Process capability indices in normal distribution with the presence of outliers

Abstract

Process capability indices (PCIs) are useful measures to evaluate the performance and capability of a process when it is under control. Assuming the specification variable is distributed from a normal population, several PCIs are derived by the researchers. Also, many scientists have worked on these indices when data are contaminated with outliers as well as in the homogenous case. But, in almost all studies, they evaluated the effect of outliers on the PCIs nonparametrical and used robust methods. Here, the parametric model of outliers is considered and introduced the PCIs based on the outliers model. Therefore, these indices are estimated based on the maximum-likelihood and moment estimator of the unknown parameters of the normal distribution contaminated by outliers. Finally, the performances of these measures as well as their parametric and nonparametric estimators are discussed by using simulation studies and several numerical examples. It has been seen that parametric estimation has better performances than a nonparametric method.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 10 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.