科研之友
微信
新浪微博
Facebook
分享链接
摘要
Let {X-n} be a sequence of independent and identically distributed random variables defined over a common probability space (Q,F,P) with common continuous distribution function F. Define eta(n) = max(n-an) < j <= (n)Xj(,) where a(n) is an integer with 0 < a(n) < n,n > 1. For any constant a > 0, let K-n((m))(a)=# {j,n-a(n) < j <= n,X-j is an element of (eta(n)-a, eta(n) )}> 1. Then K-n((m))(a) denotes the number of observations near moving maxima. In this paper, we obtain conditions for (K-n((m))(a)) to converge to 1 almost surely (a.s.), when a(n) ={n(p)}, and a(n) = [pn],0 = 1.
- 出版日期2013-1
