Opening the book…
After completing this chapter, you should be able to:
- Describe sources of variation in biotechnology processes and measurements.
- Distinguish common-cause variation from special-cause variation.
- Explain process stability and the limits of predicting future performance.
- Distinguish specification limits from control limits and interpret a result against both.
- Select an appropriate response to evidence of different sources of variation.
- Explain how unnecessary adjustments can increase variation in a stable process.
- Use process data to propose an improvement and evaluate whether it lasts.
Shewhart’s attention to process behavior and Deming’s warning against unsupported adjustments help explain how to respond to variation. The aim is to choose actions that fit the evidence while protecting the people who rely on biotechnology products and services.
A biotechnology technician checks bottles on a research-reagent filling line. The target volume is 10.00 mL. The first three results are 9.98, 10.03, and 10.01 mL. The technician wonders whether to adjust the filler after every measurement so that the next bottle lands exactly on target.
Later, a bottle measures 10.28 mL. It is still within the company’s approved fill-volume range, but it falls beyond the upper limit on the established individual-fill control chart. Should the technician ignore it because it passes the volume requirement, adjust a setting immediately, or follow the procedure for investigating a chart signal?
This hypothetical situation raises two different questions: Does the measured bottle meet its requirements, and is the process behaving as expected? Quality work requires both questions. In this chapter, you will learn how variation helps explain repeated results, when it calls for investigation, and why reacting to every small difference can make performance worse.
- 6.1: Why repeated process results differ
- This page discusses variation in biotechnology, highlighting its causes such as materials, methods, and measurement techniques, and its effect on decision-making. It emphasizes the importance of a reliable measurement system, distinguishing between accuracy (closeness to true value) and precision (consistency of results). The necessity of careful record-keeping to ensure accurate interpretation and avoid misclassification of data is also underscored.
- 6.2: Common-cause and special-cause variation
- This page explains the distinction between common-cause variation, which arises from normal process conditions leading to consistent patterns, and special-cause variation, which results from atypical influences. It emphasizes that the terms 'common' and 'special' don't reflect the impact significance. Proper identification of these variations relies on evidence and context, rather than frequency alone.
- 6.3: Process stability and predictable performance
- This page explains the concept of process stability, emphasizing consistent results and common-cause variation. Stability enhances predictive accuracy while allowing for future variability. It defines mean and spread, noting that identical means may exhibit different spreads. Control charts are introduced as monitoring tools, signaling when further investigation is needed.
- 6.4: Distinguishing specification limits from control limits
- This page outlines the distinctions between specification limits, control limits, and target values in product quality and process management. Specification limits define acceptable boundaries, while control limits analyze process behavior. The target value indicates the desired outcome, which can differ from the average. Understanding these terms is vital, as a conforming result may reflect process changes, and a stable process can produce out-of-spec values.
- 6.5: Responding appropriately to different sources of variation
- This page outlines the decision-making process for addressing material issues, focusing on immediate containment, correction, and cause assessment. It emphasizes thorough investigations, the involvement of relevant personnel, and the importance of accurate record-keeping. Ongoing evaluation in pharmaceutical manufacturing is highlighted, following FDA process verification guidelines.
- 6.6: A children’s medicine recall brings variation into focus
- This page details the FDA inspections linked to McNeil Consumer Healthcare's 2010 recall of infant and children's medicines due to product variability concerns. It highlights manufacturing control issues and the voluntary recall by Johnson & Johnson.
- 6.7: Risks of adjusting a stable process unnecessarily
- This page discusses the dangers of tampering or overadjustment in processes, which can lead to increased instability. It references Deming's funnel experiment as an illustration of how unnecessary adjustments can exacerbate issues. The page emphasizes the importance of evidence-based adjustments and established feedback controls to minimize errors.
- 6.8: Using variation knowledge to guide improvement
- This page discusses how variation knowledge helps teams select improvement questions by focusing on averages, spread, and measurement. It highlights the importance of establishing an improvement baseline for performance comparison and using a learning cycle for testing predictions and assessing stability after changes. Effectiveness verification ensures that actions meet objectives while considering consequences.
- 6.9: Chapter summary
- This page covers variations in processes, distinguishing between common-cause and special-cause variations and their impact on measurements. It underscores the importance of stability in predicting outcomes and maintaining control and specification limits. Actions related to variations should preserve evidence and minimize unnecessary changes.
This page titled 6: Variation and Process Performance was last modified on Thu, 05 Nov 2026 08:54:48 GMT and is shared under a CC BY-SA 4.0 license and was authored, remixed, and/or curated by .
The book could not be loaded just now.