Sample Size and Precision in Communication Performance Measurements

Martin J. Miles

Abstract: This report describes an interactive computer program that facilitates efficient measurement of communication system performance parameters. The program performs three primary functions: (1) determines the minimum sample size required to achieve a desired precision in estimating delay, rate, or failure probability parameters; (2) analyzes measurement results to determine the precision achieved; and (3) tests independent sets of measured data for statistical homogeneity. The report discusses statistical concepts underlying the program, shows how each function is performed, and provides comprehensive program documentation in the form of mathematical formulas, structured design diagrams, and the program listing. The program was written specifically to facilitate measurement of the performance parameters defined in a newly approved Data Communication Standard, American National Standard X3.l02. The statistical techniques implemented in it may also be applied to any other delay, rate, or failure probability measurement. The program is written in ANSI (1977) standard FORTRAN to enhance its portability. It is available from the author at duplication cost.

Keywords: performance parameters; statistical analysis; American National Standards; communication system; sample sizes

(84-153_ocr.pdf)

Disclaimer: Certain commercial equipment, components, and software may be identified in this report to specify adequately the technical aspects of the reported results. In no case does such identification imply recommendation or endorsement by the National Telecommunications and Information Administration, nor does it imply that the equipment or software identified is necessarily the best available for the particular application or uses.

Back to Search Results