{"id":"https://openalex.org/W2066179253","doi":"https://doi.org/10.1145/1386118.1386122","title":"Confidence bounds for sampling-based group by estimates","display_name":"Confidence bounds for sampling-based group by estimates","publication_year":2008,"publication_date":"2008-08-01","ids":{"openalex":"https://openalex.org/W2066179253","doi":"https://doi.org/10.1145/1386118.1386122","mag":"2066179253"},"language":"en","primary_location":{"id":"doi:10.1145/1386118.1386122","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1386118.1386122","pdf_url":null,"source":{"id":"https://openalex.org/S90119964","display_name":"ACM Transactions on Database Systems","issn_l":"0362-5915","issn":["0362-5915","1557-4644"],"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":"ACM Transactions on Database Systems","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/A5015286019","display_name":"Fei Xu","orcid":"https://orcid.org/0000-0001-9274-5971"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fei Xu","raw_affiliation_strings":["University of Florida, Gainesville, Gainesville, FL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Florida, Gainesville, Gainesville, FL","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109437922","display_name":"Christopher Jermaine","orcid":null},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher Jermaine","raw_affiliation_strings":["University of Florida, Gainesville, Gainesville, FL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Florida, Gainesville, Gainesville, FL","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008335723","display_name":"Alin Dobra","orcid":"https://orcid.org/0000-0003-2033-9952"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alin Dobra","raw_affiliation_strings":["University of Florida, Gainesville, Gainesville, FL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Florida, Gainesville, Gainesville, FL","institution_ids":["https://openalex.org/I33213144"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7628,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.76381502,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"33","issue":"3","first_page":"1","last_page":"44"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9998000264167786,"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":0.9998000264167786,"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/T11106","display_name":"Data Management and Algorithms","score":0.998199999332428,"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"}},{"id":"https://openalex.org/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9927999973297119,"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/computer-science","display_name":"Computer science","score":0.855175793170929},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.7187544107437134},{"id":"https://openalex.org/keywords/confidence-interval","display_name":"Confidence interval","score":0.5724884271621704},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5563877820968628},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.5282289981842041},{"id":"https://openalex.org/keywords/point-estimation","display_name":"Point estimation","score":0.5272197723388672},{"id":"https://openalex.org/keywords/group","display_name":"Group (periodic table)","score":0.5174092054367065},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4826972484588623},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4421060085296631},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.41329631209373474},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.36364448070526123},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.3157877027988434},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2922062277793884},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09354320168495178}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.855175793170929},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.7187544107437134},{"id":"https://openalex.org/C44249647","wikidata":"https://www.wikidata.org/wiki/Q208498","display_name":"Confidence interval","level":2,"score":0.5724884271621704},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5563877820968628},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.5282289981842041},{"id":"https://openalex.org/C41426520","wikidata":"https://www.wikidata.org/wiki/Q1192065","display_name":"Point estimation","level":2,"score":0.5272197723388672},{"id":"https://openalex.org/C2781311116","wikidata":"https://www.wikidata.org/wiki/Q83306","display_name":"Group (periodic table)","level":2,"score":0.5174092054367065},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4826972484588623},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4421060085296631},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.41329631209373474},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36364448070526123},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3157877027988434},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2922062277793884},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09354320168495178},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1386118.1386122","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1386118.1386122","pdf_url":null,"source":{"id":"https://openalex.org/S90119964","display_name":"ACM Transactions on Database Systems","issn_l":"0362-5915","issn":["0362-5915","1557-4644"],"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":"ACM Transactions on Database Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W130710483","https://openalex.org/W1513100972","https://openalex.org/W1521708890","https://openalex.org/W1968829657","https://openalex.org/W1982516880","https://openalex.org/W1985093013","https://openalex.org/W1988144572","https://openalex.org/W1991567646","https://openalex.org/W1993482412","https://openalex.org/W1997917263","https://openalex.org/W2020147322","https://openalex.org/W2020584928","https://openalex.org/W2029685080","https://openalex.org/W2058991275","https://openalex.org/W2078907037","https://openalex.org/W2105381419","https://openalex.org/W2107422095","https://openalex.org/W2110065044","https://openalex.org/W2115012618","https://openalex.org/W2117348908","https://openalex.org/W2121044470","https://openalex.org/W2126843316","https://openalex.org/W2139276812","https://openalex.org/W2142257425","https://openalex.org/W2148706674","https://openalex.org/W2153834102","https://openalex.org/W2154165046","https://openalex.org/W2197881366","https://openalex.org/W2199389590","https://openalex.org/W2296677182","https://openalex.org/W2322523654","https://openalex.org/W2796677525","https://openalex.org/W2799002609","https://openalex.org/W4205210034","https://openalex.org/W4229903866","https://openalex.org/W4241185933","https://openalex.org/W4242587584","https://openalex.org/W4246899237","https://openalex.org/W4250212406","https://openalex.org/W4292691288","https://openalex.org/W7011679150"],"related_works":["https://openalex.org/W1585007175","https://openalex.org/W2382521049","https://openalex.org/W2144385241","https://openalex.org/W4300101996","https://openalex.org/W2165950148","https://openalex.org/W4253593777","https://openalex.org/W2951497643","https://openalex.org/W4403053866","https://openalex.org/W2142393343","https://openalex.org/W2338854850"],"abstract_inverted_index":{"Sampling":[0],"is":[1,19,72,102],"now":[2],"a":[3,39,46,53,58,70,98],"very":[4,40,103],"important":[5],"data":[6],"management":[7],"tool,":[8],"to":[9,52,68,80,108,120,126,134],"such":[10,69,112],"an":[11,14],"extent":[12],"that":[13,73],"interface":[15],"for":[16,49,65,87,116],"database":[17],"sampling":[18,64],"included":[20],"in":[21,31],"the":[22,43,50,66,74,82,85,94,121,135],"latest":[23],"SQL":[24],"standard.":[25],"In":[26],"this":[27,128],"article":[28],"we":[29],"reconsider":[30],"depth":[32],"what":[33],"at":[34],"first":[35],"may":[36],"seem":[37],"like":[38],"simple":[41],"problem\u2014computing":[42],"error":[44],"of":[45,84,138],"sampling-based":[47],"guess":[48,81],"answer":[51,67],"GROUP":[54],"BY":[55],"query":[56,71,86],"over":[57],"multitable":[59],"join.":[60],"The":[61],"difficulty":[62],"when":[63],"same":[75],"sample":[76],"will":[77],"be":[78],"used":[79],"result":[83],"each":[88],"group,":[89],"which":[90],"induces":[91],"correlations":[92],"among":[93],"estimates.":[95],"Thus,":[96],"from":[97],"statistical":[99],"point-of-view":[100],"it":[101],"problematic":[104],"and":[105,130],"even":[106],"dangerous":[107],"use":[109],"traditional":[110],"methods":[111],"as":[113],"confidence":[114,141],"intervals":[115],"communicating":[117],"estimate":[118],"accuracy":[119],"user.":[122],"We":[123],"explore":[124],"ways":[125],"address":[127],"problem,":[129],"pay":[131],"particular":[132],"attention":[133],"computational":[136],"aspects":[137],"computing":[139],"\u201csafe\u201d":[140],"intervals.":[142]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}