JOURNAL OF THE JAPAN STATISTICAL SOCIETY
Online ISSN : 1348-6365
Print ISSN : 1882-2754
ISSN-L : 1348-6365
POWER APPROXIMATIONS OF THE TEST OF HOMOGENEITY FOR MULTINOMIAL POPULATIONS
Nobuhiro TaneichiYuri Sekiya
著者情報
ジャーナル フリー

1995 年 25 巻 1 号 p. 97-109

詳細
抄録
In this paper we propose three approximations to the power of the power-divergence statistic Ra on the test of homogeneity for multinomial populations. These approximations are based on the approximation theories for the multinomial goodness-of-fit test as proposed by Broffitt and Randles (1977) and Drost et al. (1989). One approximation is constructed from a limiting normal distribution of Ra. The others are constructed from the linear and quadratic terms of a Taylor series expansion of Ra. These approximations are compared with the power directly calculated from the product multinomial model. As a result of this comparison, the latter approximations are found to perform well when a≥0. On the homogeneity of two populations, we investigate the power of representative power divergence statistics R0, R2/8 and R1 using the latter approximations. Then, corresponding to alternatives, relations to the power of the three statistics are discussed.
著者関連情報
© Japan Statistical Society
前の記事 次の記事
feedback
Top