The Wilcoxon rank sum test, also known as Mann-Whitney U-test, doesn’t make any assumption concerning the statistical distribution of words in a corpus (Wilcoxon 1945, Mann & Whitney 1947). It is based on a comparison of a sum of rank orders of texts in two text collections. The rank orders of texts are defined according to a frequency of a target word, without considering to which of both corpora this text belongs (see Lijffijt 2014). In our implementation, it sums up the frequencies per segment of document; for this reason, we consider it to be a dispersion-based rather than a frequency-based measure.
References
2241481
measure_wilcoxon
1
modern-humanities-research-association
50
date
desc
595
https://zeta-project.eu/wp-content/plugins/zotpress/
%7B%22status%22%3A%22success%22%2C%22updateneeded%22%3Afalse%2C%22instance%22%3Afalse%2C%22meta%22%3A%7B%22request_last%22%3A0%2C%22request_next%22%3A0%2C%22used_cache%22%3Atrue%7D%2C%22data%22%3A%5B%7B%22key%22%3A%22F2VKYUK3%22%2C%22library%22%3A%7B%22id%22%3A2241481%7D%2C%22meta%22%3A%7B%22lastModifiedByUser%22%3A%7B%22id%22%3A5206995%2C%22username%22%3A%22roettgermann%22%2C%22name%22%3A%22%22%2C%22links%22%3A%7B%22alternate%22%3A%7B%22href%22%3A%22https%3A%5C%2F%5C%2Fwww.zotero.org%5C%2Froettgermann%22%2C%22type%22%3A%22text%5C%2Fhtml%22%7D%7D%7D%2C%22creatorSummary%22%3A%22Lijffijt%20et%20al.%22%2C%22parsedDate%22%3A%222014%22%2C%22numChildren%22%3A0%7D%2C%22bib%22%3A%22%3Cdiv%20class%3D%5C%22csl-bib-body%5C%22%20style%3D%5C%22line-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%5C%22%3E%5Cn%20%20%3Cdiv%20class%3D%5C%22csl-entry%5C%22%3ELijffijt%2C%20Jefrey%2C%20Terttu%20Nevalainen%2C%20Tanja%20S%26%23xE4%3Bily%2C%20Panagiotis%20Papapetrou%2C%20Kai%20Puolam%26%23xE4%3Bki%2C%20and%20Heikki%20Mannila%2C%20%26%23x2018%3BSignificance%20Testing%20of%20Word%20Frequencies%20in%20Corpora%26%23x2019%3B%2C%20%3Ci%3EDigital%20Scholarship%20in%20the%20Humanities%3C%5C%2Fi%3E%2C%2031.2%20%282014%29%2C%20pp.%20374%26%23x2013%3B97%2C%20%3Ca%20class%3D%27zp-DOIURL%27%20href%3D%27http%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1093%5C%2Fllc%5C%2Ffqu064%27%3Ehttp%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1093%5C%2Fllc%5C%2Ffqu064%3C%5C%2Fa%3E%3C%5C%2Fdiv%3E%5Cn%3C%5C%2Fdiv%3E%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Significance%20testing%20of%20word%20frequencies%20in%20corpora%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jefrey%22%2C%22lastName%22%3A%22Lijffijt%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Terttu%22%2C%22lastName%22%3A%22Nevalainen%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Tanja%22%2C%22lastName%22%3A%22S%5Cu00e4ily%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Panagiotis%22%2C%22lastName%22%3A%22Papapetrou%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Kai%22%2C%22lastName%22%3A%22Puolam%5Cu00e4ki%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Heikki%22%2C%22lastName%22%3A%22Mannila%22%7D%5D%2C%22abstractNote%22%3A%22Finding%20out%20whether%20a%20word%20occurs%20significantly%20more%20often%20in%20one%20text%20or%20corpus%20than%20in%20another%20is%20an%20important%20question%20in%20analysing%20corpora.%20As%20noted%20by%20Kilgarriff%20%28Language%20is%20never%2C%20ever%2C%20ever%2C%20random%2C%20Corpus%20Linguistics%20and%20Linguistic%20Theory%20%2C%202005%3B%201%282%29%3A%20263%5Cu201376.%29%2C%20the%20use%20of%20the%20%5Cu03c7%202%20and%20log-likelihood%20ratio%20tests%20is%20problematic%20in%20this%20context%2C%20as%20they%20are%20based%20on%20the%20assumption%20that%20all%20samples%20are%20statistically%20independent%20of%20each%20other.%20However%2C%20words%20within%20a%20text%20are%20not%20independent.%20As%20pointed%20out%20in%20Kilgarriff%20%28Comparing%20corpora%2C%20International%20Journal%20of%20Corpus%20Linguistics%20%2C%202001%3B%206%281%29%3A%201%5Cu201337%29%20and%20Paquot%20and%20Bestgen%20%28Distinctive%20words%20in%20academic%20writing%3A%20a%20comparison%20of%20three%20statistical%20tests%20for%20keyword%20extraction.%20In%20Jucker%2C%20A.%2C%20Schreier%2C%20D.%2C%20and%20Hundt%2C%20M.%20%28eds%29%2C%20Corpora%3A%20Pragmatics%20and%20Discourse%20.%20Amsterdam%3A%20Rodopi%2C%202009%2C%20pp.%20247%5Cu201369%29%2C%20it%20is%20possible%20to%20represent%20the%20data%20differently%20and%20employ%20other%20tests%2C%20such%20that%20we%20assume%20independence%20at%20the%20level%20of%20texts%20rather%20than%20individual%20words.%20This%20allows%20us%20to%20account%20for%20the%20distribution%20of%20words%20within%20a%20corpus.%20In%20this%20article%20we%20compare%20the%20significance%20estimates%20of%20various%20statistical%20tests%20in%20a%20controlled%20resampling%20experiment%20and%20in%20a%20practical%20setting%2C%20studying%20differences%20between%20texts%20produced%20by%20male%20and%20female%20fiction%20writers%20in%20the%20British%20National%20Corpus.%20We%20find%20that%20the%20choice%20of%20the%20test%2C%20and%20hence%20data%20representation%2C%20matters.%20We%20conclude%20that%20significance%20testing%20can%20be%20used%20to%20find%20consequential%20differences%20between%20corpora%2C%20but%20that%20assuming%20independence%20between%20all%20words%20may%20lead%20to%20overestimating%20the%20significance%20of%20the%20observed%20differences%2C%20especially%20for%20poorly%20dispersed%20words.%20We%20recommend%20the%20use%20of%20the%20t-test%2C%20Wilcoxon%20rank-sum%20test%2C%20or%20bootstrap%20test%20for%20comparing%20word%20frequencies%20across%20corpora.%22%2C%22date%22%3A%222014%22%2C%22language%22%3A%22en%22%2C%22DOI%22%3A%2210.1093%5C%2Fllc%5C%2Ffqu064%22%2C%22ISSN%22%3A%222055-7671%2C%202055-768X%22%2C%22url%22%3A%22http%3A%5C%2F%5C%2Fdsh.oxfordjournals.org%5C%2Flookup%5C%2Fdoi%5C%2F10.1093%5C%2Fllc%5C%2Ffqu064%22%2C%22collections%22%3A%5B%22IUKRIB7T%22%2C%224MZ8ZP2B%22%5D%2C%22dateModified%22%3A%222024-02-20T09%3A03%3A52Z%22%7D%7D%2C%7B%22key%22%3A%22BFMBZJ5T%22%2C%22library%22%3A%7B%22id%22%3A2241481%7D%2C%22meta%22%3A%7B%22lastModifiedByUser%22%3A%7B%22id%22%3A5206995%2C%22username%22%3A%22roettgermann%22%2C%22name%22%3A%22%22%2C%22links%22%3A%7B%22alternate%22%3A%7B%22href%22%3A%22https%3A%5C%2F%5C%2Fwww.zotero.org%5C%2Froettgermann%22%2C%22type%22%3A%22text%5C%2Fhtml%22%7D%7D%7D%2C%22creatorSummary%22%3A%22Paquot%20and%20Bestgen%22%2C%22parsedDate%22%3A%222009-01-01%22%2C%22numChildren%22%3A0%7D%2C%22bib%22%3A%22%3Cdiv%20class%3D%5C%22csl-bib-body%5C%22%20style%3D%5C%22line-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%5C%22%3E%5Cn%20%20%3Cdiv%20class%3D%5C%22csl-entry%5C%22%3EPaquot%2C%20Magali%2C%20and%20Yves%20Bestgen%2C%20%26%23x2018%3BDistinctive%20Words%20in%20Academic%20Writing%3A%20A%20Comparison%20of%20Three%20Statistical%20Tests%20for%20Keyword%20Extraction%26%23x2019%3B%2C%20in%20%3Ci%3ECorpora%3A%20Pragmatics%20and%20Discourse%3C%5C%2Fi%3E%2C%20ed.%20by%20Andreas%20H.%20Jucker%2C%20Daniel%20Schreier%2C%20and%20Marianne%20Hundt%20%28Brill%20%7C%20Rodopi%2C%202009%29%2C%20doi%3A10.1163%5C%2F9789042029101_014%3C%5C%2Fdiv%3E%5Cn%3C%5C%2Fdiv%3E%22%2C%22data%22%3A%7B%22itemType%22%3A%22bookSection%22%2C%22title%22%3A%22Distinctive%20words%20in%20academic%20writing%3A%20A%20comparison%20of%20three%20statistical%20tests%20for%20keyword%20extraction%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Andreas%20H.%22%2C%22lastName%22%3A%22Jucker%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Daniel%22%2C%22lastName%22%3A%22Schreier%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Marianne%22%2C%22lastName%22%3A%22Hundt%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Magali%22%2C%22lastName%22%3A%22Paquot%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yves%22%2C%22lastName%22%3A%22Bestgen%22%7D%5D%2C%22abstractNote%22%3A%22Most%20studies%20that%20make%20use%20of%20keyword%20analysis%20rely%20on%20log-likelihood%20ratio%20or%20chi-square%20tests%20to%20extract%20words%20that%20are%20particularly%20characteristic%20of%20a%20corpus%20%28e.g.%20Scott%20and%20Tribble%202006%29.%20These%20measures%20are%20computed%20on%20the%20basis%20of%20absolute%20frequencies%20and%20cannot%20account%20for%20the%20fact%20that%20%5Cu201ccorpora%20are%20inherently%20variable%20internally%5Cu201d%20%28Gries%202006%3A%20110%29.%20To%20overcome%20this%20limitation%2C%20measures%20of%20dispersion%20are%20sometimes%20used%20in%20combination%20with%20keyness%20values%20%28e.g.%20Rayson%202003%3B%20Oakes%20and%20Farrow%202007%29.%20Some%20scholars%20have%20also%20suggested%20using%20other%20statistical%20measures%20%28e.g.%20Wilcoxon-Mann-Whitney%20test%29%20but%20these%20techniques%20have%20not%20gained%20corpus%20linguists%5Cu2019%20favour%20%28yet%3F%29.%20One%20possible%20explanation%20for%20this%20lack%20of%20enthusiasm%20is%20that%20statistical%20tests%20for%20keyword%20extraction%20have%20rarely%20been%20compared.%20In%20this%20article%2C%20we%20make%20use%20of%20the%20log-likelihood%20ratio%2C%20the%20t-test%20and%20the%20Wilcoxon-Mann-Whitney%20test%20in%20turn%20to%20compare%20the%20academic%20and%20the%20fiction%20sub-corpora%20of%20the%20British%20National%20Corpus%20and%20extract%20words%20that%20are%20typical%20of%20academic%20discourse.%20We%20compare%20the%20three%20lists%20of%20academic%20keywords%20on%20a%20number%20of%20criteria%20%28e.g.%20number%20of%20keywords%20extracted%20by%20each%20measure%2C%20percentage%20of%20keywords%20that%20are%20shared%20in%20the%20three%20lists%2C%20frequency%20and%20distribution%20of%20academic%20keywords%20in%20the%20two%20corpora%29%20and%20explore%20the%20specificities%20of%20the%20three%20statistical%20measures.%20We%20also%20assess%20the%20advantages%20and%20disadvantages%20of%20these%20measures%20for%20the%20extraction%20of%20general%20academic%20words.%22%2C%22bookTitle%22%3A%22Corpora%3A%20Pragmatics%20and%20Discourse%22%2C%22date%22%3A%222009-01-01%22%2C%22language%22%3A%22%22%2C%22ISBN%22%3A%22978-90-420-2910-1%20978-90-420-2592-9%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fbrill.com%5C%2Fview%5C%2Fbook%5C%2Fedcoll%5C%2F9789042029101%5C%2FB9789042029101-s014.xml%22%2C%22collections%22%3A%5B%222CZHD96W%22%2C%224MZ8ZP2B%22%5D%2C%22dateModified%22%3A%222024-02-20T09%3A05%3A29Z%22%7D%7D%2C%7B%22key%22%3A%22ALFHDJVS%22%2C%22library%22%3A%7B%22id%22%3A2241481%7D%2C%22meta%22%3A%7B%22lastModifiedByUser%22%3A%7B%22id%22%3A228821%2C%22username%22%3A%22christof.s%22%2C%22name%22%3A%22Christof%20Sch%5Cu00f6ch%22%2C%22links%22%3A%7B%22alternate%22%3A%7B%22href%22%3A%22https%3A%5C%2F%5C%2Fwww.zotero.org%5C%2Fchristof.s%22%2C%22type%22%3A%22text%5C%2Fhtml%22%7D%7D%7D%2C%22creatorSummary%22%3A%22Woolson%22%2C%22parsedDate%22%3A%222008-09-19%22%2C%22numChildren%22%3A0%7D%2C%22bib%22%3A%22%3Cdiv%20class%3D%5C%22csl-bib-body%5C%22%20style%3D%5C%22line-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%5C%22%3E%5Cn%20%20%3Cdiv%20class%3D%5C%22csl-entry%5C%22%3EWoolson%2C%20R.%20F.%2C%20%26%23x2018%3BWilcoxon%20Signed-Rank%20Test%26%23x2019%3B%2C%20in%20%3Ci%3EWiley%20Encyclopedia%20of%20Clinical%20Trials%3C%5C%2Fi%3E%2C%20ed.%20by%20Ralph%20B.%20D%26%23x2019%3BAgostino%2C%20Lisa%20Sullivan%2C%20and%20Joseph%20Massaro%20%28John%20Wiley%20%26amp%3B%20Sons%2C%20Inc.%2C%202008%29%2C%20p.%20eoct979%2C%20doi%3A10.1002%5C%2F9780471462422.eoct979%3C%5C%2Fdiv%3E%5Cn%3C%5C%2Fdiv%3E%22%2C%22data%22%3A%7B%22itemType%22%3A%22bookSection%22%2C%22title%22%3A%22Wilcoxon%20Signed-Rank%20Test%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Ralph%20B.%22%2C%22lastName%22%3A%22D%27Agostino%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Lisa%22%2C%22lastName%22%3A%22Sullivan%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Joseph%22%2C%22lastName%22%3A%22Massaro%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22R.%20F.%22%2C%22lastName%22%3A%22Woolson%22%7D%5D%2C%22abstractNote%22%3A%22This%20is%20a%20nonparametric%20test%20procedure%20for%20the%20analysis%20of%20matched%5Cu2010pair%20data%2C%20based%20on%20differences%2C%20or%20for%20a%20single%20sample.%20The%20null%20hypothesis%20is%20that%20the%20differences%2C%20or%20individual%20observations%20in%20the%20single%5Cu2010sample%20case%2C%20have%20a%20distribution%20centered%20about%20zero.%20The%20absolute%20values%20are%20ranked.%20The%20test%20statistic%20is%20the%20sum%20of%20the%20ranks%20for%20either%20the%20positive%20or%20the%20negative%20values.%20Examples%20and%20details%2C%20including%20large%5Cu2010sample%20properties%2C%20are%20given.%22%2C%22bookTitle%22%3A%22Wiley%20Encyclopedia%20of%20Clinical%20Trials%22%2C%22date%22%3A%222008-09-19%22%2C%22language%22%3A%22en%22%2C%22ISBN%22%3A%22978-0-471-46242-2%22%2C%22url%22%3A%22http%3A%5C%2F%5C%2Fdoi.wiley.com%5C%2F10.1002%5C%2F9780471462422.eoct979%22%2C%22collections%22%3A%5B%224MZ8ZP2B%22%5D%2C%22dateModified%22%3A%222020-02-14T14%3A31%3A25Z%22%7D%7D%2C%7B%22key%22%3A%22NM6EKHVK%22%2C%22library%22%3A%7B%22id%22%3A2241481%7D%2C%22meta%22%3A%7B%22lastModifiedByUser%22%3A%7B%22id%22%3A228821%2C%22username%22%3A%22christof.s%22%2C%22name%22%3A%22Christof%20Sch%5Cu00f6ch%22%2C%22links%22%3A%7B%22alternate%22%3A%7B%22href%22%3A%22https%3A%5C%2F%5C%2Fwww.zotero.org%5C%2Fchristof.s%22%2C%22type%22%3A%22text%5C%2Fhtml%22%7D%7D%7D%2C%22creatorSummary%22%3A%22Zimmerman%20and%20Zumbo%22%2C%22parsedDate%22%3A%221993%22%2C%22numChildren%22%3A0%7D%2C%22bib%22%3A%22%3Cdiv%20class%3D%5C%22csl-bib-body%5C%22%20style%3D%5C%22line-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%5C%22%3E%5Cn%20%20%3Cdiv%20class%3D%5C%22csl-entry%5C%22%3EZimmerman%2C%20Donald%20W.%2C%20and%20Bruno%20D.%20Zumbo%2C%20%26%23x2018%3BRelative%20Power%20of%20the%20Wilcoxon%20Test%2C%20the%20Friedman%20Test%2C%20and%20Repeated-Measures%20ANOVA%20on%20Ranks%26%23x2019%3B%2C%20%3Ci%3EThe%20Journal%20of%20Experimental%20Education%3C%5C%2Fi%3E%2C%2062.1%20%281993%29%2C%20pp.%2075%26%23x2013%3B86%2C%20%3Ca%20class%3D%27zp-DOIURL%27%20href%3D%27http%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1080%5C%2F00220973.1993.9943832%27%3Ehttp%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1080%5C%2F00220973.1993.9943832%3C%5C%2Fa%3E%3C%5C%2Fdiv%3E%5Cn%3C%5C%2Fdiv%3E%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Relative%20Power%20of%20the%20Wilcoxon%20Test%2C%20the%20Friedman%20Test%2C%20and%20Repeated-Measures%20ANOVA%20on%20Ranks%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Donald%20W.%22%2C%22lastName%22%3A%22Zimmerman%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Bruno%20D.%22%2C%22lastName%22%3A%22Zumbo%22%7D%5D%2C%22abstractNote%22%3A%22Many%20introductory%20statistics%20textbooks%20in%20education%2C%20psychology%2C%20and%20the%20social%20sciences%20consider%20the%20Friedman%20test%20to%20be%20a%20nonparametric%20counterpart%20of%20repeated-measures%20ANOVA%2C%20just%20as%20the%20Kruskal-Wallis%20test%20is%20a%20counterpart%20of%20oneway%20ANOVA.%20However%2C%20it%20is%20known%20in%20theoretical%20statistics%20that%20the%20Friedman%20test%20is%20a%20generalization%20of%20the%20sign%20test%20and%20possesses%20the%20modest%20statistical%20power%20of%20the%20sign%20test%20for%20normal%20as%20well%20as%20many%20nonnormal%20distributions.%20Although%20not%20familiar%20to%20researchers%2C%20another%20significance%20test%20that%20can%20be%20regarded%20as%20a%20nonparametric%20counterpart%20of%20repeated-measures%20ANOVA%20is%20a%20rank-transformation%20procedure%2C%20in%20which%20the%20usual%20parametric%20statistical%20analysis%20is%20performed%20on%20ranks%20replacing%20the%20original%20scores.%20In%20the%20present%20computer%20simulation%20study%20we%20compared%20the%20ordinary%20paired-samples%20Student%20t%20test%2C%20the%20Wilcoxon%20signed-ranks%20test%2C%20and%20the%20sign%20test%20for%20correlated%20samples%20from%20normal%2C%20uniform%2C%20mixed-normal%2C%20exponential%2C%20Laplace%2C%20and%20Cauchy%20distributions%2C%20for%20which%20the%20relative%20efficiency%20of%20the%20methods%20is%20known.%20We%20also%20compared%20repeated-measures%20ANOVA%2C%20repeated-measures%20ANOVA%20on%20ranks%2C%20and%20the%20Friedman%20test%20for%20k%20mutually%20correlated%20samples%20from%20the%20same%20distributions%2C%20where%20k%20%3D%202%2C3%2C%20and%204.%20Power%20functions%20revealed%20that%20the%20Friedman%20test%20performed%20like%20the%20sign%20test%20for%20all%20distributions%2C%20whereas%20ANOVA%20on%20ranks%20performed%20like%20the%20Wilcoxon%20test%20These%20comparisons%20emphasize%20that%20classification%20of%20these%20statistical%20tests%20in%20introductory%20textbooks%20should%20be%20revised%20and%20that%20more%20attention%20should%20be%20paid%20to%20the%20rank%20transformation%20concept.%22%2C%22date%22%3A%2207%5C%2F1993%22%2C%22language%22%3A%22en%22%2C%22DOI%22%3A%2210.1080%5C%2F00220973.1993.9943832%22%2C%22ISSN%22%3A%220022-0973%2C%201940-0683%22%2C%22url%22%3A%22http%3A%5C%2F%5C%2Fwww.tandfonline.com%5C%2Fdoi%5C%2Fabs%5C%2F10.1080%5C%2F00220973.1993.9943832%22%2C%22collections%22%3A%5B%224MZ8ZP2B%22%5D%2C%22dateModified%22%3A%222020-02-14T14%3A32%3A10Z%22%7D%7D%2C%7B%22key%22%3A%22HIT346R7%22%2C%22library%22%3A%7B%22id%22%3A2241481%7D%2C%22meta%22%3A%7B%22lastModifiedByUser%22%3A%7B%22id%22%3A5935700%2C%22username%22%3A%22yulyadudar%22%2C%22name%22%3A%22Iuliia%20Dudar%22%2C%22links%22%3A%7B%22alternate%22%3A%7B%22href%22%3A%22https%3A%5C%2F%5C%2Fwww.zotero.org%5C%2Fyulyadudar%22%2C%22type%22%3A%22text%5C%2Fhtml%22%7D%7D%7D%2C%22creatorSummary%22%3A%22Mann%20and%20Whitney%22%2C%22parsedDate%22%3A%221947-03%22%2C%22numChildren%22%3A0%7D%2C%22bib%22%3A%22%3Cdiv%20class%3D%5C%22csl-bib-body%5C%22%20style%3D%5C%22line-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%5C%22%3E%5Cn%20%20%3Cdiv%20class%3D%5C%22csl-entry%5C%22%3EMann%2C%20H.%20B.%2C%20and%20D.%20R.%20Whitney%2C%20%26%23x2018%3BOn%20a%20Test%20of%20Whether%20One%20of%20Two%20Random%20Variables%20Is%20Stochastically%20Larger%20than%20the%20Other%26%23x2019%3B%2C%20%3Ci%3EThe%20Annals%20of%20Mathematical%20Statistics%3C%5C%2Fi%3E%2C%2018.1%20%281947%29%2C%20pp.%2050%26%23x2013%3B60%2C%20%3Ca%20class%3D%27zp-DOIURL%27%20href%3D%27http%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1214%5C%2Faoms%5C%2F1177730491%27%3Ehttp%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1214%5C%2Faoms%5C%2F1177730491%3C%5C%2Fa%3E%3C%5C%2Fdiv%3E%5Cn%3C%5C%2Fdiv%3E%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22On%20a%20Test%20of%20Whether%20one%20of%20Two%20Random%20Variables%20is%20Stochastically%20Larger%20than%20the%20Other%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22H.%20B.%22%2C%22lastName%22%3A%22Mann%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22D.%20R.%22%2C%22lastName%22%3A%22Whitney%22%7D%5D%2C%22abstractNote%22%3A%22Let%20xxx%20and%20yyy%20be%20two%20random%20variables%20with%20continuous%20cumulative%20distribution%20functions%20fff%20and%20ggg.%20A%20statistic%20UUU%20depending%20on%20the%20relative%20ranks%20of%20the%20xxx%27s%20and%20yyy%27s%20is%20proposed%20for%20testing%20the%20hypothesis%20f%3Dgf%3Dgf%20%3D%20g.%20Wilcoxon%20proposed%20an%20equivalent%20test%20in%20the%20Biometrics%20Bulletin%2C%20December%2C%201945%2C%20but%20gave%20only%20a%20few%20points%20of%20the%20distribution%20of%20his%20statistic.%20Under%20the%20hypothesis%20f%3Dgf%3Dgf%20%3D%20g%20the%20probability%20of%20obtaining%20a%20given%20UUU%20in%20a%20sample%20of%20nx%5Cu2032snx%5Cu2032sn%20x%27s%20and%20my%5Cu2032smy%5Cu2032sm%20y%27s%20is%20the%20solution%20of%20a%20certain%20recurrence%20relation%20involving%20nnn%20and%20mmm.%20Using%20this%20recurrence%20relation%20tables%20have%20been%20computed%20giving%20the%20probability%20of%20UUU%20for%20samples%20up%20to%20n%3Dm%3D8n%3Dm%3D8n%20%3D%20m%20%3D%208.%20At%20this%20point%20the%20distribution%20is%20almost%20normal.%20From%20the%20recurrence%20relation%20explicit%20expressions%20for%20the%20mean%2C%20variance%2C%20and%20fourth%20moment%20are%20obtained.%20The%202rth%20moment%20is%20shown%20to%20have%20a%20certain%20form%20which%20enabled%20us%20to%20prove%20that%20the%20limit%20distribution%20is%20normal%20if%20m%2Cnm%2Cnm%2C%20n%20go%20to%20infinity%20in%20any%20arbitrary%20manner.%20The%20test%20is%20shown%20to%20be%20consistent%20with%20respect%20to%20the%20class%20of%20alternatives%20f%28x%29%3Eg%28x%29f%28x%29%3Eg%28x%29f%28x%29%20%3E%20g%28x%29%20for%20every%20xxx.%22%2C%22date%22%3A%221947-03%22%2C%22language%22%3A%22EN%22%2C%22DOI%22%3A%2210.1214%5C%2Faoms%5C%2F1177730491%22%2C%22ISSN%22%3A%220003-4851%2C%202168-8990%22%2C%22url%22%3A%22http%3A%5C%2F%5C%2Fprojecteuclid.org%5C%2Feuclid.aoms%5C%2F1177730491%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222022-01-05T19%3A27%3A30Z%22%7D%7D%2C%7B%22key%22%3A%22GKPG36KW%22%2C%22library%22%3A%7B%22id%22%3A2241481%7D%2C%22meta%22%3A%7B%22lastModifiedByUser%22%3A%7B%22id%22%3A5935700%2C%22username%22%3A%22yulyadudar%22%2C%22name%22%3A%22Iuliia%20Dudar%22%2C%22links%22%3A%7B%22alternate%22%3A%7B%22href%22%3A%22https%3A%5C%2F%5C%2Fwww.zotero.org%5C%2Fyulyadudar%22%2C%22type%22%3A%22text%5C%2Fhtml%22%7D%7D%7D%2C%22creatorSummary%22%3A%22Wilcoxon%22%2C%22parsedDate%22%3A%221945%22%2C%22numChildren%22%3A0%7D%2C%22bib%22%3A%22%3Cdiv%20class%3D%5C%22csl-bib-body%5C%22%20style%3D%5C%22line-height%3A%201.35%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%5C%22%3E%5Cn%20%20%3Cdiv%20class%3D%5C%22csl-entry%5C%22%3EWilcoxon%2C%20Frank%2C%20%26%23x2018%3BIndividual%20Comparisons%20by%20Ranking%20Methods%26%23x2019%3B%2C%20%3Ci%3EBiometrics%20Bulletin%3C%5C%2Fi%3E%2C%201.6%20%281945%29%2C%20p.%2080%2C%20%3Ca%20class%3D%27zp-DOIURL%27%20href%3D%27http%3A%5C%2F%5C%2Fdoi.org%5C%2F10.2307%5C%2F3001968%27%3Ehttp%3A%5C%2F%5C%2Fdoi.org%5C%2F10.2307%5C%2F3001968%3C%5C%2Fa%3E%3C%5C%2Fdiv%3E%5Cn%3C%5C%2Fdiv%3E%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Individual%20Comparisons%20by%20Ranking%20Methods%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Frank%22%2C%22lastName%22%3A%22Wilcoxon%22%7D%5D%2C%22abstractNote%22%3A%22%22%2C%22date%22%3A%2212%5C%2F1945%22%2C%22language%22%3A%22%22%2C%22DOI%22%3A%2210.2307%5C%2F3001968%22%2C%22ISSN%22%3A%2200994987%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fwww.jstor.org%5C%2Fstable%5C%2F10.2307%5C%2F3001968%3Forigin%3Dcrossref%22%2C%22collections%22%3A%5B%22IUKRIB7T%22%5D%2C%22dateModified%22%3A%222022-01-05T19%3A26%3A14Z%22%7D%7D%5D%7D
Lijffijt, Jefrey, Terttu Nevalainen, Tanja Säily, Panagiotis Papapetrou, Kai Puolamäki, and Heikki Mannila, ‘Significance Testing of Word Frequencies in Corpora’,
Digital Scholarship in the Humanities, 31.2 (2014), pp. 374–97,
http://doi.org/10.1093/llc/fqu064
Paquot, Magali, and Yves Bestgen, ‘Distinctive Words in Academic Writing: A Comparison of Three Statistical Tests for Keyword Extraction’, in Corpora: Pragmatics and Discourse, ed. by Andreas H. Jucker, Daniel Schreier, and Marianne Hundt (Brill | Rodopi, 2009), doi:10.1163/9789042029101_014
Woolson, R. F., ‘Wilcoxon Signed-Rank Test’, in Wiley Encyclopedia of Clinical Trials, ed. by Ralph B. D’Agostino, Lisa Sullivan, and Joseph Massaro (John Wiley & Sons, Inc., 2008), p. eoct979, doi:10.1002/9780471462422.eoct979
Zimmerman, Donald W., and Bruno D. Zumbo, ‘Relative Power of the Wilcoxon Test, the Friedman Test, and Repeated-Measures ANOVA on Ranks’,
The Journal of Experimental Education, 62.1 (1993), pp. 75–86,
http://doi.org/10.1080/00220973.1993.9943832
Mann, H. B., and D. R. Whitney, ‘On a Test of Whether One of Two Random Variables Is Stochastically Larger than the Other’,
The Annals of Mathematical Statistics, 18.1 (1947), pp. 50–60,
http://doi.org/10.1214/aoms/1177730491
Wilcoxon, Frank, ‘Individual Comparisons by Ranking Methods’,
Biometrics Bulletin, 1.6 (1945), p. 80,
http://doi.org/10.2307/3001968
