Nominal data sorts things into named categories with no order and no math. Color is nominal data. Blood type is nominal data. Department name is nominal data. You cannot rank nominal categories, and you cannot add or average them. A defect type of “scratch” is not more or less than a defect type of “dent.”
Nominal data differs from ordinal data, which has a real order, like small, medium, and large. In Six Sigma, teams use nominal data to sort defects, causes, and process types into groups. They then count how often each group appears, using tools like a chi-square test or a Pareto chart, instead of averaging the categories themselves.
Quick-Reference Table: The Four Data Scales
| Scale | Has Order? | Has Equal Spacing? | True Zero? | Example |
| Nominal | No | No | No | Blood type, defect category |
| Ordinal | Yes | No | No | Satisfaction rating, defect severity |
| Interval | Yes | Yes | No | Temperature in Celsius |
| Ratio | Yes | Yes | Yes | Weight, time, defect count |
Table of contents
Key Takeaways
- Nominal data names categories. It does not rank them and does not measure a distance between them.
- You cannot do math on nominal data. Adding, averaging, or subtracting category labels produces a meaningless result.
- Nominal data is one of four measurement scales. The other three are ordinal, interval, and ratio, and each allows different math.
- The most common mistake is confusing nominal with ordinal. Order is the one feature that separates them.
- Six Sigma teams use nominal data to sort defects and causes. They then count frequencies instead of averaging the categories.
- A chi-square test is the standard tool for nominal data. It checks whether category counts differ more than random chance would explain.
What Is Nominal Data?
Nominal data is information that sorts items into named groups with no natural order. The word “nominal” comes from the Latin word for “name.” That root is the easiest way to remember it.
A color is nominal data. Red is not greater than blue. A department name is nominal data. Sales is not greater than Marketing. Nominal data only answers one question: which group does this item belong to?
Public, Onsite, Virtual, and Online Six Sigma Certification Training!
- We are accredited by the IASSC.
- Live Public Training at 52 Sites.
- Live Virtual Training.
- Onsite Training (at your organization).
- Interactive Online (self-paced) training,
Common Examples of Nominal Data
Nominal data shows up constantly in business and quality work.
- Gender (male, female, other)
- Marital status (single, married, divorced)
- Eye color (brown, blue, green)
- Blood type (A, B, AB, O)
- Defect type (scratch, dent, misalignment)
- Department (Sales, Engineering, Finance)
- Brand preference (Brand A, Brand B, Brand C)
Each example sorts items into named buckets. None of the buckets outrank each other.
Also Read: Quantitative Data: Definition, Types, and Six Sigma Use
Nominal Data vs. Ordinal Data: The Key Difference
Order is the single feature that separates nominal data from ordinal data.
Nominal data has no order. Blue is not higher or lower than green. Ordinal data has a real order, even if the gaps between levels are not equal. Small, medium, and large have a clear order, even though the size difference between them may not be even.
| Feature | Nominal Data | Ordinal Data |
| Order | None | Yes |
| Example | Eye color | Shirt size |
| Can you rank it? | No | Yes |
| Can you measure the gap between values? | No | No |
A satisfaction survey shows this difference clearly. “Which product did you buy?” produces nominal data. “How satisfied were you, from very unsatisfied to very satisfied?” produces ordinal data, because the answers have a clear order.
Nominal Data vs. Interval and Ratio Data
Interval and ratio data both use numbers with real mathematical meaning. Nominal data does not.
Interval data has equal spacing between values but no true zero. Temperature in Celsius is interval data. Zero degrees does not mean “no temperature.”
Ratio data has equal spacing and a true zero. Weight is ratio data. Zero pounds means no weight at all.
Nominal data has neither feature. Even if you assign numbers to nominal categories, like coding “male” as 1 and “female” as 2, those numbers still carry no mathematical meaning. You cannot average them, and a code of 2 is not “twice as much” as a code of 1.
Why This Matters?
Many datasets store nominal data as numbers for convenience. Zip codes are nominal data, even though they look numeric. Employee ID numbers are nominal data. A customer type code of “3” is nominal data.
This creates a common and costly mistake. Someone runs an average on a numeric-looking column without checking whether the numbers are actually nominal codes. The average of a set of zip codes is meaningless. The average of a set of employee ID numbers is meaningless. A number’s appearance does not decide its data type. Its actual meaning does.
How Six Sigma Teams Use Nominal Data?
Nominal data plays a specific role inside a Six Sigma project, most often during the Measure and Analyze steps of DMAIC.
Sorting defects by type. A team logs each defect as “scratch,” “dent,” or “misalignment.” This is nominal data. The team then counts how often each type occurs.
Sorting causes by category. A fishbone diagram often sorts root causes into nominal categories like “Method,” “Machine,” “Material,” and “Man.”
Tracking pass or fail results. A simple “pass” or “fail” outcome is nominal data with only two categories, sometimes called binary or dichotomous data.
Building a Pareto chart. A Pareto chart ranks nominal categories, like defect types, by how often each one occurs, which helps a team find the few categories driving most of the problem.
Also Read: Discrete Data: Definition, Examples, and How Six Sigma Teams Use It
Statistical Tools That Work with Nominal Data
Because nominal data cannot be averaged, it needs its own set of statistical tools.
| Tool | What It Does |
| Frequency count | Counts how many times each category occurs |
| Mode | Identifies the most common category |
| Contingency table | Cross-tabulates two nominal variables to look for a relationship |
| Chi-square test | Tests whether the difference in category counts is statistically significant |
| Pareto chart | Ranks nominal categories by frequency to find the biggest contributors |
| p-chart or np-chart | Tracks the proportion or count of defective items over time |
The mode, not the mean, is the only measure of central tendency that makes sense for nominal data. You can say “scratch is the most common defect.” You cannot say “the average defect type is 2.3.”
A Practical Example: Analyzing Defect Data
A manufacturing team logs 200 defects over a month. Each defect gets one of four nominal labels: scratch, dent, discoloration, or misalignment.
| Defect Type | Count |
| Scratch | 92 |
| Dent | 54 |
| Discoloration | 38 |
| Misalignment | 16 |
The team cannot average these categories into a single number. The team can, however, build a Pareto chart, showing that scratches and dents together make up 73% of all defects. That insight points the team toward the two categories worth investigating first.
A chi-square test could also confirm whether this distribution differs meaningfully from what the team expected before the data was collected, such as an assumption that all four defect types occur equally often.
Common Mistakes When Working with Nominal Data
Averaging category codes. Assigning numbers to categories for storage does not make those numbers mathematically meaningful.
Confusing nominal with ordinal. A defect “severity” scale of low, medium, and high is ordinal, not nominal, because it has a real order. Mislabeling this as nominal data can lead a team to skip tools, like rank-based tests, that ordinal data actually supports.
Using the wrong chart type. A line chart implies a trend over an ordered scale, which does not fit nominal categories. A bar chart or Pareto chart is the correct choice.
Ignoring category imbalance. A chi-square test loses accuracy when one category has very few observations. A team should check category sizes before running this test.
Why Getting This Right Matters for Data Analysis?
Choosing the correct data type decides which statistical tests and charts are valid. Applying an interval or ratio-scale tool, like a mean or a t-test, to nominal data produces a number that looks precise but means nothing. A Green Belt or Black Belt who misclassifies data early in a project can carry that mistake through the entire Measure and Analyze phase without realizing it.
This is why measurement scale classification is one of the first topics covered in a Six Sigma Green Belt curriculum. Getting the data type right is the foundation every later analysis step depends on.
Frequently Asked Questions on Nominal Data
What is nominal data in simple terms?
Nominal data is information that sorts items into named categories with no order, like color, gender, or defect type. You can count how often each category appears, but you cannot rank the categories or average them.
What is an example of nominal data?
Blood type is a common example. The categories A, B, AB, and O have no natural order and cannot be ranked or averaged, which makes blood type a clear case of nominal data.
What is the difference between nominal and ordinal data?
Nominal data has no order, like eye color. Ordinal data has a real order, like small, medium, and large, even though the size difference between levels may not be equal. Order is the key feature that separates the two.
Can you calculate an average for nominal data?
No. Nominal data has no mathematical meaning behind its categories, so an average is meaningless. The correct measure of central tendency for nominal data is the mode, which identifies the most frequent category.
How is nominal data used in Six Sigma?
Six Sigma teams use nominal data to sort defects, causes, and process outcomes into categories during the Measure and Analyze steps of DMAIC. Teams then count frequencies and use tools like a Pareto chart or a chi-square test to find patterns.
What statistical test works with nominal data?
The chi-square test is the standard tool for nominal data. It checks whether the observed counts across categories differ from what random chance would predict.
Is a zip code nominal or numeric data?
A zip code is nominal data, even though it looks like a number. The digits in a zip code do not represent a quantity or an order, so averaging or ranking zip codes produces a meaningless result.
Final Words
Nominal data answers one question and one question only: which named category does this item belong to? It has no order, no equal spacing, and no meaningful math behind it, which is exactly what separates it from ordinal, interval, and ratio data. The most common analysis mistake happens when a team treats a numeric-looking nominal code, like a zip code or category number, as if it carried real mathematical value.
Getting this distinction right early in a Six Sigma project decides which charts and statistical tests will actually produce a valid answer later on.
Build Your Statistical Foundation with SSDSI
Understanding data types correctly is the foundation of every Six Sigma analysis, from a simple Pareto chart to advanced hypothesis testing.
SSDSI delivers IASSC-accredited Yellow Belt, Green Belt, and Black Belt training that covers nominal, ordinal, interval, and ratio data in depth, through onsite, live virtual, public, and self-paced formats. SSDSI has certified 5,322+ professionals across 600+ organizations in 52 cities, backed by a 5-star Google review rating. If you want to build this statistical foundation properly, a conversation about the right certification path is a solid next step.
About Six Sigma Development Solutions, Inc.
Six Sigma Development Solutions, Inc. offers onsite, public, and virtual Lean Six Sigma certification training. We are an Accredited Training Organization by the IASSC (International Association of Six Sigma Certification). We offer Lean Six Sigma Green Belt, Black Belt, and Yellow Belt, as well as LEAN certifications.
Book a Call and Let us know how we can help meet your training needs.
