Approximating the power of Wilcoxon's ra
โ
James F. Troendle
๐
Article
๐
1999
๐
John Wiley and Sons
๐
English
โ 151 KB
Three methods of approximating the power of Wilcoxon's rank-sum test against shift alternatives are studied. They are obtained by using a Gaussian assumption, Edgeworth expansion, or bootstrap. It is assumed that a historical data set is available to use in estimating the shape of the distribution.