Frank G. Landram
Abstract
By computing probabilities from the normalization of the F distribution (instead of by numerical integration methods), statistical capabilities in spreadsheet operations can be greatly expanded and enhanced.
- 1 Hastings. C., Jr. Approximations for Digital Computers. Princeton University Press. Princeton, N.J., 1955. Gives a description of the closed function that approximates the corresponding probability of a normalized value. Google Scholar
Digital Library
- 2 Kelley, T.L. Fundamenfals ofStatistics. Harvard University Press, Cambridge, Mass. 1947. pp. 325-331. Describes the normalization of the F distribution and its correction for small sample sizes.Google Scholar
- 3 Kendall. MC. The Advanced Theory of Statistics, vol. 2. Charles Griffen. London, 1955. pp. 116-116. Describes the normalization of the F distribution.Google Scholar
- 4 Smillies. K.W. and Anstey. T.H. A note on the calculation of probabilities in an F distribution. Commun. ACM 7. 12 (Dec. 1964). 725. Connects the normalization of the F distribution with a Hastings approximation. Google ScholarDigital Library
Index Terms
- Spreadsheet calculations of probabilities from the F, t, χ2, and normal distribution
Recommendations
The beta generalized half-normal distribution
For the first time, we propose the so-called beta generalized half-normal distribution, which contains some important distributions as special cases, such as the half-normal and generalized half-normal (Cooray and Ananda, 2008) distributions. We derive ...
The evaluation of two-sided orthant probabilities for a quadrivariate normal distribution
In this paper it is shown how a general two-sided orthant probability for a quadrivariate normal distribution can be evaluated by a one-dimensional numerical integral calculation. The quadrivariate normal distribution can have any covariance matrix and ...
The multilinear normal distribution: Introduction and some basic properties
In this paper, the multilinear normal distribution is introduced as an extension of the matrix-variate normal distribution. Basic properties such as marginal and conditional distributions, moments, and the characteristic function, are also presented. A ...
Reviews
Stanley Wertheimer
In the Conclusion, the authors state, “The difficulty of computing probabilities for the F, t, &khgr; 2, and normal distributions restricts the use of statistics in spreadsheet operations because these probabilities are typically computed from numerical integration methods that require an iterative procedure.” The authors' method normalizes the F distribution which allows probabilities to be computed from a closed formula; the t and &khgr; 2 are likewise converted to an F value, and the previous method is used. The authors claim two-decimal-place accuracy; a little experimentation found no fault with this claim. However, two decimal places are not two significant figures. Thus, where they claim the probability to be 0.05, I found 0.0510 (&khgr; 2), 0.0481 (t), and 0.0497 (F). This work is surely of value to spreadsheet users who need to do these type of statistical calculations.
Access critical reviews of Computing literature here
Become a reviewer for Computing Reviews.
Comments