Applying series expansion to the inverse beta distribution to find percentiles of the F-distribution
暂无分享,去创建一个
Let <italic>0 ≤</italic> 1 and <italic>F</italic> be the cumulative distribution function (cdf) of the <italic>F</italic>-Distribution. We wish to find <italic>x<subscrpt>p</subscrpt></italic> such that <italic>F(x<subscrpt>p</subscrpt>|n<subscrpt>1</subscrpt>, n<subscrpt>2</subscrpt>) = p</italic>, where <italic>n<subscrpt>1</subscrpt></italic> and <italic>n<subscrpt>2</subscrpt></italic> are the degrees of freedom. Traditionally, <italic>x<subscrpt>p</subscrpt></italic> is found using a numerical root-finding method, such as Newton's method. In this paper, a procedure based on a series expansion for finding <italic>x<subscrpt>p</subscrpt></italic>is given. The series expansion method has been applied to the normal, chi-square, and <italic>t</italic> distributions, but because of computational difficulties, it has not been applied to the <italic>F</italic>-Distribution. These problems have been overcome by making the standard transformation to the beta distribution.
The procedure is explained in Sections 3 and 4. Empirical results of a comparison of CPU times are given in Section 5. The series expansion is compared to some of the standard root-finding methods. A table is given for <italic>p</italic> = .90.
[1] G. P. Bhattacharjee,et al. Inverse of the Incomplete Beta Function Ratio , 1973 .
[2] A. W. Davis,et al. Generalized Asymptotic Expansions of Cornish-Fisher Type , 1968 .
[3] Carter Ah. Approximation to percentage points of the Z-distribution. , 1947 .
[4] A. Carter. Approximation to percentage points of the Z-distribution. , 1947, Biometrika.
[5] Henry Goldberg,et al. Approximate Formulas for the Percentage Points and Normalization of $t$ and $x^2$ , 1946 .