How to Estimate the Sigma Level of the Process

Methodology/Approach: The approach is based on a model in which the process has a normal distribution and constant variance, and its mean is shifted to the right or left by 1.5 standard deviations.


Findings: The paper explains a method for creating a random sample along with determining the sample size to estimate the “defects per million opportunities” characteristic through a confidence interval. Based on it, the confidence interval for the “sigma level” of the process is determined.


Research Limitation/implication: We assume a discrete process in which n pieces of the product are selected. The proposed procedure assumes that the process is in statistical control.


Originality/Value of paper: Applying the proposed random sampling and estimation procedure can improve evaluations of process performance, aiding decision-making for Six Sigma projects.