Logarithmic Quantile Estimation for Rank Statistics
We prove an almost sure weak limit theorem for simple linear rank statistics for samples with continuous distributions functions. As a corollary, the result extends to samples with ties and to the vector version of an almost sure (a.s.) central limit theorem for vectors of linear rank statistics. Moreover, we derive such a weak convergence result for some quadratic forms. These results are then applied to quantile estimation, and to hypothesis testing for nonparametric statistical designs, here demonstrated by the c-sample problem, where the samples may be dependent. In general, the method is known to be comparable to the bootstrap and other nonparametric methods (Thangavelu 2005; Fridline 2009), and we confirm this finding for the c-sample problem.
KeywordsAlmost sure central limit theorem Rank statistics Logarithmic quantile estimation Kruskal-Wallis statistic
AMS Subject Classification62E20 62G20
Unable to display preview. Download preview PDF.
- Denker, M., and M. Fridline. 2010. The almost sure version of Cramer’s theorem. In Dependence in probability, analysis and number theory, 195–201. Heber City, UT: Kendrick Press.Google Scholar
- Fridline, M. 2009. Almost sure confidence intervals for the correlation coefficient. Ph.D. thesis, Case Western Reserve University, Cleveland, OH.Google Scholar
- Lifshits, M. A. 2001. Lecture notes on almost sure limit theorems. Publications IRMA, Lille, 54, No. 8, 1–23.Google Scholar
- Zöfel, P. 1992. Univariate Varianzanalysen. Uni-Taschenbuch 1663, G. Fischer Verlag, Jena, Stuttgart.Google Scholar