Successive maxima of samples from a GEM distribution

Publication date 6 September 2016

Abstract: We show that the maximal value in a size

n

sample from GEM

(h e t a)

distribution is distributed as a sum of independent geometric random variables. This implies that the maximal value grows as

h e t a l o g (n)

as

n o i n f t y

. For the two-parametric GEM

(a l p h a, h e t a)

distribution we show that the maximal value grows as a random factor of

n^{a l p h a / (1 - a l p h a)}

and find the limiting distribution.

This page was built for publication: Successive maxima of samples from a GEM distribution