Dr. Joan Burtner

1
The Certified Quality Engineer Handbook 3rd ed.
Ch. 26 Measurement System Analysis

• Dr. Joan Burtner
• Certified Quality Engineer
• Associate Professor of
• Industrial Engineering and Industrial Management

2
Ch. 26 Measurement System Analysis

• Terms and Definitions
• Gage Repeatability and Reproducibility
• Variables vs. Attributes
• Gage RR Methods
• Tabular
• Analysis of Variance
• Control Charts

2
3
Terms and Definitions 1 (Glossary page 630)

• Gage Repeatability and Reproducibility (GRR)
  measures the capability of a gage to determine if
  it is suitable for use in its intended
  application.
• Repeatability represents the gage variability
  when it is used to measure the same unit with the
  same setup or operator.
• Reproducibility refers to the variability arising
  from different setups or operators.

3
4
Terms and Definitions 2 (Glossary page 638)

• Repeatability how close the measurements of an
  instrument are to each other if such measurements
  are repeated on a part under the same measuring
  conditions. (Glossary)
• Reproducibility a measure of the degree of
  agreement between two single test results made on
  the same object in two different, randomly
  selected measuring locations or laboratories.
  (Glossary)

4
5
Terms and Definitions - 3

• Accuracy the difference between the measurement
  taken and the actual value of the variable
• Accuracy a qualitative term that describes the
  closeness of alignment between an observed value
  and an accepted reference value
• Bias a quantitative term representing the
  systematic difference between measurements
  obtained and the true quantity of interest

5
6
Terms and Definitions - 4

• AIAG Automotive Industry Action Group
• Linearity measures how changes in the size of
  the part being measured will affect measurement
  system bias over the expected process range
  Example Does bias change significantly as part
  size increases?
• Stability a measure of how the measurement
  system performs over time.
• Precision the variation encountered when the
  same part is measured repeatedly using the same
  measurement system (under the same conditions)
  page 258

6