Can you trust your measuring stick? Before you collect data, a Measurement System AnalysisMeasurement System Analysis (MSA) is a check that confirms a measurement system is accurate and reliable before you trust the data it produces. It looks at the instrument, the method and the people who measure. Click term for full definition makes sure the numbers reflect the process, not the measuring. Watch the short video, then work with the toolkit PDF: it explains the method, shows a worked example and gives you a blank template to fill in.
Tool video
The short tool video will appear here.
Measurement System Analysis in short
- Describe the system. What is measured, with which tool, by whom?
- Choose the study. Measured data: Gauge R&R. Pass/fail or categories: Attribute Agreement.
- Prepare samples. Gauge R&R: 10 parts across the range. Attribute: 20 to 50 known good and bad items.
- Run blind trials. 2 to 5 appraisers measure every item 2 or 3 times without seeing earlier results.
- Judge and act. Compare with the criteria. If it fails, fix tool, training or procedure, then test again.
Key points
- Observed variation = process + measurement error.
- AccuracyThe difference between the observed average value of a measurement and the true value of the thing being measured. Click term for full definition: the right number. PrecisionHow much variation exists when the same item is measured multiple times. Click term for full definition: the same number.
- Gauge R&R for measured data, Attribute Agreement for categories.
- No trusted measurement, no data collection.