This paper proposes the confidence interval for the coefficient of variation in a normal distribution with a known population mean after a preliminary T test. This has applications when one knows the population mean of a control group. A Monte Carlo simulation study was conducted to evaluate the performance of the proposed confidence interval with two existing confidence intervals. Two performance measures were used to assess the confidence interval for the coefficient of variation, namely: coverage probability and expected length. Simulation results showed that the proposed confidence interval performs well in terms of coverage probability and expected length compared with two existing confidence intervals. A real data example presenting the melting point of beeswax from 59 sources was used for illustration and performing a comparison.
Keywords: measure of dispersion, preliminary test, coverage probability, expected length, simulation study.
Corresponding author: E-mail : wararit@mathstat.sci.tu.ac.th
Panichkitkosolkul*, W. . (2018). Confidence Interval for The Coefficient of Variation in A Normal Distribution with A Known Population Mean after A Preliminary T Test. CURRENT APPLIED SCIENCE AND TECHNOLOGY, 34-46.
