Chapter 10: Is the Process Stable?

A Stable Process

A stable process is predictable, where a capable process can reliably produce parts within specification limits (more on this later). A process is stable if it has a constant mean and a constant variance over time. Processes must prove to be stable before they can be used (IST, 2012), because it makes the production process more efficient (ISIXSIGMA, 2022). The tool used to determine stability is a histogram. More than 100 samples are logged over a long period of time and are plotted. It can be beneficial to calculate control limits and add those to the plotted data as well (IST, 2012).

Stability is required before evaluating for capability, because the process must be well understood. It must be a good process before determining if it is capable. All of the special causes of variation in the system are evaluated for stability before determining if they are capable. For example: a manufacture is handling a claim process where the amount of time required to process claims would be stable and consistent, all known variations identified. If this process is not stable, it may not be capable to meet customer demands in a timely fashion (benchmark 6ix sigma, 2017).


Value of a Histogram

A histogram is a visual representation of data, which the viewer can generally understand easily and interpret the data. Histograms are used when evaluating data that is continuous and counted as separate distinct values (or discrete data). Histograms are valuable to convey information effectively and to show changes implemented within a process (Presentationeze, 2013). Histograms can also identify outliers in a process (Frost, 2019). Learn more about using histograms to understand data with this article.


Determining Stability

"Automotive Industry" by bisgovuk is licensed under CC BY-ND 2.0.
Automotive Industry” by bisgovuk is licensed under CC BY-ND 2.0.

If the process is not stable, the data would not be reliable enough to estimate anything, whether its future performance of capability of a lot of things (Haynes, 2022). In these situations, you will examine the data for non-normal conditions and/or outliers and typically, run the assessment again (van de Merbel et al., 2014).

AIAG Method for Stability

This content is from the Automotive Industry Action Group which provides education and information to a wide range of people. Their process of using SPC and maintaining control is outline below, but originated from this source: (SPC) Statistical Process Control (AIAG, 2022). Learn more by selecting the link.

There are two phases in SPC control studies:

  • Identify and eliminate the special causes of variation in the process. This will stabilize the process and provide control..
  • Next, predict future data based on the control data. Once stabilized, the process can be used to determine capability.

Test Yourself

Review the each of the hot spots below on the histogram. Then, answer the review questions to test your knowledge.




Automotive Industry Action Group (2022). (SPC) Statistical process control. AIAG. Retrieved on August 8, 2022 from

Benchmark 6ix Sigma (2017). Process stability, process capability. Retrieved on August 8, 2022 from

Cordaro, C. (2013, September 16). Process stability [Video]. YouTube.

Frost, J. (2019). Using histograms to understand your data. Retrieved on August 8, 2022 from

IST/SEMATECH. (2012). e-Handbook of Statistical Methods. Retrieved on August 8, 2022 from

ISIXSIGMA (2022). Process stability.

SPC for Excel (2019, May 1). What do these histograms tell you? The answers [Video]. YouTube.

van de Merbel N, Savoie N, Yadav M, Ohtsu Y, White J, Riccio MF, Dong K, de Vries R, & Diancin J. 2014 Feb 19.Stability: recommendation for best practices and harmonization from the Global Bioanalysis Consortium Harmonization Team. AAPS J. 2014 May;16(3):392-9. doi: 10.1208/s12248-014-9573-z. EpubĀ  PMID: 24550081; PMCID: PMC4012051.


Icon for the Creative Commons Attribution 4.0 International License

SPC and Lean Manufacturing by Andrea Bearman and Roberta Gagnon is licensed under a Creative Commons Attribution 4.0 International License, except where otherwise noted.

Share This Book