On the performance of coefficient of variation charts in the presence of measurement errors

AbstractIn the literature, coefficient of variation control charts have been introduced under the assumption of no measurement errors. However, measurement errors always exist in practice, and they do affect the performance of control charts in the detection of an out‐of‐control situation. In this paper, we therefore study the performance of a coefficient of variation Shewhart‐type control chart (Shewhart‐CV chart) and also one‐sided coefficient of variation exponentially weighted moving average–type control charts (EWMA‐γ2charts) using a model with linear covariates. Moreover, we propose and study the performance of a two‐sided EWMA‐γ2chart using a model with linear covariates. Several figures and tables are provided and analyzed to evaluate the statistical performance of these control charts for different sources of measurement errors. The obtained results show that theprecisionandaccuracyerrors significantly affect the performance of both the Shewhart‐CV and EWMA‐γ2control charts. An example illustrating the use of this study is finally presented.

On the performance of coefficient of variation charts in the presence of measurement errors Journal Articles