Asymptotic Theory of Certain "Goodness of Fit" Criteria Based on Stochastic Processes

Anderson, Theodore Wilbur and Darling, Donald Allan (1952) Asymptotic Theory of Certain "Goodness of Fit" Criteria Based on Stochastic Processes. The Annals of Mathematical Statistics, 23 (2). pp. 193-212.

Full text not available from this repository.
Official URL: http://www.jstor.org/stable/2236446

Abstract

The statistical problem treated is that of testing the hypothesis that n independent, identically distributed random variables have a specified continuous distribution function F(x). If Fn(x) is the empirical cumulative distribution function and ψ(t) is some nonnegative weight function (0 ≤ t ≤ 1), we consider n^1/2 sup (-∞<x<∞) {|F(x)-Fn(x)|ψ^1/2[F(x)]} and n∫[F(x)-Fn(x)]^2ψ[F(x)]dF(x). a general method for calculating the limiting distributions of these criteria is developed by reducing them to corresponding problems in stochastic processes, which in turn lead to more or less classical eigenvalue and boundary value problems for special classes of differential equations. For certain weight functions including ψ=1 and ψ=1/[t(1-t)] we give explicit limiting distributions. A table of the asymptotic distribution of the von Mises ω^2 criterion is given.

[error in script]
Item Type: Article
Uncontrolled Keywords: Weighting functions, Stochastic processes, Mathematical functions, Distribution functions, Differential equations, Eigenvalues, Eigenfunctions, Statistics, Mathematical integrals
Application references: Inter-event Time Distribution Analysis
Subjects: Methodology > Method and procesing > Collective properties of seismicity > Source size distribution
Project: EPOS-IP