No label defined (Q3769775)

From MaRDI portal

!

This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use the normal view instead:

scientific article; zbMATH DE number 4028628
Language Label Description Also known as
default for all languages
No label defined
    English
    No label defined
    scientific article; zbMATH DE number 4028628

      Statements

      0 references
      1989
      0 references
      moment generating function
      0 references
      estimators for the k-th moments
      0 references
      stochastic geyser
      0 references
      Let \(X_ 1,X_ 2,..\). be i.i.d. r.v. and \(S_ n=X_ 1+X_ 2+...+X_ n\) their cumulative sums. Suppose that we observe the quantities Ŝ\({}_ n=S_ n+R_ n\) where \(R_ n\) is a small random perturbation. \textit{P. Bártfai} [ibid. 1, 161-168 (1966; Zbl 0156.391)] proved that if the moment generating function (m.g.f.) of \(X_ 1\) exists, and if \(R_ n=o(\log n)\) a.s., then the distribution function of \(X_ 1\) can be determined with probability one from the infinite sequence of observations. His proof, however, [and also the ones given later, cf., e.g., \textit{P. Erdős} and \textit{A. Rényi}, J. Anal. Math. 23, 103-111 (1970; Zbl 0225.60015)] does not give a clue as to how one could estimate the distribution function (or a functional thereof) from a finite set of observations. In the present paper, we shall give a sequence of estimators for the m.g.f. of \(X_ 1\) which will then be used to derive estimators for the k-th moments that will turn out to be valid even in the case when the m.g.f. itself does not exist.
      0 references

      Identifiers

      0 references
      0 references
      0 references
      0 references