{"id":"https://openalex.org/W2020730439","doi":"https://doi.org/10.1080/00207720500159995","title":"Comparing software fault predictions of pure and zero-inflated Poisson regression models","display_name":"Comparing software fault predictions of pure and zero-inflated Poisson regression models","publication_year":2005,"publication_date":"2005-09-15","ids":{"openalex":"https://openalex.org/W2020730439","doi":"https://doi.org/10.1080/00207720500159995","mag":"2020730439"},"language":"en","primary_location":{"id":"doi:10.1080/00207720500159995","is_oa":false,"landing_page_url":"https://doi.org/10.1080/00207720500159995","pdf_url":null,"source":{"id":"https://openalex.org/S129640837","display_name":"International Journal of Systems Science","issn_l":"0020-7721","issn":["0020-7721","1464-5319"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Systems Science","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/A5089170562","display_name":"Taghi M. Khoshgoftaar","orcid":null},"institutions":[{"id":"https://openalex.org/I63772739","display_name":"Florida Atlantic University","ror":"https://ror.org/05p8w6387","country_code":"US","type":"education","lineage":["https://openalex.org/I63772739"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Taghi M. Khoshgoftaar *","raw_affiliation_strings":["\n Department of Computer Science and Engineering, Florida Atlantic University, Boca Raton, Fl. 33431, USA","Department of Computer Science and Engineering Florida Atlantic University Boca Raton, FL 33431 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\n Department of Computer Science and Engineering, Florida Atlantic University, Boca Raton, Fl. 33431, USA","institution_ids":["https://openalex.org/I63772739"]},{"raw_affiliation_string":"Department of Computer Science and Engineering Florida Atlantic University Boca Raton, FL 33431 USA","institution_ids":["https://openalex.org/I63772739"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109235962","display_name":"Kehan Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I203331390","display_name":"Eastern Connecticut State University","ror":"https://ror.org/01mhgwt57","country_code":"US","type":"education","lineage":["https://openalex.org/I203331390","https://openalex.org/I4210132746"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kehan Gao","raw_affiliation_strings":["\n Department of Mathematics and Computer Science, Eastern Connecticut State University, Willimantic, Ct. 06226, USA","Department of Mathematics and Computer Science, Eastern Connecticut State University, Willimantic, CT 06226, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\n Department of Mathematics and Computer Science, Eastern Connecticut State University, Willimantic, Ct. 06226, USA","institution_ids":["https://openalex.org/I203331390"]},{"raw_affiliation_string":"Department of Mathematics and Computer Science, Eastern Connecticut State University, Willimantic, CT 06226, USA","institution_ids":["https://openalex.org/I203331390"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034734184","display_name":"R. Szab\u00f3","orcid":"https://orcid.org/0000-0002-3258-1909"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I2802769386","display_name":"Boca Raton Regional Hospital","ror":"https://ror.org/01phhgk62","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1302444339","https://openalex.org/I2802769386"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robert M. Szabo","raw_affiliation_strings":["\n IBM Corporation, Boca Raton, Florida 33487, USA","IBM Corporation , Boca Raton, Florida 33487, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\n IBM Corporation, Boca Raton, Florida 33487, USA","institution_ids":["https://openalex.org/I2802769386"]},{"raw_affiliation_string":"IBM Corporation , Boca Raton, Florida 33487, USA","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4872,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.83239474,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"36","issue":"11","first_page":"705","last_page":"715"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12423","display_name":"Software Reliability and Analysis Research","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T10260","display_name":"Software Engineering Research","score":0.9990000128746033,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9696000218391418,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/poisson-distribution","display_name":"Poisson distribution","score":0.6943510174751282},{"id":"https://openalex.org/keywords/poisson-regression","display_name":"Poisson regression","score":0.6839301586151123},{"id":"https://openalex.org/keywords/software-quality","display_name":"Software quality","score":0.5731316208839417},{"id":"https://openalex.org/keywords/count-data","display_name":"Count data","score":0.5455621480941772},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5242072343826294},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.5034045577049255},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4953871965408325},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4710124731063843},{"id":"https://openalex.org/keywords/regression-analysis","display_name":"Regression analysis","score":0.4625709652900696},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.40669238567352295},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.37410181760787964},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.35463035106658936},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14659741520881653},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.09675487875938416},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.08387050032615662}],"concepts":[{"id":"https://openalex.org/C100906024","wikidata":"https://www.wikidata.org/wiki/Q205692","display_name":"Poisson distribution","level":2,"score":0.6943510174751282},{"id":"https://openalex.org/C73269764","wikidata":"https://www.wikidata.org/wiki/Q954529","display_name":"Poisson regression","level":3,"score":0.6839301586151123},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.5731316208839417},{"id":"https://openalex.org/C33643355","wikidata":"https://www.wikidata.org/wiki/Q5176731","display_name":"Count data","level":3,"score":0.5455621480941772},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5242072343826294},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.5034045577049255},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4953871965408325},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4710124731063843},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.4625709652900696},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.40669238567352295},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.37410181760787964},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.35463035106658936},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14659741520881653},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.09675487875938416},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.08387050032615662},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1080/00207720500159995","is_oa":false,"landing_page_url":"https://doi.org/10.1080/00207720500159995","pdf_url":null,"source":{"id":"https://openalex.org/S129640837","display_name":"International Journal of Systems Science","issn_l":"0020-7721","issn":["0020-7721","1464-5319"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Systems Science","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1830719945","https://openalex.org/W1847801368","https://openalex.org/W1978397386","https://openalex.org/W2005903772","https://openalex.org/W2009141244","https://openalex.org/W2029833477","https://openalex.org/W2041320945","https://openalex.org/W2119634512","https://openalex.org/W2139506929","https://openalex.org/W2149493527","https://openalex.org/W2159747233","https://openalex.org/W2161850932","https://openalex.org/W3121402432","https://openalex.org/W4243820718","https://openalex.org/W4302853952"],"related_works":["https://openalex.org/W1578743158","https://openalex.org/W3088295586","https://openalex.org/W2060931646","https://openalex.org/W1590941618","https://openalex.org/W3210390693","https://openalex.org/W2503331259","https://openalex.org/W3134844154","https://openalex.org/W3096804274","https://openalex.org/W2270206682","https://openalex.org/W2759839044"],"abstract_inverted_index":{"Abstract":[0],"Predicting":[1],"the":[2,26,35,49,52,68,109,122,158,164,187,200,219,226,237,259,270,273,339,344,355,359,369,373,406,413,417,430,453,491,496,505,523,531,572,574,591],"software":[3,41,72,126,133,283,285,287,469,471,473,608,611],"quality":[4,243,290,476,609,612],"prior":[5],"to":[6,13,47],"system":[7],"tests":[8],"and":[9,144,160,172,190,228,264,269,289,299,319,330,348,368,396,410,424,457,475,483,495,530,586,596,614],"operations":[10],"has":[11,303,314,385,399],"proven":[12],"be":[14],"useful":[15],"for":[16,33,341,498,593,616],"achieving":[17],"effective":[18],"reliability":[19,288,474],"improvements.":[20],"Poisson":[21,94,105,143,189,246],"(pure)":[22],"regression":[23,95,146],"modelling":[24,31,192],"is":[25,44,57,61,255,335,411,447,487,549,568],"most":[27],"commonly":[28],"used":[29],"count":[30],"technique":[32],"predicting":[34],"expected":[36],"number":[37,324],"of":[38,51,81,112,178,258,261,272,325,338,358,372,379,391,405,416,455,490,571,590],"faults":[39],"in":[40,71,86,116,214,233,282,310,322,433,444,452,508,519,527,538,555],"modules.":[42],"It":[43],"best":[45],"suited":[46],"when":[48],"distribution":[50],"fault":[53,63,73,101],"data":[54,74,127,155,162,165,239,297,484,619],"(dependent":[55],"variable)":[56],"not":[58],"biased,":[59],"that":[60,199,218],"equidispersed":[62],"data,":[64],"whose":[65],"mean":[66,110],"equals":[67],"variance.":[69],"However,":[70],"we":[75,124],"often":[76],"observe":[77],"a":[78,92,113,130,153,256,316,323,336,488,551,569],"large":[79],"portion":[80],"zeros":[82],"(no":[83],"faults),":[84],"especially":[85],"high-assurance":[87],"systems.":[88],"In":[89],"such":[90],"cases":[91],"pure":[93,142,188],"model":[96,107,202,221],"(PRM)":[97],"may":[98],"yield":[99],"inaccurate":[100],"predictions.":[102],"A":[103,182],"zero-inflated":[104],"(ZIP)":[106],"changes":[108],"structure":[111],"PRM,":[114],"resulting":[115],"improved":[117],"predictive":[118],"quality.":[119],"To":[120,148],"illustrate":[121],"same,":[123],"examined":[125],"collected":[128],"from":[129,436,511,541],"full-scale":[131],"industrial":[132],"system.":[134],"Fault":[135],"prediction":[136,234],"models":[137,173],"were":[138,174],"calibrated":[139,175],"using":[140,176],"both":[141],"ZIP":[145,191,201,220],"techniques.":[147],"prevent":[149],"claims":[150],"based":[151],"on":[152,363,377,387,412],"biased":[154],"split":[156,169,180],"(for":[157],"fit":[159],"test":[161,185,197],"sets),":[163],"set":[166],"was":[167,194],"randomly":[168],"50":[170,238],"times,":[171],"each":[177],"these":[179,311],"combinations.":[181],"comparative":[183,211],"hypothesis":[184,248],"between":[186],"techniques":[193],"performed.":[195],"The":[196],"revealed":[198],"fitted":[203],"better":[204,223,231],"than":[205,225,306],"its":[206],"counterpart.":[207],"Our":[208],"comprehensive":[209],"empirical":[210],"study":[212],"presented":[213],"this":[215],"paper":[216],"showed":[217],"yielded":[222],"predictions":[224],"PRM":[227],"also":[229],"demonstrated":[230],"robustness":[232],"accuracy":[235],"across":[236],"splits.":[240],"Keywords:":[241],"Software":[242,275,364,407,420,422,557,576],"estimationPoisson":[244],"regressionZero-inflated":[245],"regressionComparative":[247],"testPerformance":[249],"metrics":[250],"Acknowledgments":[251],"Taghi":[252],"M.":[253,502],"Khoshgoftaar":[254],"professor":[257],"Department":[260,454],"Computer":[262,346,380,434,458,493],"Science":[263,459],"Engineering,":[265,421],"Florida":[266,437,512,579],"Atlantic":[267,438,513,580],"University":[268],"Director":[271],"Empirical":[274,419,575],"Engineering":[276,366,378,435,577],"Laboratory.":[277],"His":[278,604],"research":[279,466,605],"interests":[280,467,606],"are":[281],"engineering,":[284,291,470,477,610],"metrics,":[286,472],"computational":[292,481],"intelligence,":[293,482],"computer":[294,478,509,528,539],"performance":[295,479],"evaluation,":[296],"mining,":[298],"statistical":[300],"modeling.":[301],"He":[302,313,334,352,398,521,548,567],"published":[304],"more":[305],"200":[307],"refereed":[308],"papers":[309],"areas.":[312],"been":[315],"principal":[317],"investigator":[318],"project":[320],"leader":[321],"projects":[326],"with":[327],"industry,":[328],"government,":[329],"other":[331],"research-sponsoring":[332],"agencies.":[333],"member":[337,489,570],"Association":[340,497],"Computing":[342,499],"Machinery,":[343],"IEEE":[345,349,492],"Society,":[347],"Reliability":[350,365],"Society.":[351],"served":[353,386,400],"as":[354,401],"general":[356,370],"chair":[357,371],"1999":[360],"International":[361,375],"Symposium":[362],"(ISSRE\u201999),":[367],"2001":[374],"Conference":[376],"Based":[381],"Systems.":[382,426],"Also,":[383],"he":[384],"technical":[388],"program":[389],"committees":[390],"various":[392],"international":[393],"conferences,":[394],"symposia,":[395],"workshops.":[397],"North":[402],"American":[403],"editor":[404],"Quality":[408],"Journal,":[409],"editorial":[414],"boards":[415],"journals":[418],"Quality,":[423],"Fuzzy":[425],"Kehan":[427],"Gao":[428],"received":[429,504,522],"Ph.D.":[431,506],"degree":[432,507,525,533],"University,":[439,514,544,581,600],"Boca":[440,515,563,582],"Raton,":[441,516,564,583],"FL,":[442,517,565,584],"USA,":[443],"2003.":[445],"She":[446,486],"currently":[448,550],"an":[449,587],"Assistant":[450],"Professor":[451],"Mathematics":[456],"at":[460],"Eastern":[461],"Connecticut":[462],"State":[463,543],"University.":[464],"Her":[465],"include":[468,607],"modeling,":[480,613],"mining.":[485,620],"Society":[494],"Machinery.":[500],"Robert":[501],"Szabo":[503],"science":[510,529,540],"USA":[518],"1995.":[520],"M.S.":[524],"(1981)":[526],"B.S.":[532],"(1980,":[534],"Summa":[535],"Cum":[536],"Laude)":[537],"Cleveland":[542],"Cleveland,":[545],"OH,":[546],"USA.":[547,566,603],"Senior":[552],"I/T":[553],"Architect":[554],"IBM":[556],"Group,":[558],"Public":[559],"Sector":[560],"Solutions":[561],"Development,":[562],"IEEE;":[573],"Laboratory,":[578],"USA;":[585],"Industrial":[588],"Affiliate":[589],"Center":[592],"Cardiovascular":[594],"Bioinformatics":[595],"Modeling,":[597],"Johns":[598],"Hopkins":[599],"Baltimore,":[601],"MD,":[602],"databases":[615],"supporting":[617],"biological":[618]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}