{"id":"https://openalex.org/W4205360603","doi":"https://doi.org/10.1109/bigdata52589.2021.9671301","title":"When to Re-Draw a Sample, and Why","display_name":"When to Re-Draw a Sample, and Why","publication_year":2021,"publication_date":"2021-12-15","ids":{"openalex":"https://openalex.org/W4205360603","doi":"https://doi.org/10.1109/bigdata52589.2021.9671301"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata52589.2021.9671301","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata52589.2021.9671301","pdf_url":null,"source":{"id":"https://openalex.org/S4363607718","display_name":"2021 IEEE International Conference on Big Data (Big Data)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-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/A5020075641","display_name":"Eric Bax","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Eric Bax","raw_affiliation_strings":["Yahoo!, Playa Vista, CA, USA"],"affiliations":[{"raw_affiliation_string":"Yahoo!, Playa Vista, CA, USA","institution_ids":["https://openalex.org/I4210134091"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5020075641"],"corresponding_institution_ids":["https://openalex.org/I4210134091"],"apc_list":null,"apc_paid":null,"fwci":0.308,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.4175168,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"6","issue":null,"first_page":"5848","last_page":"5850"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9943000078201294,"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"}},{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9900000095367432,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/statistic","display_name":"Statistic","score":0.8298096656799316},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.7064654231071472},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.6235657930374146},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.542993426322937},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5387637615203857},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5362815856933594},{"id":"https://openalex.org/keywords/sufficient-statistic","display_name":"Sufficient statistic","score":0.5290844440460205},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.5147886276245117},{"id":"https://openalex.org/keywords/sample-size-determination","display_name":"Sample size determination","score":0.5101140141487122},{"id":"https://openalex.org/keywords/order-statistic","display_name":"Order statistic","score":0.476536363363266},{"id":"https://openalex.org/keywords/sample-mean-and-sample-covariance","display_name":"Sample mean and sample covariance","score":0.46846291422843933},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.34086692333221436},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.292842298746109},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.07961806654930115}],"concepts":[{"id":"https://openalex.org/C89128539","wikidata":"https://www.wikidata.org/wiki/Q1949963","display_name":"Statistic","level":2,"score":0.8298096656799316},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.7064654231071472},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.6235657930374146},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.542993426322937},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5387637615203857},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5362815856933594},{"id":"https://openalex.org/C178197554","wikidata":"https://www.wikidata.org/wiki/Q1099110","display_name":"Sufficient statistic","level":2,"score":0.5290844440460205},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.5147886276245117},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.5101140141487122},{"id":"https://openalex.org/C44082924","wikidata":"https://www.wikidata.org/wiki/Q1767128","display_name":"Order statistic","level":2,"score":0.476536363363266},{"id":"https://openalex.org/C181243257","wikidata":"https://www.wikidata.org/wiki/Q1693522","display_name":"Sample mean and sample covariance","level":3,"score":0.46846291422843933},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.34086692333221436},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.292842298746109},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.07961806654930115},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata52589.2021.9671301","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata52589.2021.9671301","pdf_url":null,"source":{"id":"https://openalex.org/S4363607718","display_name":"2021 IEEE International Conference on Big Data (Big Data)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1595687138","https://openalex.org/W1767521945","https://openalex.org/W1786332878","https://openalex.org/W2002722920","https://openalex.org/W2113046370","https://openalex.org/W2119885577","https://openalex.org/W2132591512","https://openalex.org/W2164530213","https://openalex.org/W2979241111","https://openalex.org/W3008169632","https://openalex.org/W3009557165","https://openalex.org/W3097698191","https://openalex.org/W4233413206","https://openalex.org/W4251617391","https://openalex.org/W4299328742","https://openalex.org/W6638039407","https://openalex.org/W6638289159","https://openalex.org/W6681441104","https://openalex.org/W6684836731"],"related_works":["https://openalex.org/W2511265471","https://openalex.org/W2003768768","https://openalex.org/W2506732374","https://openalex.org/W2773879317","https://openalex.org/W2794698711","https://openalex.org/W2951012264","https://openalex.org/W3048493158","https://openalex.org/W1519919444","https://openalex.org/W2111127897","https://openalex.org/W2904683338"],"abstract_inverted_index":{"One":[0],"way":[1],"to":[2,12,45,69,89],"estimate":[3,33],"a":[4,7,14],"statistic":[5,27,36],"over":[6,28,37,100],"large":[8],"data":[9,22,39],"set":[10],"is":[11],"draw":[13],"sample":[15,30,52,79],"consisting":[16],"of":[17,34,66,93,98],"some":[18],"records":[19],"from":[20],"the":[21,26,29,35,38,64,77,91],"set,":[23],"and":[24,58],"compute":[25],"as":[31],"an":[32,47],"set.":[40],"This":[41],"procedure":[42],"may":[43,80],"fail":[44],"produce":[46,70],"accurate":[48,71],"estimate.":[49],"Using":[50],"one":[51,101],"for":[53,96],"multiple":[54,67,94],"statistics":[55],"reduces":[56],"computation":[57],"latency,":[59],"but":[60],"it":[61],"can":[62],"increase":[63],"probability":[65,92],"failures":[68,95],"estimates,":[72],"because":[73],"estimates":[74,99],"based":[75],"on":[76],"same":[78],"not":[81],"have":[82],"independent":[83],"failure":[84],"probabilities.":[85],"We":[86],"show":[87],"how":[88],"bound":[90],"sequences":[97],"or":[102],"more":[103],"samples.":[104]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}