Cover Image

Nearly exact sample size calculation for powerful non-randomized tests for differences between binomial proportions

In the case of two independent samples, it turns out that among the procedures taken in consideration, BOSCHLOO'S technique of raising the nominal level in the standard conditional test as far as admissible performs best in terms of power against almost all alternatives. The computational burde...

Full description

Saved in:
Bibliographic Details
Main Author: Wellek, Stefan (Author)
Format: Article (Journal)
Language:English
Published: 23 March 2015
In: Statistica Neerlandica
Year: 2015, Volume: 69, Issue: 4, Pages: 358-373
ISSN:1467-9574
DOI:10.1111/stan.12063
Online Access:Verlag, Volltext: http://dx.doi.org/10.1111/stan.12063
Verlag, Volltext: http://onlinelibrary.wiley.com.ezproxy.medma.uni-heidelberg.de/doi/10.1111/stan.12063/abstract
Get full text
Author Notes:Stefan Wellek

MARC

LEADER 00000caa a2200000 c 4500
001 1567038522
003 DE-627
005 20220814054721.0
007 cr uuu---uuuuu
008 180110s2015 xx |||||o 00| ||eng c
024 7 |a 10.1111/stan.12063  |2 doi 
035 |a (DE-627)1567038522 
035 |a (DE-576)497038528 
035 |a (DE-599)BSZ497038528 
035 |a (OCoLC)1340985825 
040 |a DE-627  |b ger  |c DE-627  |e rda 
041 |a eng 
084 |a 33  |2 sdnb 
100 1 |a Wellek, Stefan  |d 1945-  |e VerfasserIn  |0 (DE-588)1034560867  |0 (DE-627)745854095  |0 (DE-576)382153774  |4 aut 
245 1 0 |a Nearly exact sample size calculation for powerful non-randomized tests for differences between binomial proportions  |c Stefan Wellek 
264 1 |c 23 March 2015 
300 |a 16 
336 |a Text  |b txt  |2 rdacontent 
337 |a Computermedien  |b c  |2 rdamedia 
338 |a Online-Ressource  |b cr  |2 rdacarrier 
500 |a Gesehen am 10.01.2018 
520 |a In the case of two independent samples, it turns out that among the procedures taken in consideration, BOSCHLOO'S technique of raising the nominal level in the standard conditional test as far as admissible performs best in terms of power against almost all alternatives. The computational burden entailed in exact sample size calculation is comparatively modest for both the uniformly most powerful unbiased randomized and the conservative non-randomized version of the exact Fisher-type test. Computing these values yields a pair of bounds enclosing the exact sample size required for the Boschloo test, and it seems reasonable to replace the exact value with the middle of the corresponding interval. Comparisons between these mid-N estimates and the fully exact sample sizes lead to the conclusion that the extra computational effort required for obtaining the latter is mostly dispensable. This holds also true in the case of paired binary data (McNemar setting). In the latter, the level-corrected score test turns out to be almost as powerful as the randomized uniformly most powerful unbiased test and should be preferred to the McNemar-Boschloo test. The mid-N rule provides a fairly tight upper bound to the exact sample size for the score test for paired proportions. 
650 4 |a binomial two-sample problem 
650 4 |a Boschloo's approach 
650 4 |a exact non-conditional test 
650 4 |a maximized p-value 
650 4 |a McNemar setting 
650 4 |a nuisance parameter 
650 4 |a score statistic 
773 0 8 |i Enthalten in  |t Statistica Neerlandica  |d Oxford : Wiley-Blackwell, 1996  |g 69(2015), 4, Seite 358-373  |h Online-Ressource  |w (DE-627)266018351  |w (DE-600)1466958-4  |w (DE-576)082435154  |x 1467-9574  |7 nnas  |a Nearly exact sample size calculation for powerful non-randomized tests for differences between binomial proportions 
773 1 8 |g volume:69  |g year:2015  |g number:4  |g pages:358-373  |g extent:16  |a Nearly exact sample size calculation for powerful non-randomized tests for differences between binomial proportions 
856 4 0 |u http://dx.doi.org/10.1111/stan.12063  |x Verlag  |x Resolving-System  |3 Volltext 
856 4 0 |u http://onlinelibrary.wiley.com.ezproxy.medma.uni-heidelberg.de/doi/10.1111/stan.12063/abstract  |x Verlag  |3 Volltext 
951 |a AR 
992 |a 20180110 
993 |a Article 
994 |a 2015 
998 |g 1034560867  |a Wellek, Stefan  |m 1034560867:Wellek, Stefan  |d 60000  |e 60000PW1034560867  |k 0/60000/  |p 1  |x j  |y j 
999 |a KXP-PPN1567038522  |e 2992559105 
BIB |a Y 
SER |a journal 
JSO |a {"name":{"displayForm":["Stefan Wellek"]},"origin":[{"dateIssuedDisp":"23 March 2015","dateIssuedKey":"2015"}],"id":{"eki":["1567038522"],"doi":["10.1111/stan.12063"]},"physDesc":[{"extent":"16 S."}],"relHost":[{"pubHistory":["Nachgewiesen 50.1996 -"],"part":{"extent":"16","volume":"69","text":"69(2015), 4, Seite 358-373","pages":"358-373","issue":"4","year":"2015"},"note":["Gesehen am 11.04.2022"],"type":{"bibl":"periodical","media":"Online-Ressource"},"disp":"Nearly exact sample size calculation for powerful non-randomized tests for differences between binomial proportionsStatistica Neerlandica","recId":"266018351","language":["eng"],"corporate":[{"role":"isb","display":"Vereniging voor Statistiek en Operationele Research","roleDisplay":"Herausgebendes Organ"}],"title":[{"title":"Statistica Neerlandica","subtitle":"journal of the Netherlands Society for Statistics and Operations Research","title_sort":"Statistica Neerlandica"}],"physDesc":[{"extent":"Online-Ressource"}],"origin":[{"publisherPlace":"Oxford ; Oxford","dateIssuedDisp":"1996-","publisher":"Wiley-Blackwell ; Blackwell","dateIssuedKey":"1996"}],"id":{"issn":["1467-9574"],"zdb":["1466958-4"],"doi":["10.1111/(ISSN)1467-9574"],"eki":["266018351"]}}],"person":[{"role":"aut","roleDisplay":"VerfasserIn","display":"Wellek, Stefan","given":"Stefan","family":"Wellek"}],"title":[{"title_sort":"Nearly exact sample size calculation for powerful non-randomized tests for differences between binomial proportions","title":"Nearly exact sample size calculation for powerful non-randomized tests for differences between binomial proportions"}],"note":["Gesehen am 10.01.2018"],"type":{"bibl":"article-journal","media":"Online-Ressource"},"recId":"1567038522","language":["eng"]} 
SRT |a WELLEKSTEFNEARLYEXAC2320 

Similar Items