{"id":"https://openalex.org/W4235037173","doi":"https://doi.org/10.1002/sam.10021","title":"Least Angle Regression and LASSO for Large Datasets","display_name":"Least Angle Regression and LASSO for Large Datasets","publication_year":2009,"publication_date":"2009-01-21","ids":{"openalex":"https://openalex.org/W4235037173","doi":"https://doi.org/10.1002/sam.10021"},"language":"en","primary_location":{"id":"doi:10.1002/sam.10021","is_oa":false,"landing_page_url":"https://doi.org/10.1002/sam.10021","pdf_url":null,"source":{"id":"https://openalex.org/S40788348","display_name":"Statistical Analysis and Data Mining The ASA Data Science Journal","issn_l":"1932-1864","issn":["1932-1864","1932-1872"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Statistical Analysis and Data Mining: The ASA Data Science Journal","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/A5071762057","display_name":"Chris Fraley","orcid":null},"institutions":[{"id":"https://openalex.org/I4210118119","display_name":"Insilicos (United States)","ror":"https://ror.org/02p5qdz58","country_code":"US","type":"company","lineage":["https://openalex.org/I4210118119"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chris Fraley","raw_affiliation_strings":["Insightful Corporation, now at Insilicos, LLC"],"affiliations":[{"raw_affiliation_string":"Insightful Corporation, now at Insilicos, LLC","institution_ids":["https://openalex.org/I4210118119"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111405969","display_name":"Tim Hesterberg","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tim Hesterberg","raw_affiliation_strings":["Insightful Corporation, now at Google, Inc"],"affiliations":[{"raw_affiliation_string":"Insightful Corporation, now at Google, Inc","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5071762057"],"corresponding_institution_ids":["https://openalex.org/I4210118119"],"apc_list":{"value":3760,"currency":"USD","value_usd":3760},"apc_paid":null,"fwci":2.8268,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.91578342,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"1","issue":"4","first_page":"251","last_page":"259"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11871","display_name":"Advanced Statistical Methods and Models","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11871","display_name":"Advanced Statistical Methods and Models","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10136","display_name":"Statistical Methods and Inference","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10594","display_name":"Genetic and phenotypic traits in livestock","score":0.9853000044822693,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.7936773300170898},{"id":"https://openalex.org/keywords/lasso","display_name":"Lasso (programming language)","score":0.7836773991584778},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.6320961117744446},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.568470299243927},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.5671911239624023},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.49511900544166565},{"id":"https://openalex.org/keywords/regression-analysis","display_name":"Regression analysis","score":0.4897937774658203},{"id":"https://openalex.org/keywords/segmented-regression","display_name":"Segmented regression","score":0.48740795254707336},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.48096123337745667},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.46985092759132385},{"id":"https://openalex.org/keywords/partial-least-squares-regression","display_name":"Partial least squares regression","score":0.4691898822784424},{"id":"https://openalex.org/keywords/elastic-net-regularization","display_name":"Elastic net regularization","score":0.462718665599823},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.44668352603912354},{"id":"https://openalex.org/keywords/linear-regression","display_name":"Linear regression","score":0.43581852316856384},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.43235617876052856},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.39071035385131836},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3697752356529236},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.356511652469635},{"id":"https://openalex.org/keywords/polynomial-regression","display_name":"Polynomial regression","score":0.33236604928970337},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30473774671554565},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2259460687637329}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.7936773300170898},{"id":"https://openalex.org/C37616216","wikidata":"https://www.wikidata.org/wiki/Q3218363","display_name":"Lasso (programming language)","level":2,"score":0.7836773991584778},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.6320961117744446},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.568470299243927},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.5671911239624023},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49511900544166565},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.4897937774658203},{"id":"https://openalex.org/C35519122","wikidata":"https://www.wikidata.org/wiki/Q3775699","display_name":"Segmented regression","level":4,"score":0.48740795254707336},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.48096123337745667},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.46985092759132385},{"id":"https://openalex.org/C22354355","wikidata":"https://www.wikidata.org/wiki/Q422009","display_name":"Partial least squares regression","level":2,"score":0.4691898822784424},{"id":"https://openalex.org/C203868755","wikidata":"https://www.wikidata.org/wiki/Q5353562","display_name":"Elastic net regularization","level":3,"score":0.462718665599823},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.44668352603912354},{"id":"https://openalex.org/C48921125","wikidata":"https://www.wikidata.org/wiki/Q10861030","display_name":"Linear regression","level":2,"score":0.43581852316856384},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.43235617876052856},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.39071035385131836},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3697752356529236},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.356511652469635},{"id":"https://openalex.org/C120068334","wikidata":"https://www.wikidata.org/wiki/Q45343","display_name":"Polynomial regression","level":3,"score":0.33236604928970337},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30473774671554565},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2259460687637329},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1002/sam.10021","is_oa":false,"landing_page_url":"https://doi.org/10.1002/sam.10021","pdf_url":null,"source":{"id":"https://openalex.org/S40788348","display_name":"Statistical Analysis and Data Mining The ASA Data Science Journal","issn_l":"1932-1864","issn":["1932-1864","1932-1872"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Statistical Analysis and Data Mining: The ASA Data Science Journal","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6299999952316284}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W585413210","https://openalex.org/W1580960713","https://openalex.org/W1984568490","https://openalex.org/W2024850630","https://openalex.org/W2051540418","https://openalex.org/W2063978378","https://openalex.org/W2075665712","https://openalex.org/W2135046866","https://openalex.org/W4300819821","https://openalex.org/W4301491118","https://openalex.org/W4301621763","https://openalex.org/W4320800818"],"related_works":["https://openalex.org/W2468272465","https://openalex.org/W2429564919","https://openalex.org/W757986597","https://openalex.org/W4212910148","https://openalex.org/W4213314600","https://openalex.org/W4210804200","https://openalex.org/W4285814086","https://openalex.org/W3123944750","https://openalex.org/W2787225985","https://openalex.org/W2954774635"],"abstract_inverted_index":{"Abstract":[0],"Least":[1],"angle":[2],"regression":[3,93],"and":[4,31,95,119],"LASSO":[5],"(\u2113":[6],"1":[7],"\u2010penalized":[8],"regression)":[9],"offer":[10],"a":[11,66,73],"number":[12,46,102,108],"of":[13,36,47,63,86,98,103,109],"advantages":[14],"in":[15,43,68],"variable":[16],"selection":[17],"applications":[18],"over":[19],"procedures":[20],"such":[21],"as":[22,65],"stepwise":[23],"or":[24],"ridge":[25],"regression,":[26],"including":[27],"prediction":[28],"accuracy,":[29],"stability,":[30],"interpretability.":[32],"We":[33],"discuss":[34],"formulations":[35],"these":[37],"algorithms":[38],"that":[39,53],"extend":[40],"to":[41,59,90,100],"datasets":[42],"which":[44],"the":[45,61,77,84,87,92,101,107],"observations":[48],"could":[49],"be":[50,57],"so":[51],"large":[52],"it":[54],"would":[55],"not":[56],"possible":[58],"access":[60],"matrix":[62],"predictors":[64],"unit":[67],"computations.":[69],"Our":[70],"methods":[71],"require":[72],"single":[74],"pass":[75],"through":[76],"data":[78],"for":[79],"orthogonal":[80],"transformation,":[81],"effectively":[82],"reducing":[83],"dimension":[85],"computations":[88],"required":[89],"obtain":[91],"coefficients":[94],"residual":[96],"sum":[97],"squares":[99],"predictors,":[104],"rather":[105],"than":[106],"observations.":[110],"Copyright":[111],"\u00a9":[112],"2009":[113,124],"Wiley":[114],"Periodicals,":[115],"Inc.":[116],"Statistical":[117],"Analysis":[118],"Data":[120],"Mining":[121],"1:":[122],"000\u2010000,":[123]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":5},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}