• Refine Query
  • Source
  • Publication year
  • to
  • Language
  • No language data
  • Tagged with
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • About
  • The Global ETD Search service is a free service for researchers to find electronic theses and dissertations. This service is provided by the Networked Digital Library of Theses and Dissertations.
    Our metadata is collected from universities around the world. If you manage a university/consortium/country archive and want to be added, details can be found on the NDLTD website.
1

相關變數之隨機修剪L : 統計量之漸近性 / On the asymptotic behavior of randomly trimmed L-statistics with dependent random variables

陳宗雄 Unknown Date (has links)
摘要 本文主要在探討絕對正則隨機變數序列的隨機修剪L統計量的漸近性,當修剪係系數收斂至a和b時(O<a<b<l),對它們的分配函數限制並不多;然而當a=0及b=1 時,則限制的條件須更加嚴格,這也就是為什麼我們要做隨機修剪的主要原因。同時,由於大部分的時間序列模式都是絕對正則的隨機變數序列,這也是研究本文的主要動機之一。 本文是想嘗試著把G. R. Shorack (1989)的論文隨機修剪L統計量,推廣,把該文中立相獨立的隨機變數序列換成絕對正則的隨機變數序列。在這同時,我們必需將一些經驗累積分配函數的不等式推廣,推廣過程中將重覆使用Yoshihara (1978) 的機率不等式。 / ABSTRACT We will prove central limit theorem for randomly trimmed L-statistics with absolutely regular random variables. When the fractions trimmed converge to a and l-b, (with 0<a<b<l) there are little restrictions on the df's of the r.v.'s, - but the limiting r.v. has several contributing terms, making the studentization complicated unless the trimming fractions converge fast enough. For a=0 and b=l, the restriction on the rate of convergence of the trimming fractions is more severe, however this is a most reasonable way to trim.

Page generated in 0.0663 seconds