{"id":"https://openalex.org/W7220904496","doi":"https://doi.org/10.31234/osf.io/v735g_v4","title":"Estimand or estimator? Comparing vowel overlap measures against a known ground truth","display_name":"Estimand or estimator? Comparing vowel overlap measures against a known ground truth","publication_year":2026,"publication_date":"2026-10-07","ids":{"openalex":"https://openalex.org/W7220904496","doi":"https://doi.org/10.31234/osf.io/v735g_v4"},"language":"en","primary_location":{"id":"doi:10.31234/osf.io/v735g_v4","doi":"https://doi.org/10.31234/osf.io/v735g_v4","is_oa":true,"landing_page_url":"https://doi.org/10.31234/osf.io/v735g_v4","pdf_url":null,"source":{"id":"https://openalex.org/S4306401687","display_name":"PsyArXiv (OSF Preprints)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2799848540","host_organization_name":"Center for Open Science","host_organization_lineage":["https://openalex.org/I2799848540"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.31234/osf.io/v735g_v4","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042125665","display_name":"Grant M. Berry","orcid":"https://orcid.org/0000-0002-4376-4305","observed_orcids":["https://orcid.org/0000-0002-4376-4305"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Grant M Berry","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-4376-4305","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5042125665"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9872999787330627,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.9872999787330627,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11640","display_name":"Linguistic Variation and Morphology","score":0.006399999838322401,"subfield":{"id":"https://openalex.org/subfields/3310","display_name":"Linguistics and Language"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.000699999975040555,"subfield":{"id":"https://openalex.org/subfields/3616","display_name":"Speech and Hearing"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/vowel-categories","display_name":"vowel categories","score":0.5789999961853027},{"id":"https://openalex.org/keywords/bhattacharyya-distance","display_name":"Bhattacharyya distance","score":0.9589999914169312},{"id":"https://openalex.org/keywords/euclidean-distance","display_name":"Euclidean distance","score":0.8429999947547913},{"id":"https://openalex.org/keywords/jensen-shannon-divergence","display_name":"Jensen-Shannon divergence","score":0.8320000171661377},{"id":"https://openalex.org/keywords/kernel-density-estimation","display_name":"kernel density estimation","score":0.8130000233650208},{"id":"https://openalex.org/keywords/sociophonetic-variation","display_name":"sociophonetic variation","score":0.5090000033378601}],"concepts":[{"id":"https://openalex.org/C24145651","wikidata":"https://www.wikidata.org/wiki/Q2901249","display_name":"Bhattacharyya distance","level":2,"score":0.7064999938011169},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.6492999792098999},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5396000146865845},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5088000297546387},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40400001406669617},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3783999979496002},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3686999976634979},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.3497999906539917},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34549999237060547},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.34450000524520874},{"id":"https://openalex.org/C120174047","wikidata":"https://www.wikidata.org/wiki/Q847073","display_name":"Euclidean distance","level":2,"score":0.33820000290870667},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.33230000734329224},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.3041999936103821},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3000999987125397},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2953999936580658},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.2939000129699707},{"id":"https://openalex.org/C2639959","wikidata":"https://www.wikidata.org/wiki/Q1344778","display_name":"Distance measures","level":2,"score":0.2930999994277954},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2919999957084656},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.29100000858306885},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.29100000858306885},{"id":"https://openalex.org/C116714509","wikidata":"https://www.wikidata.org/wiki/Q32278","display_name":"Truncated mean","level":3,"score":0.2879999876022339},{"id":"https://openalex.org/C88271906","wikidata":"https://www.wikidata.org/wiki/Q786973","display_name":"Autocovariance","level":3,"score":0.28349998593330383},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.28119999170303345},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.26429998874664307},{"id":"https://openalex.org/C186450821","wikidata":"https://www.wikidata.org/wiki/Q17295","display_name":"Euclidean space","level":2,"score":0.2639999985694885},{"id":"https://openalex.org/C2780129039","wikidata":"https://www.wikidata.org/wiki/Q1931107","display_name":"Section (typography)","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C1921717","wikidata":"https://www.wikidata.org/wiki/Q1334846","display_name":"Mahalanobis distance","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.2587999999523163},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.31234/osf.io/v735g_v4","doi":"https://doi.org/10.31234/osf.io/v735g_v4","is_oa":true,"landing_page_url":"https://doi.org/10.31234/osf.io/v735g_v4","pdf_url":null,"source":{"id":"https://openalex.org/S4306401687","display_name":"PsyArXiv (OSF Preprints)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2799848540","host_organization_name":"Center for Open Science","host_organization_lineage":["https://openalex.org/I2799848540"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.31234/osf.io/v735g_v4","doi":"https://doi.org/10.31234/osf.io/v735g_v4","is_oa":true,"landing_page_url":"https://doi.org/10.31234/osf.io/v735g_v4","pdf_url":null,"source":{"id":"https://openalex.org/S4306401687","display_name":"PsyArXiv (OSF Preprints)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2799848540","host_organization_name":"Center for Open Science","host_organization_lineage":["https://openalex.org/I2799848540"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2940770446","https://openalex.org/W4402112286","https://openalex.org/W6941050454","https://openalex.org/W4400288586","https://openalex.org/W3010968424","https://openalex.org/W2133535745","https://openalex.org/W6997241246","https://openalex.org/W7097361209","https://openalex.org/W2052157232","https://openalex.org/W2013239784"],"abstract_inverted_index":{"Deciding":[0],"how":[1,96],"much":[2],"two":[3,176],"vowel":[4,93],"categories":[5],"overlap":[6,50,70,82],"is":[7,146,156,162],"a":[8,165,171],"core":[9],"problem":[10],"in":[11,102,121,197],"laboratory":[12],"phonology":[13],"and":[14,16,31,45,76,107,128,153,189],"sociophonetics,":[15],"the":[17,26,42,57,73,132,138,143,147,175],"field":[18],"has":[19],"proposed":[20],"several":[21],"metrics":[22,40,71],"to":[23,83,119,194],"quantify":[24],"overlap:":[25],"Pillai":[27,145,191],"trace,":[28],"Bhattacharyya":[29],"distance,":[30,33,170],"Euclidean":[32],"among":[34],"others.":[35],"Researchers":[36],"rarely":[37,163],"compute":[38],"multiple":[39,69],"on":[41,72,99,140],"same":[43,58,74],"data,":[44,101],"what":[46],"look":[47],"like":[48],"distinct":[49],"definitions":[51],"are":[52,115,126],"sometimes":[53],"different":[54],"estimates":[55,125],"of":[56],"quantity.":[59],"I":[60,77,167],"introduce":[61],"Phontrast,":[62],"an":[63],"open-source":[64],"R":[65],"toolkit":[66],"that":[67,180],"computes":[68],"tokens,":[75],"simulate":[78],"distributions":[79,179],"with":[80],"known":[81,164],"disentangle":[84],"each":[85],"measure's":[86],"estimator":[87],"from":[88],"its":[89],"estimand.":[90],"Two":[91],"public":[92],"corpora":[94],"show":[95,195],"measures":[97,114],"behave":[98],"real":[100],"F1":[103],"\u00d7":[104],"F2":[105],"space":[106],"thirteen-dimensional":[108],"MFCC":[109],"space.":[110],"Mean-":[111],"or":[112],"Gaussian-based":[113],"precise":[116,149],"but":[117,130],"unresponsive":[118],"separation":[120,155,182],"higher":[122],"moments.":[123],"Kernel":[124],"biased":[127],"bandwidth-dependent,":[129],"within":[131],"simulation's":[133],"operating":[134],"region":[135],"they":[136],"recover":[137],"ordering":[139,187],"average,":[141],"whatever":[142],"mechanism.":[144],"most":[148],"for":[150,186],"small":[151],"samples":[152],"whenever":[154],"driven":[157],"by":[158],"means.":[159,199],"Since":[160],"this":[161],"priori,":[166],"foreground":[168],"Jensen\u2013Shannon":[169],"distribution-free":[172],"distance":[173],"between":[174],"vowels'":[177],"probability":[178],"registers":[181],"however":[183],"it":[184,193],"arises,":[185],"speakers":[188],"contrasts\u2014with":[190],"beside":[192],"movement":[196],"category":[198]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-10-09T00:00:00"}