{"id":"https://openalex.org/W2031847856","doi":"https://doi.org/10.1145/1141277.1141687","title":"Applying statistical methodology to optimize and simplify software metric models with missing data","display_name":"Applying statistical methodology to optimize and simplify software metric models with missing data","publication_year":2006,"publication_date":"2006-04-23","ids":{"openalex":"https://openalex.org/W2031847856","doi":"https://doi.org/10.1145/1141277.1141687","mag":"2031847856"},"language":"en","primary_location":{"id":"doi:10.1145/1141277.1141687","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1141277.1141687","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2006 ACM symposium on Applied computing","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/A5066624039","display_name":"W. Eric Wong","orcid":"https://orcid.org/0000-0002-1021-4753"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"W. Eric Wong","raw_affiliation_strings":["University of Texas at Dallas"],"affiliations":[{"raw_affiliation_string":"University of Texas at Dallas","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113590168","display_name":"Jin Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jin Zhao","raw_affiliation_strings":["University of Texas at Dallas"],"affiliations":[{"raw_affiliation_string":"University of Texas at Dallas","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022687207","display_name":"Victor K. Y. Chan","orcid":"https://orcid.org/0000-0002-3755-4512"},"institutions":[{"id":"https://openalex.org/I49835588","display_name":"Macao Polytechnic University","ror":"https://ror.org/02sf5td35","country_code":"MO","type":"education","lineage":["https://openalex.org/I49835588"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Victor K. Y. Chan","raw_affiliation_strings":["Macao Polytechnic Institute"],"affiliations":[{"raw_affiliation_string":"Macao Polytechnic Institute","institution_ids":["https://openalex.org/I49835588"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5066624039"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6417,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.88249041,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1728","last_page":"1733"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9998999834060669,"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9991999864578247,"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/T12127","display_name":"Software System Performance and Reliability","score":0.944599986076355,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.8252682685852051},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.6424828767776489},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5471509695053101},{"id":"https://openalex.org/keywords/software-metric","display_name":"Software metric","score":0.5264961123466492},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.45468616485595703},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.44714128971099854},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.43473196029663086},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.35222917795181274},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3214167654514313},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32115137577056885},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.28792381286621094},{"id":"https://openalex.org/keywords/software-quality","display_name":"Software quality","score":0.21335923671722412},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.1843286156654358}],"concepts":[{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.8252682685852051},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.6424828767776489},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5471509695053101},{"id":"https://openalex.org/C82214349","wikidata":"https://www.wikidata.org/wiki/Q657339","display_name":"Software metric","level":5,"score":0.5264961123466492},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.45468616485595703},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.44714128971099854},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.43473196029663086},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.35222917795181274},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3214167654514313},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32115137577056885},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28792381286621094},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.21335923671722412},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.1843286156654358},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1141277.1141687","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1141277.1141687","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2006 ACM symposium on Applied computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6100000143051147}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1575961892","https://openalex.org/W1594031697","https://openalex.org/W1963745770","https://openalex.org/W1972851018","https://openalex.org/W1994410397","https://openalex.org/W2019207321","https://openalex.org/W2030551707","https://openalex.org/W2044758663","https://openalex.org/W2089856939","https://openalex.org/W2095778055","https://openalex.org/W2096863518","https://openalex.org/W2102041666","https://openalex.org/W2103041471","https://openalex.org/W2103518983","https://openalex.org/W2108480826","https://openalex.org/W2113936771","https://openalex.org/W2127741023","https://openalex.org/W2129707602","https://openalex.org/W2136691316","https://openalex.org/W2151409568","https://openalex.org/W2154995572","https://openalex.org/W2156401290","https://openalex.org/W2156820168","https://openalex.org/W2157542847","https://openalex.org/W2480680997","https://openalex.org/W3015287909","https://openalex.org/W3085162807","https://openalex.org/W4238763888","https://openalex.org/W4285719527","https://openalex.org/W4295134715","https://openalex.org/W4297957988","https://openalex.org/W6608134946","https://openalex.org/W6674696959"],"related_works":["https://openalex.org/W4386799044","https://openalex.org/W2773208253","https://openalex.org/W2494189957","https://openalex.org/W1965637956","https://openalex.org/W2116876706","https://openalex.org/W3020983048","https://openalex.org/W2059510943","https://openalex.org/W2350290471","https://openalex.org/W2166119067","https://openalex.org/W1792767331"],"abstract_inverted_index":{"During":[0],"the":[1,8,31,38,67,71,78,84,102,106,113,117,128,131,134,141,144,176,182,203,238],"construction":[2,73],"of":[3,105,108,119,130,160],"a":[4,12,42,46,94,120,161,186,233],"software":[5],"metric":[6,15,33,40,62,111,122,136,150,164,236],"model,":[7],"decision":[9],"on":[10,23,37,50,112],"whether":[11,157],"particular":[13],"predictor":[14,32,57,61,90,110,121,135,149,163,224,235],"should":[16,137,165],"be":[17,138,166,219],"included":[18],"is":[19,65,74,80,210],"most":[20],"likely":[21],"based":[22,28,49],"an":[24,35,52],"intuitive":[25],"or":[26],"experience":[27],"assumption":[29,53,68],"that":[30,215],"has":[34],"impact":[36,107],"target":[39,114,132],"with":[41,127,195],"statistical":[43,95,103],"significance.":[44],"However,":[45],"model":[47,72,79],"constructed":[48],"such":[51],"may":[54],"contain":[55],"redundant":[56,89,223],"metric(s)":[58],"and/or":[59],"unnecessary":[60,148,228],"complexity.":[63],"This":[64],"because":[66],"made":[69],"before":[70],"not":[75,124],"verified":[76],"after":[77],"constructed.":[81],"To":[82],"resolve":[83],"first":[85],"problem":[86,146],"(i.e.,":[87,147],"possible":[88],"metric(s)),":[91],"we":[92,152],"propose":[93],"hypothesis":[96],"testing":[97],"methodology":[98,217],"to":[99,155,193],"verify":[100],"\"retrospectively\"":[101],"significance":[104],"each":[109],"metric.":[115],"If":[116],"variation":[118,129],"does":[123],"correlate":[125],"enough":[126],"metric,":[133],"deleted":[139],"from":[140,202],"model.":[142,183,239],"For":[143],"second":[145],"complexity),":[151],"use":[153,185],"\"goodness-of-fit\"":[154],"determine":[156],"certain":[158],"categories":[159,229],"categorical":[162,234],"combined":[167],"together.":[168],"In":[169],"addition,":[170],"missing":[171],"data":[172,177,201],"often":[173],"appear":[174],"in":[175,221,237],"sample":[178],"used":[179],"for":[180,232],"constructing":[181],"We":[184],"modified":[187],"k-nearest":[188],"neighbors":[189],"(k-NN)":[190],"imputation":[191],"method":[192],"deal":[194],"this":[196],"problem.":[197],"A":[198],"study":[199],"using":[200],"\"Repository":[204],"Data":[205],"Disk":[206],"-":[207],"Release":[208],"6\"":[209],"reported.":[211],"The":[212],"results":[213],"indicate":[214],"our":[216],"can":[218],"useful":[220],"trimming":[222],"metrics":[225],"and":[226],"identifying":[227],"initially":[230],"assumed":[231]},"counts_by_year":[{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
