Measurement Systems Analysis allows us to make sure that the variation in our measurement is minimal compared to the variation in our process.
The Need for Accurate Data by DMAIC Phase
 During the measure phase not only do we have to collect data, we have to make sure that we are collecting the same data accurately and consistently.
 Creation of visual tools like Pareto Charts are only as good as the measured DATA.
 In the improve phase you will require precise and accurate data to perform Designs of Experiments and inform pilot plans.
 In the control phase we use measurements to produce data to perform statistical process control and prepare things like control charts to visualize if a process is in control or not.
 If our visual factory is based upon data, then that specific control will only be as good as the underlying data.
MEASUREMENT SYSTEM TERMINOLOGY
Let’s take a look at some measurement system terminology which would helpful in measurement system analysis.
Discrimination: Smallest detectable increment between two measured values not the same as Accuracy or repeatability. Whenever you are using a gage then there is a least count or minimum value that you can measure with this gauge.
Accuracy: It is a difference between the true average and observed average. (True average may be obtained by using a more precise measure tool). The moment that the average value is differ from the true average, then the system is not accurate. This is an indication of inaccurate system.
Stability: The difference in the average of at least 2 set of measurements with a gage over time. Let we measured an object at Time (T1) and then after time (T2) there average value are totally different.
Also see Gage Repeatability and Reproducability
Measurement is the key and essential in six sigma. Measurement System Analysis (MSA) is an experimental and mathematical method of determining how much the variation within the measurement process contributes to overall process variability. There are five parameters to investigate in an MSA;
 Bias
 Linearity
 Stability
 Repeatability
 Reproducibility
Measurement Error
In Six Sigma, we want to base as much of our decisions on reliable data as possible. Measurement System Analysis uses techniques to understand the variation within measuring equipment. For example the variation brought into the equipment by people and by the environment. There are some useful methods for an estimation of how much error being committed by the gage and how much error being committed by the individual. For an MSA you should know about several types of errors and how each can be introduced and avoided.
Measurement Error
Measurement Error is considered to be the difference between a value measured and the true value. It depends upon two things.
 What kind of instrument that you are using
 Who is the person using instrument
Therefore anytime you are using an instrument keep your mind open about some possibilities of measurement error being there.
How Much Measurement Error is Acceptable?
According to AIAG (2002), a general rule of thumb for measurement system acceptability is:
 Under 10 percent error is satisfactory.
 10 percent to 30 percent error suggests that the system is acceptable depending on the importance of application, cost of measurement device, cost of repair, and other factors.
 Over 30 percent error is considered unacceptable, and you should improve the measurement system.
Measurement Accuracy and Precision
The purpose of Measurement System Analysis is to qualify a measurement system for use by quantify its accuracy, precision and stability.
1Measurement are said to be accurate if their tendency is to center around the actual value of entity being measured. Measurement accuracy is attained when the measured value has little deviation from the actual value.
2Measurement are precise if they differ from one another by a small amount.
What would you say about the cause relating to each type of variation? Can we find their effect? This issue is addressed by MS analysis.
Measurement Variation
Remember that DMAIC is a tool for removing defects from our process – especially by limiting variation. That total observed variation comes in 2 flavors:
Total Variation = Process Variation + Measurement Variation
For example, let’s say you are measuring how many cups of M&Ms are in a production run. If you are measuring using a measuring cup that is not very accurate and your colleague is using a device that is accurate, you will have different measures. The accumulated variation between your two measuring cups is Measurement Variation.
Alternately, imagine that a call center has auditors that review the quality of each phone associate’s call. And the phone associates are graded on that quality; which impacts their paycheck. If every auditor graded to a different standard, there would be a lot of variation in that measurement technique, wouldn’t there?
Measurement Systems Analysis Fundamentals (from here)

Determine the number of appraisers, number of sample parts, and the number of repeat readings. Larger numbers of parts and repeat readings give results with a higher confidence level, but the numbers should be balanced against the time, cost, and disruption involved.

Use appraisers who normally perform the measurement and who are familiar with the equipment and procedures.

Make sure there is a set, documented measurement procedure that is followed by all appraisers.

Select the sample parts to represent the entire process spread. This is a critical point. If the process spread is not fully represented, the degree of measurement error may be overstated.

If applicable, mark the exact measurement location on each part to minimize the impact of withinpart variation (e.g. outofround).

Ensure that the measurement device has adequate discrimination/resolution, as discussed in the Requirements section.

Parts should be numbered, and the measurements should be taken in random order so that the appraisers do not know the number assigned to each part or any previous measurement value for that part. A third party should record the measurements, the appraiser, the trial number, and the number for each part on a table.
Measurement Systems Analysis Videos
Six Sigma Green Belt Certification Measurement System Analysis Questions:
Question: As we calibrate our Measurement System to assure accurate data we frequently encounter Bias which is the __________________ of a measured value from the ________________ value. (Taken from Iassc sample Green Belt exam.)
(A) Spread, Mean of the population
(B) Deviation, hoped for
(C) Deviation, true
(D) Spread, idea
Answer: (c) Deviation, true. This is a definition question. See MSA.
Six Sigma Black Belt Certification Measurement System Analysis Questions:
Question: In measurement system analysis, which of the following pairs of data measures is used to determine total variance? (Taken from ASQ sample Black Belt exam.)
(A) Process variance and reproducibility
(B) Noise system and repeatability
(C) Measurement variance and process variance
(D) System variance and bias
Answer: (c) Measurement variance and process variance. Remember, Total Variation = Process Variation + Measurement Variation. Reproducibility and repeatability are covered in a gage r & r.
Question: A measurement system analysis is designed to assess the statistical properties of:
(A) gage variation
(B) process performance
(C) process stability
(D) engineering tolerances
Answer: (A) Gage variation. A measurement system analysis is designed to assess the statistical properties of gage variation. Process performance and stability can be determined in other ways. Engineering tolerances are calculated by need.
vijay kumar says
yes very helpful
Six Sigma Study Guide says
Glad it helped, Vijay!