{"id":"https://openalex.org/W2205260688","doi":"https://doi.org/10.1109/bigdata.2015.7363746","title":"Data streaming algorithms for the Kolmogorov-Smirnov test","display_name":"Data streaming algorithms for the Kolmogorov-Smirnov test","publication_year":2015,"publication_date":"2015-10-01","ids":{"openalex":"https://openalex.org/W2205260688","doi":"https://doi.org/10.1109/bigdata.2015.7363746","mag":"2205260688"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2015.7363746","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2015.7363746","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 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/A5085185917","display_name":"Ashwin Lall","orcid":"https://orcid.org/0009-0003-2046-0055"},"institutions":[{"id":"https://openalex.org/I20577493","display_name":"Denison University","ror":"https://ror.org/05pqx1c24","country_code":"US","type":"education","lineage":["https://openalex.org/I20577493"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ashwin Lall","raw_affiliation_strings":["Department of Mathematics and Computer Science, Denison University, Granville, OH, USA"],"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Computer Science, Denison University, Granville, OH, USA","institution_ids":["https://openalex.org/I20577493"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5085185917"],"corresponding_institution_ids":["https://openalex.org/I20577493"],"apc_list":null,"apc_paid":null,"fwci":2.1572,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.90330217,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"95","last_page":"104"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9993000030517578,"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"}},"topics":[{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9993000030517578,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9973999857902527,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9950000047683716,"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/kolmogorov\u2013smirnov-test","display_name":"Kolmogorov\u2013Smirnov test","score":0.8856077194213867},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.611146092414856},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.6106396317481995},{"id":"https://openalex.org/keywords/streaming-algorithm","display_name":"Streaming algorithm","score":0.5528700351715088},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5486338138580322},{"id":"https://openalex.org/keywords/statistical-hypothesis-testing","display_name":"Statistical hypothesis testing","score":0.5253733396530151},{"id":"https://openalex.org/keywords/streaming-data","display_name":"Streaming data","score":0.5189361572265625},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.49151095747947693},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.47326114773750305},{"id":"https://openalex.org/keywords/data-stream","display_name":"Data stream","score":0.469117671251297},{"id":"https://openalex.org/keywords/sample-size-determination","display_name":"Sample size determination","score":0.4563380777835846},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.4523719549179077},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4352363646030426},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4284627139568329},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.42839640378952026},{"id":"https://openalex.org/keywords/sample-space","display_name":"Sample space","score":0.4259493947029114},{"id":"https://openalex.org/keywords/sampling-distribution","display_name":"Sampling distribution","score":0.411957323551178},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.3269772529602051},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.304951548576355},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27374744415283203},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.08545276522636414}],"concepts":[{"id":"https://openalex.org/C82581908","wikidata":"https://www.wikidata.org/wiki/Q575766","display_name":"Kolmogorov\u2013Smirnov test","level":3,"score":0.8856077194213867},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.611146092414856},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.6106396317481995},{"id":"https://openalex.org/C187166803","wikidata":"https://www.wikidata.org/wiki/Q2835831","display_name":"Streaming algorithm","level":3,"score":0.5528700351715088},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5486338138580322},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.5253733396530151},{"id":"https://openalex.org/C2777611316","wikidata":"https://www.wikidata.org/wiki/Q39045282","display_name":"Streaming data","level":2,"score":0.5189361572265625},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.49151095747947693},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.47326114773750305},{"id":"https://openalex.org/C2778484313","wikidata":"https://www.wikidata.org/wiki/Q1172540","display_name":"Data stream","level":2,"score":0.469117671251297},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.4563380777835846},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.4523719549179077},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4352363646030426},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4284627139568329},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.42839640378952026},{"id":"https://openalex.org/C100279318","wikidata":"https://www.wikidata.org/wiki/Q467440","display_name":"Sample space","level":2,"score":0.4259493947029114},{"id":"https://openalex.org/C167723999","wikidata":"https://www.wikidata.org/wiki/Q3773214","display_name":"Sampling distribution","level":2,"score":0.411957323551178},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3269772529602051},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.304951548576355},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27374744415283203},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.08545276522636414},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2015.7363746","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2015.7363746","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 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":25,"referenced_works":["https://openalex.org/W1766932551","https://openalex.org/W1967361896","https://openalex.org/W1981663184","https://openalex.org/W2010729689","https://openalex.org/W2042518617","https://openalex.org/W2042620791","https://openalex.org/W2043843644","https://openalex.org/W2077599515","https://openalex.org/W2078764670","https://openalex.org/W2080234606","https://openalex.org/W2091567345","https://openalex.org/W2094835873","https://openalex.org/W2099941470","https://openalex.org/W2108214384","https://openalex.org/W2109885200","https://openalex.org/W2112452856","https://openalex.org/W2114944618","https://openalex.org/W2120587290","https://openalex.org/W2134169350","https://openalex.org/W2136987366","https://openalex.org/W2154721480","https://openalex.org/W2156896296","https://openalex.org/W2161118867","https://openalex.org/W2162914161","https://openalex.org/W2189948602"],"related_works":["https://openalex.org/W3191101401","https://openalex.org/W2241126753","https://openalex.org/W1824789409","https://openalex.org/W2991654599","https://openalex.org/W201138236","https://openalex.org/W3122033752","https://openalex.org/W2128692898","https://openalex.org/W2398953209","https://openalex.org/W1733902306","https://openalex.org/W3002138439"],"abstract_inverted_index":{"We":[0,113,129],"propose":[1],"space-efficient":[2],"algorithms":[3,98,119,133],"for":[4,19,99,107],"performing":[5],"the":[6,21,46,60,72,81,91,101,104,115,143],"Kolmogorov-Smirnov":[7,13,55],"test":[8,14,18,144],"on":[9,123],"streaming":[10],"data.":[11,152],"The":[12],"is":[15,29,68,87],"a":[16,24,32,63,111],"non-parametric":[17],"measuring":[20],"strength":[22],"of":[23,41,93,117,148],"hypothesis":[25],"that":[26,38,59,85,131,139],"some":[27,52],"data":[28,42,108],"drawn":[30,44],"from":[31,45],"fixed":[33],"distribution":[34,48,61],"(one-sample":[35],"test),":[36],"or":[37],"two":[39],"sets":[40],"are":[43,134],"same":[47],"(two-sample":[49],"test).":[50],"Unlike":[51],"other":[53,83],"tests,":[54],"does":[56],"not":[57,77],"assume":[58],"has":[62],"known":[64],"form":[65],"(e.g.,":[66],"it":[67,75,86],"normal),":[69],"and":[70,103,126,138],"in":[71,110,151],"two-sample":[73,105],"case":[74],"need":[76],"know":[78],"anything":[79],"about":[80],"distribution,":[82],"than":[84],"continuous.":[88],"Motivated":[89],"by":[90],"challenges":[92],"big":[94],"data,":[95],"we":[96],"present":[97],"both":[100,124],"one-sample":[102],"tests":[106],"processed":[109],"stream.":[112],"demonstrate":[114],"accuracy":[116],"our":[118,132],"via":[120],"extensive":[121],"experimentation":[122],"real":[125],"synthetic":[127],"datasets.":[128],"show":[130],"superior":[135],"to":[136],"sampling":[137],"they":[140],"accurately":[141],"perform":[142],"with":[145],"several":[146],"orders":[147],"magnitude":[149],"reduction":[150]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}