Abstract
Suppose that a statistic is asymptotically distributed as a distribution function as some parameter . We consider monotone transformations of in order to improve the asymptotic approximation. The transformations proposed here preserve monotonicity and give transformed statistics whose distribution function is coincident with up to the order . It may be observed that the proposed transformations give a significant improvement to approximations. Further, we shall also consider error bounds for the remainder term of an asymptotic expansion for the distribution of . Finally, some applications of the findings are demonstrated for some test statistics.
Funding Statement
Research of the second author was partially supported by Grant-in-Aid for Exploratory Research, the Ministry of Education, Culture, Sports, Science and Technology, Japan, under Contract Number 16650059.
Acknowledgments
We are grateful to the referee for helpful comments.
Citation
Hiroyuki Enoki. Makoto Aoshima. "Transformations with improved asymptotic approximations and their accuracy." SUT J. Math. 42 (1) 97 - 122, January 2006. https://doi.org/10.55937/sut/1159987680
Information