{"id":"https://openalex.org/W4401090911","doi":"https://doi.org/10.1080/03610918.2024.2378149","title":"On the prediction of rare events when sampling from large data","display_name":"On the prediction of rare events when sampling from large data","publication_year":2024,"publication_date":"2024-07-29","ids":{"openalex":"https://openalex.org/W4401090911","doi":"https://doi.org/10.1080/03610918.2024.2378149"},"language":"en","primary_location":{"id":"doi:10.1080/03610918.2024.2378149","is_oa":false,"landing_page_url":"https://doi.org/10.1080/03610918.2024.2378149","pdf_url":null,"source":{"id":"https://openalex.org/S153329750","display_name":"Communications in Statistics - Simulation and Computation","issn_l":"0361-0918","issn":["0361-0918","1532-4141"],"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":"Communications in Statistics - Simulation and Computation","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/A5059649223","display_name":"Johanna de Haan\u2010Ward","orcid":null},"institutions":[{"id":"https://openalex.org/I125749732","display_name":"Western University","ror":"https://ror.org/02grkyz14","country_code":"CA","type":"education","lineage":["https://openalex.org/I125749732"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Johanna de Haan-Ward","raw_affiliation_strings":["Department of Statistical and Actuarial Sciences, University of Western Ontario","Department of Statistical and Actuarial Sciences, University of Western Ontario, London, Ontario, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Statistical and Actuarial Sciences, University of Western Ontario","institution_ids":["https://openalex.org/I125749732"]},{"raw_affiliation_string":"Department of Statistical and Actuarial Sciences, University of Western Ontario, London, Ontario, Canada","institution_ids":["https://openalex.org/I125749732"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044369724","display_name":"Simon J. Bonner","orcid":"https://orcid.org/0000-0003-2063-4572"},"institutions":[{"id":"https://openalex.org/I125749732","display_name":"Western University","ror":"https://ror.org/02grkyz14","country_code":"CA","type":"education","lineage":["https://openalex.org/I125749732"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Simon J. Bonner","raw_affiliation_strings":["Department of Statistical and Actuarial Sciences, University of Western Ontario","Department of Statistical and Actuarial Sciences, University of Western Ontario, London, Ontario, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Statistical and Actuarial Sciences, University of Western Ontario","institution_ids":["https://openalex.org/I125749732"]},{"raw_affiliation_string":"Department of Statistical and Actuarial Sciences, University of Western Ontario, London, Ontario, Canada","institution_ids":["https://openalex.org/I125749732"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036712923","display_name":"Douglas G. Woolford","orcid":null},"institutions":[{"id":"https://openalex.org/I125749732","display_name":"Western University","ror":"https://ror.org/02grkyz14","country_code":"CA","type":"education","lineage":["https://openalex.org/I125749732"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Douglas Woolford","raw_affiliation_strings":["Department of Statistical and Actuarial Sciences, University of Western Ontario","Department of Statistical and Actuarial Sciences, University of Western Ontario, London, Ontario, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Statistical and Actuarial Sciences, University of Western Ontario","institution_ids":["https://openalex.org/I125749732"]},{"raw_affiliation_string":"Department of Statistical and Actuarial Sciences, University of Western Ontario, London, Ontario, Canada","institution_ids":["https://openalex.org/I125749732"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5059649223"],"corresponding_institution_ids":["https://openalex.org/I125749732"],"apc_list":null,"apc_paid":null,"fwci":0.2777,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.5637904,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"54","issue":"10","first_page":"4344","last_page":"4364"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10555","display_name":"Fire effects on ecosystems","score":0.9919999837875366,"subfield":{"id":"https://openalex.org/subfields/2306","display_name":"Global and Planetary Change"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10555","display_name":"Fire effects on ecosystems","score":0.9919999837875366,"subfield":{"id":"https://openalex.org/subfields/2306","display_name":"Global and Planetary Change"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11186","display_name":"Hydrology and Drought Analysis","score":0.9919999837875366,"subfield":{"id":"https://openalex.org/subfields/2306","display_name":"Global and Planetary Change"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11880","display_name":"Forest ecology and management","score":0.9715999960899353,"subfield":{"id":"https://openalex.org/subfields/2309","display_name":"Nature and Landscape Conservation"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.6957754492759705},{"id":"https://openalex.org/keywords/covariate","display_name":"Covariate","score":0.6528756022453308},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.6488321423530579},{"id":"https://openalex.org/keywords/stratified-sampling","display_name":"Stratified sampling","score":0.6330137848854065},{"id":"https://openalex.org/keywords/logistic-regression","display_name":"Logistic regression","score":0.593189537525177},{"id":"https://openalex.org/keywords/sampling-design","display_name":"Sampling design","score":0.5825986266136169},{"id":"https://openalex.org/keywords/simple-random-sample","display_name":"Simple random sample","score":0.4966445565223694},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.47167715430259705},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.46965140104293823},{"id":"https://openalex.org/keywords/offset","display_name":"Offset (computer science)","score":0.46763184666633606},{"id":"https://openalex.org/keywords/importance-sampling","display_name":"Importance sampling","score":0.46085992455482483},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4504677355289459},{"id":"https://openalex.org/keywords/sample-size-determination","display_name":"Sample size determination","score":0.43924060463905334},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.43449974060058594},{"id":"https://openalex.org/keywords/stratum","display_name":"Stratum","score":0.41045647859573364},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3560672402381897},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.34976956248283386},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.276459276676178},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09921380877494812}],"concepts":[{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.6957754492759705},{"id":"https://openalex.org/C119043178","wikidata":"https://www.wikidata.org/wiki/Q320723","display_name":"Covariate","level":2,"score":0.6528756022453308},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.6488321423530579},{"id":"https://openalex.org/C49898467","wikidata":"https://www.wikidata.org/wiki/Q1517706","display_name":"Stratified sampling","level":2,"score":0.6330137848854065},{"id":"https://openalex.org/C151956035","wikidata":"https://www.wikidata.org/wiki/Q1132755","display_name":"Logistic regression","level":2,"score":0.593189537525177},{"id":"https://openalex.org/C75373757","wikidata":"https://www.wikidata.org/wiki/Q7410160","display_name":"Sampling design","level":3,"score":0.5825986266136169},{"id":"https://openalex.org/C20353970","wikidata":"https://www.wikidata.org/wiki/Q1056998","display_name":"Simple random sample","level":3,"score":0.4966445565223694},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.47167715430259705},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.46965140104293823},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.46763184666633606},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.46085992455482483},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4504677355289459},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.43924060463905334},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.43449974060058594},{"id":"https://openalex.org/C175585516","wikidata":"https://www.wikidata.org/wiki/Q12758989","display_name":"Stratum","level":2,"score":0.41045647859573364},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3560672402381897},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.34976956248283386},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.276459276676178},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09921380877494812},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","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},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.0},{"id":"https://openalex.org/C187320778","wikidata":"https://www.wikidata.org/wiki/Q1349130","display_name":"Geotechnical engineering","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},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1080/03610918.2024.2378149","is_oa":false,"landing_page_url":"https://doi.org/10.1080/03610918.2024.2378149","pdf_url":null,"source":{"id":"https://openalex.org/S153329750","display_name":"Communications in Statistics - Simulation and Computation","issn_l":"0361-0918","issn":["0361-0918","1532-4141"],"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":"Communications in Statistics - Simulation and Computation","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"display_name":"Life in Land","id":"https://metadata.un.org/sdg/15"}],"awards":[{"id":"https://openalex.org/G2083543503","display_name":null,"funder_award_id":"RGPIN-2021-03920","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"},{"id":"https://openalex.org/G7824362142","display_name":null,"funder_award_id":"RGPIN-2016-04432","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"}],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"},{"id":"https://openalex.org/F8261615848","display_name":"Canadian Statistical Sciences Institute","ror":"https://ror.org/046n2jy73"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W563952771","https://openalex.org/W1526406472","https://openalex.org/W1988056000","https://openalex.org/W1994374969","https://openalex.org/W2005028768","https://openalex.org/W2013416277","https://openalex.org/W2018144913","https://openalex.org/W2020144485","https://openalex.org/W2022724931","https://openalex.org/W2024689521","https://openalex.org/W2045685519","https://openalex.org/W2050973892","https://openalex.org/W2057913086","https://openalex.org/W2078129874","https://openalex.org/W2095967516","https://openalex.org/W2134676181","https://openalex.org/W2142487491","https://openalex.org/W2148143831","https://openalex.org/W2167918728","https://openalex.org/W2318261078","https://openalex.org/W2321880705","https://openalex.org/W2469053811","https://openalex.org/W2498119267","https://openalex.org/W2545119860","https://openalex.org/W2551708067","https://openalex.org/W2581034649","https://openalex.org/W2582743722","https://openalex.org/W2772359634","https://openalex.org/W2775363893","https://openalex.org/W2777842083","https://openalex.org/W3024272665","https://openalex.org/W3098488568","https://openalex.org/W3098865414","https://openalex.org/W3112717819","https://openalex.org/W3112802122","https://openalex.org/W3123271700","https://openalex.org/W3125937743","https://openalex.org/W3198283686","https://openalex.org/W4225086356","https://openalex.org/W4246661169","https://openalex.org/W4296899512","https://openalex.org/W4399647826"],"related_works":["https://openalex.org/W4238714840","https://openalex.org/W2350399852","https://openalex.org/W336480102","https://openalex.org/W2555206834","https://openalex.org/W225930446","https://openalex.org/W2091497721","https://openalex.org/W2034762654","https://openalex.org/W1059159418","https://openalex.org/W2792266669","https://openalex.org/W1872822586"],"abstract_inverted_index":{"When":[0],"modeling":[1],"rare":[2],"events":[3],"using":[4,51],"logistic":[5,108],"regression,":[6],"independent":[7],"samples":[8],"of":[9,57,71,83,90,106,133,141],"event":[10],"occurrence":[11,147],"(ones)":[12],"and":[13,59,114],"nonoccurrence":[14],"(zeros)":[15],"are":[16],"commonly":[17],"taken":[18],"from":[19,69],"large":[20],"datasets":[21],"in":[22,35,78,149,153],"order":[23],"to":[24,38,61,86,102,121,144],"fit":[25],"models":[26],"efficiently.":[27],"A":[28],"deterministic":[29],"offset":[30],"may":[31,65,75],"then":[32],"be":[33],"included":[34],"the":[36,55,88,107,112],"model":[37],"compensate":[39],"for":[40],"that":[41,63,123],"sampling":[42,49,53,96],"method.":[43],"We":[44,94,118,136],"propose":[45],"a":[46,80,91,150],"more":[47,67],"complex":[48],"approach":[50],"stratified":[52],"within":[54],"sets":[56],"ones":[58],"zeros":[60,68,84],"ensure":[62],"we":[64],"sample":[66,82],"strata":[70],"interest.":[72],"This":[73],"design":[74],"avoid":[76],"situations":[77],"which":[79],"random":[81],"fails":[85],"capture":[87],"range":[89],"key":[92],"covariate.":[93],"employ":[95],"weights":[97],"along":[98],"with":[99,131],"stratum-specific":[100],"intercepts":[101],"obtain":[103],"unbiased":[104,127],"estimates":[105,129],"regression":[109],"coefficients":[110],"(including":[111],"intercept)":[113],"their":[115],"standard":[116],"errors.":[117],"use":[119],"simulation":[120],"show":[122],"this":[124,142],"method":[125,143],"provides":[126],"parameter":[128],"comparable":[130],"those":[132],"maximum":[134],"likelihood.":[135],"also":[137],"illustrate":[138],"an":[139],"application":[140],"wildland":[145],"fire":[146],"prediction":[148],"study":[151],"area":[152],"northwestern":[154],"Ontario,":[155],"Canada.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}