Higher-order Bartlett-type adjustment

作者: Yoshihide Kakizawa

DOI: 10.1016/S0378-3758(97)00051-7

关键词:

摘要: Abstract This paper deals with Bartlett-type adjustment which makes all the terms up to order n−k in asymptotic expansion vanish, where k is an integer ⩾ 1 and n depends on sample size. Extending Cordeiro Ferrari (1991, Biometrika, 78, 573–582) for case of = 1, we derive a general formula kth-order test statistic whose distribution given by finite linear combination chi-squared suitable degrees freedom. Two examples second-order are given. We also elucidate connection between Cornish-Fisher expansion.

参考文章(21)
David R. Cox, Nancy Reid, Approximations to noncentral distributions Canadian Journal of Statistics-revue Canadienne De Statistique. ,vol. 15, pp. 105- 114 ,(1987) , 10.2307/3315199
Peter Hall, Inverting an Edgeworth Expansion Annals of Statistics. ,vol. 11, pp. 569- 576 ,(1983) , 10.1214/AOS/1176346162
Minoru Siotani, An Asymptotic Expansion of the Non-Null Distribution of Hotelling's Generalized $T_0^2$-Statistic Annals of Mathematical Statistics. ,vol. 42, pp. 560- 571 ,(1971) , 10.1214/AOMS/1177693406
R. N. Bhattacharya, J. K. Ghosh, ON THE VALIDITY OF THE FORMAL EDGEWORTH EXPANSION Annals of Statistics. ,vol. 6, pp. 434- 451 ,(1978) , 10.1214/AOS/1176344134
C. S. Withers, Accurate confidence intervals for distributions with one parameter Annals of the Institute of Statistical Mathematics. ,vol. 35, pp. 49- 61 ,(1983) , 10.1007/BF02480963