1.4
Nominal Level of Measurement
The way a set of data is measured is called its level of measurement. Correct statistical procedures depend on a researcher being familiar with levels…
In statistics, the context of the data is critical to decide the right statistical method. For instance, taking the average of all the numbers to get a common phone number for the class is meaningless.
For the purpose of analysis, data are classified into four levels of measurement—nominal, ordinal, interval, and ratio.
The data that cannot be measured or ordered but can be grouped into categories fall under the nominal level of measurement. For example, one cannot measure or place hairstyles in a particular order but can group them into different categories.
Although these groups can be numbered for the sake of convenience, the difference between these numbers or the average of these numbers is meaningless.
Survey responses such as like-dislike, yes-no, or political party affiliations also fall under the nominal level of measurement.
View the full transcript and gain access to JoVE Core videos
Q1: What is the nominal level of measurement in statistics?
The nominal level of measurement classifies data into categories that cannot be measured or ordered. Examples include hairstyles, survey responses like yes-no or like-dislike, and political party affiliations. Although categories can be numbered for convenience, the numbers themselves are meaningless and cannot be averaged.
Q2: Why can't you calculate the average of nominal level data?
Nominal data consists of categories without inherent numerical value or order. Calculating an average requires meaningful numerical relationships, which nominal categories lack. For example, averaging phone number categories or restaurant types produces meaningless results because the numbers assigned to categories are arbitrary labels, not true measurements.
Q3: What are examples of nominal level data?
Nominal level data includes categories, colors, names, labels, favorite foods, and yes-or-no responses. Restaurant types grouped by diet—vegetarian, non-vegetarian, or vegan—also represent nominal data. These examples share the characteristic that they can be grouped into distinct categories but cannot be measured or ranked in order.
Q4: How does nominal data differ from other levels of measurement?
Data are classified into four levels of measurement: nominal, ordinal, interval, and ratio. Nominal data can only be grouped into categories, while ordinal data can be ordered, and interval and ratio data involve numerical measurements. Nominal is the most basic level because it lacks both order and measurable differences between categories.
Q5: Is nominal level data qualitative or quantitative?
Nominal level data is qualitative, meaning it describes qualities or characteristics rather than quantities. Categories, colors, names, and labels are descriptive in nature and cannot be expressed as numerical measurements. This qualitative nature is why mathematical operations like averaging are inappropriate for nominal data.
Q6: Why is understanding levels of measurement important for statistical analysis?
Correct statistical procedures depend on researchers understanding levels of measurement because not every statistical operation can be used with every dataset. Using inappropriate methods—like averaging nominal categories—produces meaningless results. Identifying whether data is nominal, ordinal, interval, or ratio ensures researchers apply valid analytical techniques.
Q7: Can nominal categories be numbered or coded?
Yes, nominal categories can be numbered for convenience during data entry or analysis. However, these numbers are arbitrary labels without mathematical meaning. The difference between assigned numbers or their average is meaningless because the numbers represent category labels, not actual measurements or quantities.