The Effect of Autocorrelated Data on Taguchi Process Capability Index Cpm Based on AR(1) Model

Most previous researches on process capability analysis do not specifically test the independence assumption for observations. However, autocorrelation is prevalent in continuous production processes especially in chemical and pharmaceutical industries. With the development of measurement technology and data acquisition technology, sampling frequency is getting higher and higher and the existence of autocorrelation cannot be ignored. This paper discusses the statistical characteristics of Taguchi process capability index for autocorrelated data. For AR(1) model, the estimation of Taguchi process capability index (Ccirc_pmr) is analyzed. The effects of autocorrelated data on mean, standard deviation and probability distribution of Ccirc_pmr are discussed.