{"id":"https://openalex.org/W4403746706","doi":"https://doi.org/10.48550/arxiv.2409.12129","title":"Bayesian estimation of the number of significant principal components for cultural data","display_name":"Bayesian estimation of the number of significant principal components for cultural data","publication_year":2024,"publication_date":"2024-09-18","ids":{"openalex":"https://openalex.org/W4403746706","doi":"https://doi.org/10.48550/arxiv.2409.12129"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2409.12129","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.12129","pdf_url":"https://arxiv.org/pdf/2409.12129","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2409.12129","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011918656","display_name":"Joshua C. Macdonald","orcid":"https://orcid.org/0000-0002-3643-6266","observed_orcids":["https://orcid.org/0000-0002-3643-6266"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL","US"],"is_corresponding":false,"raw_author_name":"Macdonald, Joshua C.","raw_affiliation_strings":["Current Address: Department of International Health , Bloomberg School of Public Health , Johns Hopkins University , Baltimore , MD , USA","School of Zoology , Faculty of Life Sciences , Tel Aviv University , Tel Aviv , Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Current Address: Department of International Health , Bloomberg School of Public Health , Johns Hopkins University , Baltimore , MD , USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"School of Zoology , Faculty of Life Sciences , Tel Aviv University , Tel Aviv , Israel","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014656259","display_name":"Javier Blanco-Portillo","orcid":"https://orcid.org/0000-0003-3168-2756","observed_orcids":["https://orcid.org/0000-0003-3168-2756"]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Blanco-Portillo, Javier","raw_affiliation_strings":["Department of Biology , Stanford University , Stanford , CA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biology , Stanford University , Stanford , CA , USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085988625","display_name":"Marcus William Feldman","orcid":"https://orcid.org/0000-0002-0664-3803","observed_orcids":["https://orcid.org/0000-0002-0664-3803"]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Feldman, Marcus W.","raw_affiliation_strings":["Department of Biology , Stanford University , Stanford , CA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biology , Stanford University , Stanford , CA , USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049174192","display_name":"Yoav Ram","orcid":"https://orcid.org/0000-0002-9653-4458","observed_orcids":["https://orcid.org/0000-0002-9653-4458"]},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Ram, Yoav","raw_affiliation_strings":["Safra Center for Bioinformatics , Tel Aviv University , Tel Aviv , Israel","School of Zoology , Faculty of Life Sciences , Tel Aviv University , Tel Aviv , Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Safra Center for Bioinformatics , Tel Aviv University , Tel Aviv , Israel","institution_ids":["https://openalex.org/I16391192"]},{"raw_affiliation_string":"School of Zoology , Faculty of Life Sciences , Tel Aviv University , Tel Aviv , Israel","institution_ids":["https://openalex.org/I16391192"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13141","display_name":"Statistical Methods and Applications","score":0.9848999977111816,"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/T13141","display_name":"Statistical Methods and Applications","score":0.9848999977111816,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.006200000178068876,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10057","display_name":"Face and Expression Recognition","score":0.00039999998989515007,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/principal-component-analysis","display_name":"principal component analysis","score":0.8460000157356262},{"id":"https://openalex.org/keywords/number-of-principal-components","display_name":"number of principal components","score":0.8529999852180481},{"id":"https://openalex.org/keywords/variational-bayesian-inference","display_name":"variational inference","score":0.8970000147819519},{"id":"https://openalex.org/keywords/cultural-data","display_name":"cultural data","score":0.7770000100135803},{"id":"https://openalex.org/keywords/high-dimensional-data","display_name":"high-dimensional data","score":0.640999972820282},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"noise reduction","score":0.6710000038146973},{"id":"https://openalex.org/keywords/missing-data","display_name":"missing data","score":0.8169999718666077},{"id":"https://openalex.org/keywords/categorical-data","display_name":"categorical data","score":0.8230000138282776},{"id":"https://openalex.org/keywords/morphological-data","display_name":"morphological data","score":0.6439999938011169},{"id":"https://openalex.org/keywords/behavioral-data","display_name":"behavioral data","score":0.6809999942779541},{"id":"https://openalex.org/keywords/ecological-data","display_name":"ecological data","score":0.6859999895095825}],"concepts":[{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.6877911686897278},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.6357943415641785},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.6189747452735901},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.5383651256561279},{"id":"https://openalex.org/C68022304","wikidata":"https://www.wikidata.org/wiki/Q842217","display_name":"Bayes estimator","level":3,"score":0.4591395854949951},{"id":"https://openalex.org/C144559511","wikidata":"https://www.wikidata.org/wiki/Q2986279","display_name":"Principal (computer security)","level":2,"score":0.4360736608505249},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.43023034930229187},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.3568968176841736},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.34654003381729126},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.33305227756500244},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.12173151969909668},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2409.12129","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.12129","pdf_url":"https://arxiv.org/pdf/2409.12129","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2409.12129","doi":"https://doi.org/10.48550/arxiv.2409.12129","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2409.12129","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2409.12129","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.12129","pdf_url":"https://arxiv.org/pdf/2409.12129","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306193","display_name":"John Templeton Foundation","ror":"https://ror.org/035tnyy05"},{"id":"https://openalex.org/F4320320878","display_name":"Minerva Foundation","ror":"https://ror.org/02rxjts25"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403746706.pdf","grobid_xml":"https://content.openalex.org/works/W4403746706.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2963671280","https://openalex.org/W7117360479","https://openalex.org/W1575232566","https://openalex.org/W7100018557","https://openalex.org/W2753993582","https://openalex.org/W1999692887","https://openalex.org/W4298184129","https://openalex.org/W1542311886","https://openalex.org/W2182227024","https://openalex.org/W2091571775"],"abstract_inverted_index":{"Principal":[0],"component":[1],"analysis":[2],"(PCA)":[3],"is":[4,25,71,135,203],"often":[5],"used":[6],"to":[7,28,52,75,110],"analyze":[8],"multivariate":[9],"data":[10,40,121,139,165],"together":[11],"with":[12,128,140],"cluster":[13],"analysis,":[14],"which":[15],"depends":[16],"on":[17,162],"the":[18,30,59,67,79,92,178,184,207],"number":[19,31,60,68,80,93,179,189],"of":[20,32,49,61,69,72,81,94,100,112,116,146,180,190],"principal":[21,34,95,181],"components":[22,35,96,182,191],"used.":[23],"It":[24],"therefore":[26],"important":[27],"determine":[29],"significant":[33,62],"(PCs)":[36],"extracted":[37],"from":[38],"a":[39,45,54,73],"set.":[41],"Here":[42],"we":[43],"use":[44],"variational":[46],"Bayesian":[47],"version":[48],"classical":[50],"PCA,":[51],"develop":[53],"new":[55],"method":[56,161],"for":[57,138,183,194],"estimating":[58],"PCs":[63],"in":[64,89],"contexts":[65],"where":[66],"samples":[70],"similar":[74,144],"or":[76],"greater":[77],"than":[78],"features.":[82],"This":[83,105],"eliminates":[84],"guesswork":[85],"and":[86,97,118,127,130,143,148,155,166,169],"potential":[87],"bias":[88],"manually":[90],"determining":[91],"avoids":[98],"overestimation":[99],"variance":[101],"by":[102],"filtering":[103],"noise.":[104],"framework":[106],"can":[107],"be":[108],"applied":[109],"datasets":[111,168],"different":[113,120],"shapes":[114],"(number":[115],"rows":[117,147],"columns),":[119],"types":[122],"(binary,":[123],"ordinal,":[124],"categorical,":[125],"continuous),":[126],"noisy":[129],"missing":[131],"data.":[132,186],"Therefore,":[133],"it":[134,172,202],"especially":[136],"useful":[137],"arbitrary":[141],"encodings":[142],"numbers":[145],"columns,":[149],"such":[150],"as":[151],"cultural,":[152],"ecological,":[153],"morphological,":[154],"behavioral":[156],"datasets.":[157],"We":[158],"tested":[159],"our":[160],"both":[163],"synthetic":[164,185],"empirical":[167,196],"found":[170,193],"that":[171,201],"may":[173],"underestimate":[174],"but":[175],"not":[176],"overestimate":[177],"A":[187],"small":[188],"was":[192],"each":[195],"dataset.":[197],"These":[198],"results":[199],"suggest":[200],"broadly":[204],"applicable":[205],"across":[206],"life":[208],"sciences.":[209]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-10-17T09:40:24.721904","created_date":"2024-10-25T00:00:00"}