{"entities":{"Q1081998":{"pageid":1092750,"ns":120,"title":"Item:Q1081998","lastrevid":69595035,"modified":"2026-04-13T08:05:08Z","type":"item","id":"Q1081998","labels":{"en":{"language":"en","value":"An extreme value theory for sequence matching"}},"descriptions":{"en":{"language":"en","value":"scientific article; zbMATH DE number 3971966"}},"aliases":{},"claims":{"P31":[{"mainsnak":{"snaktype":"value","property":"P31","hash":"fd5912e4dab4b881a8eb0eb27e7893fef55176ad","datavalue":{"value":{"entity-type":"item","numeric-id":56887,"id":"Q56887"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q1081998$7208AC48-6638-42A7-B1C5-0C5583F03F81","rank":"normal"}],"P159":[{"mainsnak":{"snaktype":"value","property":"P159","hash":"7ebd6da8f67d796c65df9ab988d5efd02be5fe32","datavalue":{"value":{"text":"An extreme value theory for sequence matching","language":"en"},"type":"monolingualtext"},"datatype":"monolingualtext"},"type":"statement","id":"Q1081998$C11F0CAC-BD74-48D1-8B47-382D7FBA2A47","rank":"normal"}],"P225":[{"mainsnak":{"snaktype":"value","property":"P225","hash":"567cf8e6088adf4d7266587a990d62e228d30b9a","datavalue":{"value":"0602.62015","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q1081998$59E1CB41-0601-42C1-8515-ABAB9609F17B","rank":"normal"}],"P16":[{"mainsnak":{"snaktype":"value","property":"P16","hash":"ac21bf7a04a815c2e3aeb34521257315899f8b6e","datavalue":{"value":{"entity-type":"item","numeric-id":360355,"id":"Q360355"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q1081998$0D3B74B2-5351-4879-85D0-10DEFAF269A7","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P16","hash":"a6c0fb8a0c32205e68f0cd0149bfb7c7930e45f1","datavalue":{"value":{"entity-type":"item","numeric-id":795438,"id":"Q795438"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q1081998$31BD64A6-3672-4E52-9800-5D49DE32CCAD","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P16","hash":"8207abe0e0ba0a835bd033756c6fe396f59af93a","datavalue":{"value":{"entity-type":"item","numeric-id":242889,"id":"Q242889"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q1081998$A8AFB646-56EE-4C26-9B55-E28F38DCD46C","rank":"normal"}],"P200":[{"mainsnak":{"snaktype":"value","property":"P200","hash":"0b73f6da78562727d9e1c290db85e0053cdeb667","datavalue":{"value":{"entity-type":"item","numeric-id":60819,"id":"Q60819"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q1081998$F0950FC3-719D-439C-9B2B-854DFA59B1BF","rank":"normal"}],"P28":[{"mainsnak":{"snaktype":"value","property":"P28","hash":"63df7153432d81fa42019fcabb076c89649b0b5b","datavalue":{"value":{"time":"+1986-00-00T00:00:00Z","timezone":0,"before":0,"after":0,"precision":9,"calendarmodel":"http://www.wikidata.org/entity/Q1985727"},"type":"time"},"datatype":"time"},"type":"statement","id":"Q1081998$D95F2FB2-6ED1-48FA-87F0-B6494B712E4C","rank":"normal"}],"P1448":[{"mainsnak":{"snaktype":"value","property":"P1448","hash":"c62bac36acd136d5b266efc57deb77d58d3e3cc3","datavalue":{"value":"Suppose there are two finite sequences \\(X_ 1,X_ 2,...,X_ m\\) and \\(Y_ 1,Y_ 2,...,Y_ n\\) where the letters \\(\\{X_ i\\}\\) and \\(\\{Y_ j\\}\\) are chosen i.i.d. on a countable alphabet with \\(p=P\\{X_{\\ell}=Y_{\\ell}\\}\\in (0,1)\\). This paper studies the distribution of the longest contiguous run of matches between the X's and Y's, allowing at most k mismatches. The distribution is closely approximated by that of the maximum of (1-p)mn i.i.d. negative binomial random variables. The latter is shown to behave like the integer part of an extreme value distribution. Approximations to the expectation and the variance are found. The paper concludes with an example in which segments taken from the DNA sequence of the bacteriophage lambda are compared.    The authors attribute the lack of fit from asymptotic prediction to the small sample properties of the distribution of the maximum k-interrupted match run length. However, this reviewer's experience is that the i.i.d. assumption is usually not valid for such data, and so this may be the cause of the lack of fit. Corresponding results for the more difficult case of insertions and deletions are still outstanding.","type":"string"},"datatype":"string"},"type":"statement","id":"Q1081998$AE5CDFD6-D7BF-4A55-A35E-6C656A742D8E","rank":"normal"}],"P226":[{"mainsnak":{"snaktype":"value","property":"P226","hash":"111e6ab7e1421da23c7541a67fc8b00de58fc7a9","datavalue":{"value":"62E20","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q1081998$5446EB13-CE45-43A2-AD32-8976E8A0AF33","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P226","hash":"708a6f1a75f978962215fcdf6748c16c77f4fd6e","datavalue":{"value":"62P10","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q1081998$711D4F94-CA71-442C-9023-B7051D82EA3A","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P226","hash":"8acfb5681686a479769f1498162f25169e468cda","datavalue":{"value":"92D10","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q1081998$403078E4-41D1-408C-B8E1-33AE5C86F19E","rank":"normal"}],"P1451":[{"mainsnak":{"snaktype":"value","property":"P1451","hash":"8442ee17d21504d6178eaa8db218bdabcc125dc2","datavalue":{"value":"3971966","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q1081998$C42C9408-90A4-4C07-AF9D-7FCA6F51600F","rank":"normal"}],"P1450":[{"mainsnak":{"snaktype":"value","property":"P1450","hash":"ec67b25288c127ba5e42e187f6f34fa3ee60a6ee","datavalue":{"value":"distribution of the longest contiguous run of matches","type":"string"},"datatype":"string"},"type":"statement","id":"Q1081998$D94FDF02-89FB-4D0F-BFDC-0AC446171682","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"d959f86f5db72f910676b9df66c7c4bea75c41e9","datavalue":{"value":"negative binomial","type":"string"},"datatype":"string"},"type":"statement","id":"Q1081998$24ABB26C-C979-47D2-8201-D6D110B2DDCD","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"04b70f785c303f53f0f30d3b384389b4f4e9c374","datavalue":{"value":"extreme value distribution","type":"string"},"datatype":"string"},"type":"statement","id":"Q1081998$650C4167-F6F6-4C1A-ADE8-F2BFCA9E087E","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"dd4bda405b4daec10c0569d45b8bbd171546e9e4","datavalue":{"value":"DNA sequence","type":"string"},"datatype":"string"},"type":"statement","id":"Q1081998$9093BE97-E9BA-465C-B14D-FFEBDDA0C38E","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1450","hash":"d8e17fc80342225cf6a5641a9f88ea52e5b529c3","datavalue":{"value":"bacteriophage lambda","type":"string"},"datatype":"string"},"type":"statement","id":"Q1081998$566FA41A-BFCB-4379-9BAE-9C729C0B2130","rank":"normal"}],"P1447":[{"mainsnak":{"snaktype":"value","property":"P1447","hash":"30997e144e2ef50b65e8d3f1e48ea3a467b9054d","datavalue":{"value":{"entity-type":"item","numeric-id":458801,"id":"Q458801"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q1081998$D9B2837D-CB4C-4061-BFEA-0B74D3505489","rank":"normal"}],"P1460":[{"mainsnak":{"snaktype":"value","property":"P1460","hash":"57f7fea50d2ce1b39b695c4a1313582eed405e38","datavalue":{"value":{"entity-type":"item","numeric-id":5976449,"id":"Q5976449"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q1081998$9530031B-2BC9-45C4-AC02-323DF452CCAD","rank":"normal"}],"P205":[{"mainsnak":{"snaktype":"value","property":"P205","hash":"598eb09d74e088ac3d6326a7f190d87562279737","datavalue":{"value":"https://doi.org/10.1214/aos/1176350045","type":"string"},"datatype":"url"},"type":"statement","id":"Q1081998$EDBD0CF8-413E-4DC6-9BF5-658E52E3841C","rank":"normal"}],"P388":[{"mainsnak":{"snaktype":"value","property":"P388","hash":"5f3db747132c90e7b34011f3e777775375b64fae","datavalue":{"value":"W2093189601","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q1081998$4012E42C-B958-410F-9FA0-C154D5B17D20","rank":"normal"}],"P12":[{"mainsnak":{"snaktype":"value","property":"P12","hash":"ece1ed8c8d275e1ca174b209261f6683220b4364","datavalue":{"value":"Q104764149","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q1081998$1C2CBEF6-85DB-4EF9-B3FE-AE6B17AB20A2","rank":"normal"}],"P27":[{"mainsnak":{"snaktype":"value","property":"P27","hash":"2e63fa1fab75e5dcd108a6f7a12f9db7b16bbe22","datavalue":{"value":"10.1214/AOS/1176350045","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q1081998$C88784BE-1998-4CCC-9E65-5F89325C1F89","rank":"normal"}],"P1643":[{"mainsnak":{"snaktype":"value","property":"P1643","hash":"105a8b7f6ef17b22cc48921ac026987f6bdb3c5a","datavalue":{"value":{"entity-type":"item","numeric-id":3731417,"id":"Q3731417"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"6d9ea57927563a1ec09c0754b633b660ce875a02","datavalue":{"value":{"amount":"+0.8599497675895691","unit":"1"},"type":"quantity"},"datatype":"quantity"}],"P1660":[{"snaktype":"value","property":"P1660","hash":"a327a09ea0305e98d5cf33bd4036320e19f2aed0","datavalue":{"value":{"entity-type":"item","numeric-id":6821328,"id":"Q6821328"},"type":"wikibase-entityid"},"datatype":"wikibase-item"}]},"qualifiers-order":["P1659","P1660"],"id":"Q1081998$A0570056-3C93-4CB0-8F86-BE9AEA1F0952","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1643","hash":"1c82d864ba03790906b0e7a93e4666343754d2a3","datavalue":{"value":{"entity-type":"item","numeric-id":1920138,"id":"Q1920138"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"542d31ea14a0ba0531b1fd6939ceef55918f5cd7","datavalue":{"value":{"amount":"+0.845943808555603","unit":"1"},"type":"quantity"},"datatype":"quantity"}],"P1660":[{"snaktype":"value","property":"P1660","hash":"a327a09ea0305e98d5cf33bd4036320e19f2aed0","datavalue":{"value":{"entity-type":"item","numeric-id":6821328,"id":"Q6821328"},"type":"wikibase-entityid"},"datatype":"wikibase-item"}]},"qualifiers-order":["P1659","P1660"],"id":"Q1081998$0C86636E-BCB0-4D79-9FC7-0D11A6986BAE","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1643","hash":"26eaf1d7458e48202580c9cdf34ec72d6046f387","datavalue":{"value":{"entity-type":"item","numeric-id":1805569,"id":"Q1805569"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"542d31ea14a0ba0531b1fd6939ceef55918f5cd7","datavalue":{"value":{"amount":"+0.845943808555603","unit":"1"},"type":"quantity"},"datatype":"quantity"}],"P1660":[{"snaktype":"value","property":"P1660","hash":"a327a09ea0305e98d5cf33bd4036320e19f2aed0","datavalue":{"value":{"entity-type":"item","numeric-id":6821328,"id":"Q6821328"},"type":"wikibase-entityid"},"datatype":"wikibase-item"}]},"qualifiers-order":["P1659","P1660"],"id":"Q1081998$C1A1D573-48C2-4D18-B192-1FB26C5E2AB5","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1643","hash":"396779f8126420ae57778154252dcd75e829bee1","datavalue":{"value":{"entity-type":"item","numeric-id":3757093,"id":"Q3757093"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"1e9d31957504078c0ae424df7840531aa890f0de","datavalue":{"value":{"amount":"+0.8345478177070618","unit":"1"},"type":"quantity"},"datatype":"quantity"}],"P1660":[{"snaktype":"value","property":"P1660","hash":"a327a09ea0305e98d5cf33bd4036320e19f2aed0","datavalue":{"value":{"entity-type":"item","numeric-id":6821328,"id":"Q6821328"},"type":"wikibase-entityid"},"datatype":"wikibase-item"}]},"qualifiers-order":["P1659","P1660"],"id":"Q1081998$43BB3638-F50E-4561-8889-DC64486BB60B","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1643","hash":"d59d4b640da1926798691852f17755278e3e988d","datavalue":{"value":{"entity-type":"item","numeric-id":1064665,"id":"Q1064665"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1659":[{"snaktype":"value","property":"P1659","hash":"1f251a81de912ad432aea5cf08a9fb280831833b","datavalue":{"value":{"amount":"+0.8330159187316895","unit":"1"},"type":"quantity"},"datatype":"quantity"}],"P1660":[{"snaktype":"value","property":"P1660","hash":"a327a09ea0305e98d5cf33bd4036320e19f2aed0","datavalue":{"value":{"entity-type":"item","numeric-id":6821328,"id":"Q6821328"},"type":"wikibase-entityid"},"datatype":"wikibase-item"}]},"qualifiers-order":["P1659","P1660"],"id":"Q1081998$29A570C4-5E00-4388-B53F-58E646D18E1B","rank":"normal"}]},"sitelinks":{"mardi":{"site":"mardi","title":"An extreme value theory for sequence matching","badges":[],"url":"https://portal.mardi4nfdi.de/wiki/An_extreme_value_theory_for_sequence_matching"}}}}}