Control charts are one of the most used and important tools in statistical quality control. It is essential to design control charts considering the estimation effects. To that end, research has addressed these effects from an unconditional perspective and, recently, under a conditional one. This project examines and compares these perspectives, in terms of the performance of the graphs for monitoring the variance of the process, whose study to date has been incomplete. Then, according to the conditional perspective, it proposes new criteria for the design of graphics based on tolerance intervals, whose mathematical-statistical relationship is identified and used. These new designs are compared with the traditional one and their most relevant advantages are highlighted. Finally, new knowledge, some practical recommendations, and the development of an R package are provided, all aimed at professionals and researchers working on monitoring and improving the quality of manufacturing processes and services.
Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.