Ordinal data refers to non-numerical data that has an inherent order or ranking. It is a sub-type of categorical data, and can include categories like clothing sizes and school grades (Babbie, Halley & Zaino, 2007; De Vaus, 2001).
If you’re writing an essay or methodology chapter on ordinal data, you may consider using a scholarly definition. Here are some good ones I found:
- “Ordinal data is a type of categorical data where the categories have a natural order or ranking. The categories can be arranged in a meaningful sequence, such as from low to high or from least to most.” (Dhingra, 2023)
- “Ordinal data is a discrete variable that has a relative order based on its position on a scale. Categorical variables that judge size (small, medium, large) are ordinal data.” (Albers, 2017)
Below are some prominent examples.
Ordinal Data Examples
1. Educational Levels
The hierarchy of educational attainment can be logically ordered. We could rank categories such as “elementary school,” “high school,” “bachelor’s degree,” and “postgraduate degree.” The order indicates increasing levels of education, but the differences between adjacent levels are not necessarily consistent or quantifiable.
2. Customer Satisfaction Ratings
Customer satisfaction data often comes from surveys where customers rate products or services on scales like “very dissatisfied,” “dissatisfied,” “neutral,” “satisfied,” and “very satisfied” (a variation of the Likert scale). The categories have a clear order from negative to positive, but the exact differences between categories (e.g., between “dissatisfied” and “neutral”) are not precisely defined.
3. Socioeconomic Status Tiers
SES refers to different classes or tiers within a society based on income, education, occupation, and other factors. Examples might include “low,” “middle,” and “high” socioeconomic status. The categories indicate relative standings within society, but the gaps between the tiers might not have a uniform measure.
4. Military Ranks
Military organizations around the world have structured hierarchies based on ranks. These can range from “private” to “corporal,” “sergeant,” and up to “general” or “admiral.” Each rank signifies a different level of authority and responsibility, but the exact difference in authority between two consecutive ranks is not always quantifiable.
5. Pain Intensity Scale
In medical settings, patients are often asked to rate their pain on a scale, such as “no pain,” “mild pain,” “moderate pain,” and “severe pain.” While these categories have a clear progression from least to most intense, the subjective experience of pain can vary, making the differences between categories not strictly uniform.
6. Movie Ratings
Film classification boards rate movies based on their content suitability for different audiences. Categories might include “G” (General Audiences), “PG” (Parental Guidance), “PG-13,” “R” (Restricted), and “NC-17” (Adults Only). These categories indicate increasing levels of mature content, but the differences between adjacent ratings aren’t uniformly defined.
7. Hotel Star Ratings
Hotels are often rated based on their quality, amenities, and services offered, using a system of stars, typically ranging from one to five. A “five-star” hotel is expected to offer luxury services and amenities, while a “one-star” hotel offers basic services. The difference in quality and services between adjacent star ratings is recognizable but not strictly quantifiable.
8. Clothing Sizes
Clothing items are often categorized into sizes like “extra small,” “small,” “medium,” “large,” and “extra large.” These categories indicate a progression in size, but the exact measurements that differentiate one size from another can vary between brands and regions. The order represents increasing dimensions, but the specific differences between sizes are not always consistent.
9. Severity of Disease
Medical professionals often categorize the progression of a disease into stages. For instance, cancer can be classified as “Stage I,” “Stage II,” “Stage III,” and “Stage IV.” Each stage indicates a progression in the severity and spread of the disease, but the exact differences between adjacent stages can be complex and might not be uniformly defined.
10. Employee Performance Ratings
In corporate settings, employees might be assessed based on their performance and given ratings such as “below expectations,” “meets expectations,” “exceeds expectations,” and “outstanding.” While these categories represent a clear progression in performance quality, the distinctions between them are qualitative and might not be precisely quantifiable.
11. Tornado/Storm Intensity
Meteorologists use scales like the Enhanced Fujita scale to categorize tornadoes. Ratings can range from “EF0” (minor damage) to “EF5” (incredible damage). Each category indicates increasing damage potential, but the differences between adjacent ratings are based on observed damage and estimated wind speeds.
12. Earthquake Magnitude
Seismologists categorize earthquakes based on their magnitude using scales like the Richter scale. Categories might range from “minor” to “light,” “moderate,” “strong,” “major,” and “great.” Each category signifies an increase in the earthquake’s energy and potential destructiveness, but the difference between each category involves logarithmic increases in amplitude.
13. Product Lifecycle Stages
Products in the market often go through stages like “introduction,” “growth,” “maturity,” and “decline.” These stages represent the product’s life from its launch to its eventual decline in popularity. While the order signifies the progression in a product’s market life, the duration and characteristics of each stage can vary.
14. Alert Levels
Governments or organizations might use alert levels to signify the severity of a situation, such as a threat or a natural disaster. Levels could range from “low” or “green” to “moderate” or “yellow,” “high” or “orange,” and “severe” or “red.” Each level indicates an increasing degree of risk or urgency, but the criteria for each category might differ based on the context.
15. Hiking Trail Difficulty
Hiking trails are often categorized based on their difficulty level. They can be labeled as “easy,” “moderate,” “challenging,” and “expert.” Each category indicates an increase in trail difficulty, encompassing factors like terrain, distance, and elevation gain. However, the exact challenges distinguishing one category from another can vary by location and individual perception.
16. UV Index Scale
The Ultraviolet (UV) Index measures the strength of sunburn-producing ultraviolet radiation at a particular place and time. The scale can range from “low” to “moderate,” “high,” “very high,” and “extreme.” Each level signifies an increase in potential harm from unprotected sun exposure, but the exact UV value ranges defining each category can differ based on the geographical region.
17. Hair Curliness Scale
Hair types can be categorized based on the curliness or texture of the hair. The scale might include “straight,” “wavy,” “curly,” and “coily.” Each type represents a different pattern of hair curl, but the distinctions between them are based on visual assessment and can be subjective.
18. Language Proficiency Levels
Language learners are often assessed based on their proficiency in a language. Levels can range from “beginner” to “elementary,” “intermediate,” “advanced,” and “native speaker.” Each level indicates a progression in language skills, but the exact competencies associated with each category can vary based on the assessment criteria.
19. Likert Scales in Surveys
A Likert scale is commonly used in questionnaires to capture respondents’ attitudes or feelings towards a statement. Responses might range from “strongly disagree” to “disagree,” “neutral,” “agree,” and “strongly agree.” Each category represents a progression in agreement or sentiment, but the psychological distance between categories isn’t necessarily uniform.
20. Spice Levels in Food
Dishes at restaurants might be categorized based on their spiciness. Levels can include “mild,” “medium,” “hot,” and “extra hot.” Each level signifies an increase in spice intensity, but the exact spiciness can vary based on ingredients and individual tolerance.
21. Software Release Phases
Software products often go through different release phases before they’re made widely available. These can be categorized as “alpha,” “beta,” “release candidate,” and “final release.” Each phase represents a progression in software stability and completeness, though the exact criteria differentiating the phases can vary by developer.
22. Pollution Air Quality Index
Air quality is often reported using an index that categorizes pollution levels. The scale might range from “good” to “moderate,” “unhealthy for sensitive groups,” “unhealthy,” “very unhealthy,” and “hazardous.” Each category indicates a progression in potential health risks, with specific pollutant concentration ranges defining each level.
23. Priority Levels
Tasks or issues, especially in project management or technical settings, can be labeled based on urgency or importance. Categories might include “low,” “medium,” “high,” and “critical.” While each level indicates a progression in urgency or significance, the criteria for determining priority can vary based on context.
24. Skincare Routine Steps
Skincare routines can be categorized based on the order and purpose of products applied. The sequence might include “cleanser,” “toner,” “serum,” “moisturizer,” and “sunscreen.” Each step has a specific purpose in skincare, and while the order is typically consistent, the benefits of each product can vary by individual needs.
25. Loyalty Program Tiers
Many businesses offer loyalty programs with tiers based on customer engagement or spending. Tiers can range from “bronze” to “silver,” “gold,” and “platinum.” Each tier signifies better rewards or benefits, but the exact criteria for reaching each tier and the benefits associated can vary by company.
Other Types of Data
There are four main types of data:
- Nominal Data: Nominal data represents categories that do not have a specific order or ranking (Katz, 2006a, 2006b). They are simply used to label variables without any quantitative value (Thiagarajan, 2023). Examples include colors (red, blue, green), gender (male, female, non-binary), and types of fruits (apple, banana, cherry).
- Ordinal Data: Ordinal data represents categories that have a meaningful order, but the distances between the categories are not defined or consistent (Stockemer, 2018). Examples include educational levels (high school, bachelor’s, master’s, doctorate) and Likert scale responses (strongly disagree, disagree, neutral, agree, strongly agree).
- Interval Data: Interval data have a consistent order and a consistent interval between values. However, they don’t possess a true zero point, which means you can’t make statements about something being “twice as much” as another. Examples include temperature in Celsius or Fahrenheit (because 0°C or 0°F does not indicate an absence of temperature) and IQ scores.
- Ratio Data: Ratio data possess all the properties of interval data and, additionally, have a true zero point. This zero point means an absence of the quantity in question (Wilson & Joye, 2016). Examples include age (0 years means an absence of age), height (0 cm or 0 inches means no height), and weight.
Albers, M. J. (2017). Introduction to Quantitative Data Analysis in the Behavioral and Social Sciences. Wiley.
Babbie, E., Halley, F., & Zaino, J. (2007). Adventures in Social Research: Data Analysis Using SPSS 14.0 and 15.0 for Windows (6th ed.). New York: SAGE Publications.
De Vaus, D. A. (2001). Research Design in Social Research. New York: SAGE Publications.
Dhingra, H. (2023). ICSE Robotics and Artificial Intelligence. Goyal Brothers Prakashan.
Katz, M. (2006). Study Design and Statistical Analysis: A Practical Guide for Clinicians. Cambridge: Cambridge University Press.
Katz, M. H. (2006). Multivariable analysis: A practical guide for clinicians. Cambridge: Cambridge University Press.
Stockemer, D. (2018). Quantitative Methods for the Social Sciences: A Practical Introduction with Examples in SPSS and Stata. London: Springer International Publishing.
Thiagarajan, B. (2023). Unlocking the Power of Data: A Beginner’s Guide to Data Analysis. Otolaryngology online.
Wilson, J. H., & Joye, S. W. (2016). Research Methods and Statistics: An Integrated Approach. New York: SAGE Publications.
Dr. Chris Drew is the founder of the Helpful Professor. He holds a PhD in education and has published over 20 articles in scholarly journals. He is the former editor of the Journal of Learning Development in Higher Education. [Image Descriptor: Photo of Chris]