A Survey of Confidence Interval Formulae for Coverage Analysis
Jong-Suk Ruth Lee, Donald McNickle and Krzysztof Pawlikowski
Department of Computer Science
University of Canterbury
Abstract
Confidence interval estimators for proportions using normal approximation have been commonly used for coverage analysis of simulation output even though alternative approximate estimators of confidence intervals for proportions were proposed. This is because the normal approximation was easier to use in practice than the other approximate estimators. Computing technology has no problem with dealing these alternative estimators. Recently, one of the approximation methods for coverage analysis which is based on arcsin transformation has been used for estimating proportion and for controlling the required precision in [Raa95].
In this report, we compare three approximate interval estimators, based on a normal distribution approximation, an arcsin transformation and an F-distribution approximation, of a single proportion. These have application in sequential coverage analysis, conducted for assessing the quality of methods used in simulation output data analysis.
Keywords : sequential simulation, coverage analysis, confidence interval, proportion