Tabtrainer® Series - Nested Gage R&R with Minitab®

Master nested Gage R&R in Minitab for destructive tests – meet AIAG standards and improve reproducibility with real data

Created byProf. Dr. Murat Mola

Last updated 4/2026

English

What you'll learn

Understand nested Gage R&R studies and know when to apply them in destructive testing environments for accurate and reliable measurement evaluation.
Design and conduct valid nested Gage R&R studies with structured sampling plans based on AIAG standards and the 40-4 rule for batch testing.
Perform complete nested Gage R&R analyses in Minitab and interpret statistical outputs including p-values, variance components, and nested GR&R values.
Distinguish between repeatability and reproducibility and identify the dominant source of variation in a nested measurement system.
Evaluate measurement systems using AIAG acceptance criteria based on variance, standard deviation, and number of distinct categories (ndc).
Use R charts, Xbar charts, and boxplots to visualize operator influence and detect systematic variation or inconsistencies in test results.
Interpret scatterplots grouped by sample positions to detect intra-batch inconsistencies and evaluate the homogeneity of mechanical properties.
Apply statistical logic to reject or retain hypotheses about operator and batch influence using defined significance levels (e.g. p < 0.05).
Implement targeted improvement actions to correct measurement system issues and validate improvements through follow-up Gage R&R studies.
Achieve a validated and AIAG-compliant measurement system suitable for ongoing process optimization and robust quality improvement.

Course content

2 sections • 11 lectures • 1h 1m total length

Explore the curriculum2:16
Explore the curriculum
MSA Nested: Gage R&R with Destructive Testing3:44
In this training unit, participants will explore how to perform a nested Gage R&R study, which is required when each operator cannot measure the same parts, typically due to destructive testing procedures.
Using a realistic case from the Smartboard Company’s axle test bench, learners will examine the fatigue strength of skateboard axles tested under dynamically increasing load conditions until breakage. Because the test is destructive, each axle can only be measured once, making a traditional Gage R&R study unsuitable.
The lesson introduces the nested design, highlighting:
The importance of homogeneous production batches.
Random assignment of batches to different operators (Blackbird, Thrush, Finch).
The two key conditions for a valid nested study.
Differences between crossed and nested Gage R&R designs.
How to ensure repeatability and reproducibility even with destructive tests.
Participants will learn when and how to apply the nested Gage R&R method to gain reliable insights into measurement system variation under real-world constraints.
MSA Nested: Sampling Strategy and Data Structure4:28
In this training unit, learners explore how to design and structure a nested Gage R&R study when dealing with destructive testing methods, using a real-world example from Smartboard Company.
Key Learning Topics:
Introduction to the 40-4 Rule for nested Gage R&R:
A minimum of 40 total test parts.
At least 4 parts drawn per production batch.
Sampling must be systematic: draw one part from each quarter of the batch (positions A–D).
Implementation in the Practical Scenario:
12 randomly selected production batches are assigned to 3 operators:
Blackbird: batches 1–4
Thrush: batches 5–8
Finch: batches 9–12
Each operator samples 4 axles from each batch (one from each quarter), totaling 16 samples per operator.
Final sample size: 3 × 16 = 48 destructively tested parts.
Purpose: Ensure homogeneity within production batches and validate the measurement system's reproducibility and repeatability despite destructive testing.
Students will learn how to analyze, interpret, and structure such data, preparing them to conduct and assess nested Gage R&R studies in professional manufacturing settings.
MSA Nested: Statistical Analysis and Interpretation3:45
In this lesson, learners are guided step-by-step through the statistical evaluation of a nested Gage R&R study, applied to destructive fatigue testing of skateboard axles at Smartboard Company.
Topics Covered:
Performing the Analysis in Minitab:
Navigate to: Statistics → Quality Tools → Gage Study → Gage R&R Study (Nested).
Input variables:
C1: Batch number
C2: Operator
C5: Fatigue strength (measurement data)
Run the nested analysis and explore the results.
Interpreting p-values:
Operator Effect:
Null hypothesis: Operator has no significant effect on measurements.
p = 0.00 → reject null hypothesis → Operators do significantly affect results.
Batch Effect:
Null hypothesis: No significant batch-to-batch differences.
p = 0.00 → reject null hypothesis → Batch differences are significant, which is desirable, as the goal is to detect these variations.
Special considerations for nested studies:
In nested designs, batches are nested within operators due to destructive testing — i.e., no repeat testing of the same part by multiple operators is possible.
Interpretation must consider that batch variation is tied to operator assignment (indicated in the output as “Batch (Operator)”).
Random batch assignment ensures no bias (e.g., one operator getting only “easy” or “difficult” batches).
Learning Outcome:
Participants learn how to:
Correctly apply and interpret a nested Gage R&R study.
Understand how operator and batch effects impact measurement variation.
Recognize why nested designs are necessary in destructive testing environments.
Evaluate measurement system capability even when parts cannot be re-tested.
MSA Nested: Variance Components and Evaluation of Measurement System6:12
MSA Nested: AIAG Acceptance Criteria and Conversions4:31
In this final nested Gage R&R unit, participants learn how to evaluate the quality of a measurement system based on both standard deviation (σ) and variance (σ²) according to AIAG guidelines.
Key Topics Covered:
AIAG Standard Rules (based on standard deviation σ):
< 10%: Acceptable measurement system.
10%–30%: Conditionally acceptable.
≥ 30%: Not acceptable.
Conversion to Variance (σ²) for Comparison:
Because variance is the square of the standard deviation, the thresholds change:
10% (σ) → 0.1² = 0.01 → 1% (σ²)
30% (σ) → 0.3² = 0.09 → 9% (σ²)
Learning Outcome:
By completing this lesson, learners will:
Master the AIAG acceptance criteria for measurement systems.
Understand how to translate and interpret Gage R&R values in both σ and σ² formats.
Identify when and why a measurement system fails.
Recognize the critical importance of operator consistency in destructive testing scenarios.
MSA Nested: Number of Distinct Categories and Measurement Resolution3:48
This lesson focuses on the resolution power of the measurement system, using the Number of Distinct Categories (ndc) as a key metric based on AIAG standards:

Key Topics Covered:
What is ndc?
ndc = Number of Distinct Categories
Indicates how many different part categories the measurement system can reliably distinguish.
Calculated as:

AIAG Classification of ndc:
ndc = 1 → Unacceptable, cannot distinguish process variation.
ndc = 2–4 → Still unacceptable, only useful for go/no-go decisions.
ndc ≥ 5 → Acceptable, system can be used for process optimization.
Result: The measurement system is unacceptable and has very low resolution.

Consequences of ndc = 1:
The system can only detect if a part is within or outside specification.
It is not suitable for evaluating trends, shifts, or process improvements.

Learning Outcome:
By the end of this session, learners will:
Understand the importance of measurement system resolution.
Know how to calculate ndc and interpret its meaning.
Recognize when a measurement system is fit for process control or optimization.
Be prepared to plan corrective actions to improve the system and re-run a valid Gage R&R study.

MSA Nested: Analysis Report & Deriving Improvements9:23
In this continuation of the nested Gage R&R training, learners perform an in-depth analysis of the measurement system report and derive targeted improvement actions based on graphical and statistical outputs. The focus is on identifying weaknesses in reproducibility and validating assumptions about batch homogeneity.
Key Learning Topics:
Graphical Report Overview:
Interpretation of bar charts:
Blue bars represent % contribution (variance-based)
Red bars represent % study variance (standard deviation-based)
Visual cue: Reproducibility dominates variation → main system weakness
Control Charts Analysis:
R Chart (Range Chart): Measures variation within batches → all operators show good repeatability
Xbar Chart (Mean Chart): Compares mean values between operators
Blackbird consistently measures lower fatigue strengths
Thrush and Finch show increasing trends → suspicious pattern
Key Observations:
Blackbird shows the best repeatability but very low mean values
Thrush and Finch display systematic increases in mean values
This questions the random assignment of batches and homogeneity within batches
Recommendations for Improvement:
Verify homogeneity of mechanical properties via renewed process analysis
Reduce operator variation through standardized test instructions and an operator training program
Scatterplot & Individual Value Plot:
Used to validate batch assignment and visualize data cloud structure
Each cloud contains 4 points (Samples A–D from one batch)
Scatterplot helps reinforce suspicion of non-random sample distribution
Learning Outcomes:
After completing this lesson, learners will:
Skillfully interpret Gage R&R graphical outputs (R-chart, Xbar chart, variance plots)
Differentiate between repeatability and reproducibility
Identify violations in experimental assumptions (e.g., non-random batch assignment)
Derive actionable improvement measures for measurement system validation
Utilize scatterplots and control charts to detect systemic issues
MSA Nested: Scatterplot Evaluation, Error Detection & Improvement Actions7:32
In this lesson, learners take the next step in the nested Gage R&R analysis by using scatterplots, boxplots, and a new dataset to reveal systematic errors, verify batch homogeneity, and evaluate the impact of corrective actions.
Key Topics Covered:
Creating a Scatterplot with Grouping:
Graphs → Scatterplot → With Groups
Y-variable: Fatigue strength (C5)
X-variable: Batches (C1)
Grouping variable: Sample positions A–D (C4)
The grouped scatterplot allows for visual evaluation of intra-batch variation by showing which sample (A–D) each point represents.
Insights from the Scatterplot:
For operators Thrush and Finch, fatigue strength increases from sample A to D → indicates intra-batch inhomogeneity.
Violates the homogeneity assumption, which is crucial for the validity of a nested Gage R&R study.
Reinforcement of the 40-4 Rule:
Sampling must occur consistently from the same batch positions to validate homogeneity.
The scatterplot confirms systematic trends across positions A–D.
Boxplot "Fatigue Strengths by Tester":
Used to assess operator bias.
Operator Blackbird shows significantly lower values → indicates a systematic issue, not random variation.
Three Major Improvement Measures Identified:
Operator Error (Blackbird):
Set an incorrect oscillation frequency on the test bench → led to premature failures and lower measured fatigue strength.
Lack of Batch Homogeneity:
A new process capability analysis revealed that production batches are not homogeneous.
A process optimization was initiated to stabilize and improve batch quality.
Faulty Random Assignment of Batches:
Batches were not randomly assigned as required.
Two-person verification introduced to enforce correct random assignment and sampling location accuracy.
Learning Outcomes:
By completing this lesson, learners will:
Use scatterplots to detect systematic measurement and process issues.
Evaluate operator performance with boxplots.
Understand the consequences of violating core assumptions in nested designs.
Identify and implement corrective actions to improve reproducibility and process quality.
Prepare and validate a second Gage R&R study with corrected methods.
MSA Nested: Before-and-After Analysis: Validating Improvement Measures9:48
In this final evaluation session, learners perform a full before-and-after comparison of the Gage R&R nested study. The focus is on validating whether the implemented improvement measures led to a statistically acceptable measurement system in line with AIAG standards.
Key Learning Topics:
Restarting the Nested Gage R&R Study
P-Value Interpretation: Operator effect vs Batch effect:
Variance and Standard Deviation Evaluation:
Variance-based Gage R&R (%GR&R)
Standard Deviation-based GR&R:
ndc Interpretation (Number of Distinct Categories)
Graphical Results – Before-and-After Comparison
Bar Charts (Variance & Std. Dev.)
Control Charts (R and Xbar)
Scatterplots with Groups
Boxplots (Fatigue Strength by Tester)
Final Outcome:
The improved measurement system:
Meets AIAG criteria (variance, std. dev., ndc)
Has no operator bias
Reflects random batch assignment
Can now be safely used for process optimization
The training concludes with confirmation that process stability, sampling integrity, and operator training were effective corrective actions.
Learning Outcome:
After completing this lesson, learners will:
Compare and validate measurement system performance before and after improvements
Apply hypothesis testing to real-world quality metrics
Use Minitab outputs (p-values, %GR&R, ndc, control charts, scatterplots, boxplots) to support improvement validation
Understand how to turn an invalid system into a valid, AIAG-compliant measurement system
Summary of the most important findings5:43
Consolidated Review of Essential Outcomes from the Gage R&R Analysis

Requirements

No Specific Prior Knowledge Needed: all topics are explained in a practical step-by-step manner.

Description

Welcome to the Tabtrainer® Masterclass Series – your trusted source for advanced quality engineering and measurement system expertise.

In this course, you will master Nested Gage R&R Studies using Minitab, designed specifically for destructive testing environments where each part can be measured only once. Based on a real-world case from the Smartboard Company, this hands-on training guides you through the entire lifecycle of a nested study – from design and data collection to AIAG-compliant analysis and process improvement.

Led by Prof. Dr. Murat Mola, TÜV-certified instructor and founder of Tabtrainer®, this course equips you with both the theoretical background and the practical tools to evaluate and optimize measurement systems when crossed designs are not feasible.

Course Description

This advanced training course provides a step-by-step, hands-on introduction to nested Gage R&R studies, specifically tailored for destructive testing environments where each part can only be measured once. Using a practical business case from the Smartboard Company, participants are guided through the full analysis cycle—from study design to final evaluation of system validity.

Across multiple modules, learners will explore how to design a statistically sound measurement system analysis when crossed designs are not applicable, and how to validate the system using AIAG standards.

The course combines statistical theory, software-based execution in Minitab, and real-world interpretation of outputs including p-values, variance components, number of distinct categories, and visual control charts.

Participants will learn how to detect measurement system weaknesses, especially those related to reproducibility, and implement corrective actions through operator training, process capability analysis, and sampling strategy improvements. A complete before-and-after study comparison concludes the course and confirms the success of the applied measures.

By the end of this course, participants will be able to design, execute, interpret, and optimize nested Gage R&R studies that meet international quality standards and support long-term process optimization.

What You Will Learn:

When and why to apply a nested Gage R&R design.
How to handle destructive testing scenarios where part retesting is not possible.
The importance of homogeneous production batches and correct sampling (40-4 rule).
Step-by-step setup and execution of a nested study in Minitab.
How to interpret control charts (R chart, Xbar chart) and scatterplots.
How to apply AIAG acceptance criteria using variance, standard deviation, and ndc.
How to detect and reduce operator bias and machine influence.
How to validate measurement system improvements using before-and-after comparison.
The link between measurement resolution and process optimization capability.
How to build a robust and audit-ready Gage R&R study for industrial environments.

Who this course is for:

Quality Assurance Professionals: Those responsible for monitoring production processes and ensuring product quality will gain practical tools for defect analysis.
Production Managers: Managers overseeing manufacturing operations will benefit from learning how to identify and address quality issues effectively.
Six Sigma Practitioners: Professionals looking to enhance their expertise in statistical tools for process optimization and decision-making.
Engineers and Analysts: Individuals in manufacturing or technical roles seeking to apply statistical methods to real-world challenges in production.
Business Decision-Makers: Executives and leaders aiming to balance quality, cost, and efficiency in production through data-driven insights and strategies.

Tabtrainer® Series - Nested Gage R&R with Minitab®

What you'll learn

Explore related topics

Course content

MSA Gage R&R Study - nested, Part 17 lectures • 29min

MSA Gage R&R Study - nested, Part 24 lectures • 32min

Requirements

Description

Who this course is for: