MSA- Measurement System Analysis 

MSA is defined as an experimental and mathematical method of
determining the amount of variation that exists within a measurement process.
MSA is used to certify the measurement system for use by evaluating the
system’s accuracy, precision and stability.

Objective of MSA:-

  1. To quantify the variation in measurement system.
  2. To ensure stability of measurement system.
  3. To minimize measurement system variation within
    total process variation.

Statistical Properties of Measurement System (MS):-

  1. Adequate discrimination (Sensitivity)
    :- Least count of instrument should be 1/10
    th of process variation
    (Process variation could be specification limit)
  2. MS variation is due to common causes, not
    because of special causes.
  3. Measurement error should be small compared to
    tolerance spread/process variability.

Measurement system error:-

  1. Location error [Accuracy, Bias, Stability,
  2. Width Error [Precision, Repeatability,
    Reproducibility, GRR]

Effect of MS error on measurement decision:-

  1. Calling OK part NG
  2. Calling NG part OK
  3. Calling common cause as special cause
  4. Calling special cause as common cause

Understanding MS errors:-

BIAS: – Difference between observed value and
reference value on same characteristics and same part.

Precision: – It is standard deviation of MS,
smaller the spread, better is precision. It is further divided into 2 parts.

  1. Repeatability [Within
    the system variation
    ]-Show by R chart (It is EV)
  2. Reproducibility [Between
    the system variation
    ]- Show by average (X-bar) chart. (It is AV)
  3. GRR [Gage repeatability & reproducibility] –
    σ²(GRR)= σ²(reproducibility) + σ²(repeatability) 

MSA Acceptance criteria:-

  1. %R&R should be less than 10%. If more than
    10 and less than 30% instrument can be accepted under some condition. But if
    %R&R is more than 30% than we have to reject the instrument.
  2. When repeatability of measurement is more than reproducibility
    then maintenance/Replacement of gauge is required.
  3. When
    reproducibility is more than repeatability then training to operator is

What is ndc in MSA?

Ndc= Number of distinct categories (It should be more than
5). Calculated only in Variable MSA. In attribute MSA we calculate Kappa.

What are variation in MSA?

TV (Total Variation),

AV-Appraisal variation,

PV- Part variation,

EV- Equipment variation.

What is formula for R&R in MSA?

R&R= Sqr-root((EV²
+ AV²)

Thank You for reading and visiting on the blog. Write comment for suggestion. 

You may like these articles:-

Article related to SPC

Self training program for IATF-16949

Vendor assessment System audit

If you want to write article on this website, drop a mail on