Abstract
LetX 1,X 2,... be a sequence of independent random variables with distributionF. Suppose that 0<p<1, thatξ p is the uniquepth quantile ofF, and thatξ p,n is the samplepth quantile ofX 1,...,X n . Ifb(n)→0+ sufficiently slowly, then
and
are proper random variables (finite with probability one). In this paper we investigate the moment behavior of exp{Nb 2 (N)} and exp{Lb 2 (L)}.
Similar content being viewed by others
References
Babu, G. J., and Singh, K. (1982). Onr-quick limit sets for empirical and related processes based on mixing random variables.Journal of Multivariate Analysis 12, 508–525.
Chao, C.-C. (1984). Unpublished Ph.D. dissertation, SUNY, Buffalo.
De Haan, L. (1974). On sample quantiles from a regularly varying distribution function.Ann. Stat. 2, 815–818.
Russo, R. P., and Chao, C.-C. (1987). Boundary crossing random variables related to quantile convergence,Stat. Prob. Lett. 6, 117–123.
Sefling, R. J. (1980).Approximation Theorems of Mathematical Statistics, John Wiley and Sons, New York.
Slivka, J., and Severo, N. C. (1970). On the strong law of large numbers,Proc. Amer. Math. Soc. 24, 729–734.
Takács, L. (1970). On the fluctuations of election returns.J. Appl. Prob. 7, 114–123.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Rothmann, M.D., Russo, R.P. On boundary crossings of the samplepth quantile. J Theor Probab 5, 407–416 (1992). https://doi.org/10.1007/BF01046744
Received:
Issue Date:
DOI: https://doi.org/10.1007/BF01046744