𝔖 Bobbio Scriptorium
✦   LIBER   ✦

Improvement of approximations for the distributions of multinomial goodness-of-fit statistics under nonlocal alternatives

✍ Scribed by Yuri Sekiya; Nobuhiro Taneichi

Publisher
Elsevier Science
Year
2004
Tongue
English
Weight
236 KB
Volume
91
Category
Article
ISSN
0047-259X

No coin nor oath required. For personal study only.

✦ Synopsis

Cressie and Read (J. Roy. Statist. Soc. B 46 (1984) introduced the power divergence statistics, R a ; as multinomial goodness-of-fit statistics. Each R a has a limiting noncentral chi-square distribution under a local alternative and has a limiting normal distribution under a nonlocal alternative. Taneichi et al. (J. Multivariate Anal. 81 (2002) 335-359) derived an asymptotic approximation for the distribution of R a under local alternatives. In this paper, using multivariate Edgeworth expansion for a continuous distribution, we show how the approximation based on the limiting normal distribution of R a under nonlocal alternatives can be improved. We apply the expansion to the power approximation for R a : The results of numerical investigation show that the proposed power approximation is very effective for the likelihood ratio test.

πŸ“œ SIMILAR VOLUMES

Asymptotic Approximations for the Distri
Asymptotic Approximations for the Distributions of the Multinomial Goodness-of-Fit Statistics under Local Alternatives
✍ Nobuhiro Taneichi; Yuri Sekiya; Akio Suzukawa πŸ“‚ Article πŸ“… 2002 πŸ› Elsevier Science 🌐 English βš– 172 KB

introduced a class of multinomial goodness-of-fit statistics R a based on power divergence. All R a have the same chi-square limiting distribution under null hypothesis and have the same noncentral chi-square limiting distribution under local alternatives. In this paper, we investigate asymptotic ap

Asymptotic distributions for goodness-of
Asymptotic distributions for goodness-of-fit statistics in a sequence of multinomial models
✍ L. GyΓΆrfi; I. Vajda πŸ“‚ Article πŸ“… 2002 πŸ› Elsevier Science 🌐 English βš– 130 KB

We consider f-disparities D f ( pn ; p n ) between discrete distributions p n = (p n1 ; : : : ; p nkn ) and their estimates pn = ( pn1 ; : : : ; pnkn ) based on relative frequencies in an i.i.d. sample of size n, where f : (0; ∞) β†’ R is twice continuously di erentiable in a neighborhood of 1 with f