A RULE-OF-THUMB METHOD FOR OBTAINING MINIMUM VAIIANCE ESTIMATES OF STANDARD DEVIATION FROM NORMAL DATA,
Abstract
A rule-of-thumb method is derived for reducing a sample of statistically independent data, obtained from an unbiased, circular normal distribution, so as to yield an unbiased, minimum variance estimate of the standard deviation fo the parent distribution. By establishment of a mathematical model, the concept of minimum variance is developed, and the rule-of-thumb approximation is derived. Sources of error are considered to determine the accuracy of the method employed. The computational technique employed provides an example of the empirical establishment of a mathematical theorem which is valid over the intended range of its applicability and which cannot, to the author's knowledge, be established in any other manner. It is suggested, as a corollary to this study, that contractual specifications for missile systems which refer to circular error probable (CEP) be modified in future contracts in such a manner that these CEP specifications be replaced by corresponding specifications with respect to the radius of a circle containing 80 per cent of the test shots. (Author)
Document Details
- Document Type
- Technical Report
- Publication Date
- Dec 07, 1964
- Accession Number
- AD0452575
Entities
People
- Marilyn A. Brown