Measurement System Analysis (MSA)

What is Measurement System Analysis?

Before asking whether the process is capable, first ask whether the measurements are capable.

Measurement System Analysis (MSA) is the process of evaluating how well a measurement system performs. Rather than evaluating the process itself, MSA evaluates the tools, equipment, methods, and people used to collect data to determine whether measurements are accurate, consistent, and suitable for decision-making.

Every measurement contains some degree of variation. The objective of MSA is to determine whether that variation is small enough that the data can be trusted when analyzing process performance or making improvement decisions.

A measurement system includes far more than the measuring instrument. It also includes the operator, measurement method, environment, calibration, software, fixtures, and even the part being measured. MSA examines all of these components to determine whether they contribute unacceptable measurement error.

Why Measurement System Analysis Matters

Lean Six Sigma relies on facts and data to understand process performance, identify root causes, and verify improvements. If the measurement system is unreliable, every analysis built upon that data becomes questionable. How do you ensure improvement efforts focus on real process variation rather than measurement error.

Imagine using a bathroom scale that displays a different weight every time you step on it. Even if your weight never changed, the scale would suggest otherwise. Likewise, an inaccurate measurement system may indicate process changes that never occurred—or hide real improvements that actually did.

Performing MSA helps organizations:

Isolate real variation
Build confidence in process data.
Reduce measurement variation.
Improve decision-making.
Avoid costly incorrect conclusions.
Guarantee data reliability
Increase confidence in statistical analysis.

Measurement System Analysis (MSA) ensures that the data you collect is trustworthy, accurate, and precise.

Measurement System Analysis (MSA) infographic showing how reliable measurement systems produce trustworthy data by evaluating accuracy, precision, measurement variation, and sources of error to support better Lean Six Sigma decisions.

Explore The Full Course

When to Use Measurement System Analysis

MSA should be performed whenever data will be used to make important business decisions, particularly during the Measure phase of the DMAIC methodology. Typical applications include:

Before collecting baseline process data.
Prior to Process Capability Studies.
Before Statistical Process Control (SPC).
Prior to Design of Experiments (DOE).
Before Hypothesis Testing.
When introducing new measuring equipment.
After significant equipment maintenance or calibration.
When multiple operators collect measurements.
Whenever unexpected data variation raises concerns.

How Measurement System Analysis Works

MSA systematically evaluates whether a measurement system is both accurate and repeatable. The evaluation typically examines questions such as:

Does the instrument consistently produce the same measurement?
Do different operators obtain similar results?
Does the measurement remain stable over time?
Is the instrument properly calibrated?
Is the instrument capable of detecting meaningful process differences?

Depending on the type of data being collected, different MSA techniques are used. Variable data are typically evaluated using Gauge Repeatability and Reproducibility (Gauge R&R), while attribute data often require Attribute Agreement Analysis.

The goal is not to eliminate all measurement error—an impossible task—but rather to ensure that measurement variation is small compared with the actual variation occurring within the process.

Key Concepts in Measurement System Analysis

Several important concepts help describe the quality of a measurement system.

Accuracy: How closely measurements reflect the true value.
Precision: The ability to obtain consistent measurements when repeating the same measurement.
Repeatability: Variation introduced when the same operator measures the same part multiple times using the same equipment.
Reproducibility: Variation resulting from differences between operators.
Bias: A consistent difference between measured values and the true value.
Linearity: Whether measurement accuracy remains consistent across the instrument's operating range.
Stability: Whether measurements remain consistent over time.
Resolution (Discrimination): The smallest change that a measuring device can reliably detect.
Calibration: Checking and adjusting a measuring device to ensure it provides accurate and reliable results

Common Pitfalls to Avoid

Organizations sometimes overlook the importance of validating their measurement systems before beginning improvement work. Common mistakes include:

Assuming calibrated equipment automatically produces reliable measurements.
Ignoring differences between operators.
Collecting process data before validating the measurement system.
Using instruments with insufficient resolution.
Confusing measurement variation with process variation.
Skipping MSA because measurements "appear reasonable."
Believing MSA applies only in manufacturing rather than service, healthcare, finance, or government.

Where Measurement System Analysis Fits in Lean Six Sigma

Measurement System Analysis is one of the foundational activities within the Measure phase of DMAIC.

Before analyzing process capability, identifying root causes, testing hypotheses, or optimizing process settings, practitioners must first establish confidence in the quality of the data being collected.

Without a capable measurement system, even sophisticated statistical analyses may produce misleading conclusions.

MSA therefore provides the foundation upon which reliable process analysis and evidence-based decision-making are built.

What is Measurement System Analysis in Simple Terms?

Measurement System Analysis (MSA) is the process of determining whether you can trust the data you collect. Before improving a process, MSA verifies that your measuring system is accurate, consistent, and reliable enough to support good decisions.