Insights
Notes from the
production floor
Practical articles on the statistics behind product and process data — written for the engineers, quality professionals, and reviewers who have to defend the numbers.
- Measurement Systems
- Process Capability
- Risk Management
- Sample Size
Putting Numbers on Risk: Statistics in ISO 14971
ISO 14971 asks for the probability of harm. Here is where process data can supply that number, why zero failures in 30 units proves far less than teams assume, and what occurrence rating your evidence actually supports.
Read the articleCpk vs. Ppk: Which Capability Index Should You Report?
Cpk and Ppk answer different questions about your process. What separates short-term from long-term variation, which index belongs in your validation report, and how much data it takes before the number means anything.
How Many Samples? Sample Size Justification for Design Verification
How to determine sample size for variables and attribute testing — the tolerance-interval rule that ties n to process capability, why the minimum n is not a plan, and how risk sets the claim.
Gage R&R: How to Interpret %GRR, ndc, and %Tolerance
A Gage R&R study returns several percentages that can disagree. Here is what %Study Variation, %Tolerance, and number of distinct categories each mean, and which to judge your measurement system against.
Insights by email
New articles, when they’re published
Practical statistics for medical device and pharma manufacturing — process validation, capability, MSA, sampling. No more than one email per article, and nothing else.
Start a conversation
Have a question these articles don’t answer?
Most of what we write about started as a client question. Bring yours — we’ll tell you what the data can support.