並列摘要
An important characteristic in quality industry is resistivity which is well known to have a distribution with heavy right tail and thus a gamma distribution may indeed be appropriate. For positive observations analysis can often be based on either the log-normal or the gamma model. It is well known that the gamma model with the constant coefficient of variation and the log-normal model with constant variance often give similar analyses. However, in the analysis for resistivity data, neither the coefficient of variation nor the variance needs to be constant, so that the two models do not necessarily give similar results. A choice needs to be made between the gamma and the lognormal models of resistivity for non-constant variance. This article examines the resistivity distribution based on three real examples. It identifies that the variance of resistivity may be constant and non-constant. Analyses of two examples show that estimates of log-normal and gamma distribution fit are almost same. However, the analysis of one example shows that log-normal fit is slightly better than gamma fit.