USA"],"affiliations":[{"raw_affiliation_string":"1 Department of Electrical and Computer Engineering, 2Center for Bioinformatics and Genomic Systems Engineering and 3Department of Statistics, Texas A&M University, College Station, TX, 77843, USA","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040086890","display_name":"Amin Zollanvari","orcid":"https://orcid.org/0000-0002-9172-8413"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amin Zollanvari","raw_affiliation_strings":["1 Department of Electrical and Computer Engineering, 2Center for Bioinformatics and Genomic Systems Engineering and 3Department of Statistics, Texas A&M University, College Station, TX, 77843, USA"],"affiliations":[{"raw_affiliation_string":"1 Department of Electrical and Computer Engineering, 2Center for Bioinformatics and Genomic Systems Engineering and 3Department of Statistics, Texas A&M University, College Station, TX, 77843, USA","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112221423","display_name":"Edward R. Dougherty","orcid":null},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Edward R. Dougherty","raw_affiliation_strings":["1 Department of Electrical and Computer Engineering, 2Center for Bioinformatics and Genomic Systems Engineering and 3Department of Statistics, Texas A&M University, College Station, TX, 77843, USA"],"affiliations":[{"raw_affiliation_string":"1 Department of Electrical and Computer Engineering, 2Center for Bioinformatics and Genomic Systems Engineering and 3Department of Statistics, Texas A&M University, College Station, TX, 77843, USA","institution_ids":["https://openalex.org/I91045830"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5026990034"],"corresponding_institution_ids":["https://openalex.org/I91045830"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":1.5656,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.83048895,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"30","issue":"23","first_page":"3349","last_page":"3355"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9883000254631042,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11970","display_name":"Molecular Biology Techniques and Applications","score":0.9764000177383423,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.7363126277923584},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.7172596454620361},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.5607762932777405},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5558270215988159},{"id":"https://openalex.org/keywords/cross-validation","display_name":"Cross-validation","score":0.5189566016197205},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.45232897996902466},{"id":"https://openalex.org/keywords/sampling-bias","display_name":"Sampling bias","score":0.4438530206680298},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.44059503078460693},{"id":"https://openalex.org/keywords/unbiased-estimation","display_name":"Unbiased Estimation","score":0.4290527403354645},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.42748144268989563},{"id":"https://openalex.org/keywords/systematic-sampling","display_name":"Systematic sampling","score":0.42444437742233276},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3751384913921356},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.33907920122146606},{"id":"https://openalex.org/keywords/sample-size-determination","display_name":"Sample size determination","score":0.30204278230667114}],"concepts":[{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.7363126277923584},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.7172596454620361},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.5607762932777405},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5558270215988159},{"id":"https://openalex.org/C27181475","wikidata":"https://www.wikidata.org/wiki/Q541014","display_name":"Cross-validation","level":2,"score":0.5189566016197205},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.45232897996902466},{"id":"https://openalex.org/C75917345","wikidata":"https://www.wikidata.org/wiki/Q2725298","display_name":"Sampling bias","level":3,"score":0.4438530206680298},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.44059503078460693},{"id":"https://openalex.org/C2909318450","wikidata":"https://www.wikidata.org/wiki/Q15222032","display_name":"Unbiased Estimation","level":3,"score":0.4290527403354645},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.42748144268989563},{"id":"https://openalex.org/C192489979","wikidata":"https://www.wikidata.org/wiki/Q1502997","display_name":"Systematic sampling","level":2,"score":0.42444437742233276},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3751384913921356},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.33907920122146606},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.30204278230667114},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009369","descriptor_name":"Neoplasms","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D009369","descriptor_name":"Neoplasms","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D009369","descriptor_name":"Neoplasms","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D010300","descriptor_name":"Parkinson Disease","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D010300","descriptor_name":"Parkinson Disease","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D010300","descriptor_name":"Parkinson Disease","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011336","descriptor_name":"Probability","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011336","descriptor_name":"Probability","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011336","descriptor_name":"Probability","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015983","descriptor_name":"Selection Bias","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015983","descriptor_name":"Selection Bias","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015983","descriptor_name":"Selection Bias","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020411","descriptor_name":"Oligonucleotide Array Sequence Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020411","descriptor_name":"Oligonucleotide Array Sequence Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020411","descriptor_name":"Oligonucleotide Array Sequence Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059467","descriptor_name":"Transcriptome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059467","descriptor_name":"Transcriptome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059467","descriptor_name":"Transcriptome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btu527","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btu527","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/30/23/3349/48932478/bioinformatics_30_23_3349.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:25123902","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/25123902","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:4296143","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4296143","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btu527","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btu527","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/30/23/3349/48932478/bioinformatics_30_23_3349.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2150073804.pdf","grobid_xml":"https://content.openalex.org/works/W2150073804.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W1564947197","https://openalex.org/W1605688901","https://openalex.org/W1817561967","https://openalex.org/W2047717400","https://openalex.org/W2065175896","https://openalex.org/W2079100340","https://openalex.org/W2107956883","https://openalex.org/W2110298216","https://openalex.org/W2110502951","https://openalex.org/W2112765817","https://openalex.org/W2114986399","https://openalex.org/W2138218344","https://openalex.org/W2143426320","https://openalex.org/W2150671673","https://openalex.org/W2155165473","https://openalex.org/W2327691244","https://openalex.org/W4230946174"],"related_works":["https://openalex.org/W2158754421","https://openalex.org/W2626882636","https://openalex.org/W2015152150","https://openalex.org/W2009279294","https://openalex.org/W2122054373","https://openalex.org/W2293974546","https://openalex.org/W1411719529","https://openalex.org/W192787926","https://openalex.org/W4233079211","https://openalex.org/W2000750027"],"abstract_inverted_index":{"The":[0],"source":[1],"code":[2],"in":[3],"C++,":[4],"along":[5],"with":[6],"the":[7],"Supplementary":[8],"Materials,":[9],"is":[10],"available":[11],"at:":[12],"http://gsp.tamu.edu/Publications/supplementary/zollanvari13/.":[13]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
