Exclusive Content & Downloads from ASQ

Using Graphical Diagnostics to Deal With Bad Data

Summary: [This abstract is based on the authors' abstract.]The problem of how to deal with individual results that do not appear to fit with the rest of the data is considered. Graphical tools are provided that aid in the diagnosis of this response data while maintaining a balance between deleting data that vary due to common causes and not detecting true outliers that occur due to special causes. The review of two real life data sets demonstrates that diagnostic plots found in readily available statistical software aid in determining the course of action needed to draw proper conclusions from experiments that produce bad data.

Anyone with a subscription, including Site and Enterprise members, can access this article.

Other Ways to Access content:

Join ASQ

Join ASQ as a Full member. Enjoy all the ASQ member benefits including access to many online articles.

  • Topics: Design of Experiments, Data Quality, Engineering, Statistics
  • Keywords: Box-Cox model, Design of experiments (DOE), Diagnostics, Outliers, Transformation
  • Author: Anderson, Mark J.; Whitcomb, Patrick J.
  • Journal: Quality Engineering