Multivariate extremal processes generated by independent non-identically distributed random variables

1 March 1975

journal article
research article
Published by Cambridge University Press (CUP) in Journal of Applied Probability

Vol. 12 (03) , 477-487
https://doi.org/10.1017/s0021900200048282

Abstract

Letbe thekth largest amongX_n1, …,X_n[nt], whereX_ni= (X_i– a_n)/b_n, {X_i} is a sequence of independent random variables andb_n> 0 anda_nare norming constants. Suppose that for eachconverges in distribution. Then all the finite-dimensional laws ofconverge. The limiting process is represented in terms of a non-homogeneous two-dimensional Poisson process.

Keywords

This publication has 4 references indexed in Scilit:

The structure of extremal processes
Advances in Applied Probability, 1973
The two-dimensional Poisson process and extremal processes
Journal of Applied Probability, 1971
Extremal Processes, II
Illinois Journal of Mathematics, 1966
On Extreme Order Statistics
The Annals of Mathematical Statistics, 1964