{"id":"https://openalex.org/W1983170052","doi":"https://doi.org/10.14778/2350229.2350279","title":"Statistical distortion","display_name":"Statistical distortion","publication_year":2012,"publication_date":"2012-07-01","ids":{"openalex":"https://openalex.org/W1983170052","doi":"https://doi.org/10.14778/2350229.2350279","mag":"1983170052"},"language":"en","primary_location":{"id":"doi:10.14778/2350229.2350279","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2350229.2350279","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086114454","display_name":"Tamraparni Dasu","orcid":null},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tamraparni Dasu","raw_affiliation_strings":["AT&T Labs Research, NJ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AT&T Labs Research, NJ","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111811331","display_name":"Ji Meng Loh","orcid":null},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ji Meng Loh","raw_affiliation_strings":["AT&T Labs Research, NJ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AT&T Labs Research, NJ","institution_ids":["https://openalex.org/I1283103587"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1283103587"],"apc_list":null,"apc_paid":null,"fwci":5.2145,"has_fulltext":false,"cited_by_count":76,"citation_normalized_percentile":{"value":0.95174428,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"5","issue":"11","first_page":"1674","last_page":"1683"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.996399998664856,"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/T11614","display_name":"Cloud Data Security Solutions","score":0.9889000058174133,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/glitch","display_name":"Glitch","score":0.7231891751289368},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.7123529314994812},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.7093883156776428},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6411409378051758},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.6107160449028015},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5611971616744995},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5489748120307922},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.49451467394828796},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.42733627557754517},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.32999682426452637},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3281887173652649},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2401089072227478},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1516716182231903},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.1408301591873169}],"concepts":[{"id":"https://openalex.org/C191287063","wikidata":"https://www.wikidata.org/wiki/Q543281","display_name":"Glitch","level":3,"score":0.7231891751289368},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.7123529314994812},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.7093883156776428},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6411409378051758},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.6107160449028015},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5611971616744995},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5489748120307922},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.49451467394828796},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.42733627557754517},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.32999682426452637},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3281887173652649},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2401089072227478},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1516716182231903},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1408301591873169},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/2350229.2350279","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2350229.2350279","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.5099999904632568,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1979819093","https://openalex.org/W2004291985","https://openalex.org/W2026140005","https://openalex.org/W2031913229","https://openalex.org/W2085845250","https://openalex.org/W2117366235","https://openalex.org/W2133354554","https://openalex.org/W2137243801","https://openalex.org/W2164187405","https://openalex.org/W2165528679","https://openalex.org/W2171235719","https://openalex.org/W2171332293","https://openalex.org/W2278337674","https://openalex.org/W4236318182"],"related_works":["https://openalex.org/W2364921833","https://openalex.org/W2302028273","https://openalex.org/W1525643724","https://openalex.org/W2067938758","https://openalex.org/W2382623646","https://openalex.org/W3087771547","https://openalex.org/W2333420780","https://openalex.org/W2375199418","https://openalex.org/W2368437561","https://openalex.org/W1983170052"],"abstract_inverted_index":{"We":[0,19,65],"introduce":[1],"the":[2,13,58],"notion":[3],"of":[4,15,61,77],"statistical":[5,42,59],"distortion":[6,43],"as":[7],"an":[8],"essential":[9],"metric":[10,22],"for":[11,32],"measuring":[12],"effectiveness":[14],"data":[16,34,62],"cleaning":[17,35,63],"strategies.":[18,64],"use":[20],"this":[21],"to":[23],"propose":[24],"a":[25,74],"widely":[26],"applicable":[27],"yet":[28],"scalable":[29],"experimental":[30],"framework":[31,68],"evaluating":[33],"strategies":[36],"along":[37],"three":[38],"dimensions:":[39],"glitch":[40,51],"improvement,":[41],"and":[44,53,79],"cost-related":[45],"criteria.":[46],"Existing":[47],"metrics":[48],"focus":[49],"on":[50,57,69],"improvement":[52],"cost,":[54],"but":[55],"not":[56],"impact":[60],"illustrate":[66],"our":[67],"real":[70],"world":[71],"data,":[72],"with":[73],"comprehensive":[75],"suite":[76],"experiments":[78],"analyses.":[80]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":27},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2025-10-10T00:00:00"}