Back To Index Previous Article Next Article Full Text


Statistica Sinica 6(1996), 299-309


BOOTSTRAPPING A SAMPLE QUANTILE WHEN THE

DENSITY HAS A JUMP


J. S. Huang, P. K. Sen and J. Shao


University of Guelph, University of North Carolina


Abstract: Albeit the superiority of bootstrapping to jackknifing in estimating the (asymptotic) variance of a sample quantile in the regular case, the bootstrap may encounter technical problems in some non-regular cases. The related methodology for one such important non-regular case is considered here, and the theory is supplemented with numerical studies.



Key words and phrases: Bahadur representation, bootstrap, nonregular density, sample quantile.



Back To Index Previous Article Next Article Full Text