MicrosoftTeams image 10

SURVEY METHODOLOGIES

Ordinal Scale: Definition, Characteristics, & Uses

Transform your insight generation process

Use our in-depth online survey guide to create an actionable feedback collection survey process.

SHARE THE ARTICLE ON

Table of Contents

Introduction:

In survey and market research data collection is an integral step that leads you to make effective business decisions. The ordinal scale is one of the ways marketers collect qualitative data by associating numerical values. 

This blog will dive deep into everything about the Ordinal Scale. 

What is the Ordinal Scale?

Ordinal Scale is listed 2nd in the four ‘Levels of Measurement’, as described by S.S. Stevens. The Ordinal scale includes statistical data type where variables are in order or rank but without a degree of difference between categories.

The ordinal scale contains qualitative data; ‘ordinal’ meaning ‘order’. It places variables in order/rank, only permitting to measure the value as higher or lower in scale. The scale cannot generate a precise comparison between the two categories.

For instance, in a horse race, we only see the ranking of the horses that won as 1st, 2nd, and 3rd. The ranks don’t tell us by how much distance did the first horse win or the third horse lose.

Characteristics of Ordinal scale

  1. You can use an ordinal scale for research and survey purposes to understand the higher or lower value of a data set. The scale identifies the magnitude of the variables.
  2.  It does not explain the distance between the variables. The ordinal scale cannot answer “how much” different the two categories are.
  3. Like a Likert scale, the ordinal scale can measure frequency, importance, satisfaction, likelihood, quality, and experience, etc.
  4. The measures in ordinal scale do not have absolute value hence the real difference between adjacent values may not have the same meaning. For example, the values in the age scale “less than 20” and “20-50” do not have the same meaning as “50-80” and “over 80”.

See Voxco survey software in action with a Free demo.

How to measure data collected using the Ordinal Scale?

Data obtained using an ordinal scale can be analyzed using descriptive & inferential statistics. So let’s explore the two different statistical approaches to analyzing ordinal data. 

Descriptive Statistics

The frequency distribution table can inform the number of times each response was selected.

For example, you ask 30 respondents 

Q. I take home-cooked meals to the office. 

Answers: 

Always

Often

Sometimes

Rarely

Never

Frequency Distribution Table

Agreement level

Frequency

Always

12

Often

5

Sometimes

6

Rarely

3

Never

4

**You can visualize the data in a bar graph. It is important to remember that the categories used in the ordinal scale should be in proper order when displaying data. 

To find the Central Tendency, you can calculate the mode or the median.

The mode can be found in almost all ordinal scale data. But, the median can be found in some cases. 

Based on the above dataset, the mode is “Always.” Mode is the value that appears most frequently in your dataset. 

The value of the median is found in two ways for odd & even-numbered datasets. 

Odd-numbered dataset: The median is the middle value of the dataset. 

Even-numbered dataset: The median is the mean of the two values in the middle.

In this example, the median would be the value at the 15th, and 16th positions,i.e., “Often” 

Inferential Statistics

Non-parametric tests are used in the case of inferential statistics. The following are non-parametric tests you can use to analyze ordinal data. 

Non-parametric test

Aim

Samples or Variables

Mood’s median test

Compare the medians

2 or more samples

Mann-Whitney U test

Compare sum of rankings of the scores

2 independent samples

Wilcoxon matched-pairs signed-rank test

Compare magnitude & direction of difference between the distribution of scores

2 dependent samples

Kruskal- Wallis H test

Compare the mean ranking of scores

3 or more samples

Spearmen’s rho, or rank correlation coefficient

Correlate 2 variables

2 ordinal variables

Transform your insight generation process

Create an actionable feedback collection process.

Types of Ordinal Scales to use

We have compiled types of ordinal scales you can use to gather customer data. 

Familiarity: 

The familiarity scale can help you gather the level of knowledge your respondents have about the topic. 

Very Familiar

Quite Familiar

Moderately Familiar

Somewhat Familiar

Not at all Familiar

A brand can use this type of ordinal scale to test how familiar their audiences are with the brand’s product. 

Agreement: 

This scale can help determine how much your respondents agree/disagree with your statement.

Strongly Agree

Agree

Neutral

Disagree

Strongly Disagree 

A company can evaluate employee opinion on work-life balance. The degree of agreement or disagreement can help identify how the company can improve employee perception. 

Frequency

This ordinal scale can inform you how often an activity is performed to help you evaluate the behavior pattern. 

Always

Often

Sometimes

Rarely

Never

A coffee brand can survey prospective customers about how often they drink coffee in a week. The brand can use the result to segment customers based on their coffee intake and develop strategies suitable for each segment. 

Satisfaction: 

The best way to understand how satisfied your customers, employees, and prospects are with your services and products. 

Very Satisfied

Satisfied

Neutral

Dissatisfied 

Very Dissatisfied 

Gather customer satisfaction at every touchpoint in their journey using this scale to determine which touchpoint needs improvement and where you are excelling. 

Likelihood: 

This scale helps you understand how likely the respondents will perform the suggested activity. 

Certainly

Most-likely

Maybe

Unlinkey

Not at all

A company can use this to identify which customers are most likely to recommend your product to friends and family members. 

Explore all the survey question types
possible on Voxco

Conclusion

Ordinal scale is used to collect data so that researchers can infer conclusions. It helps us infer how many respondents are satisfied or dissatisfied with your services. The ordinal scale does not offer the reason behind the response. 

However, the ordinal scale can help you gauge customer response quickly and collect data fast. You can create short surveys using an ordinal scale for initial research. 

Read more

Violin Plot

Violin Plot SHARE THE ARTICLE ON Table of Contents A violin plot is a combination between a box plot and a kernel density plot that

Read More »

Post Event Survey Questions

Post Event Survey Questions SHARE THE ARTICLE ON Share on facebook Share on twitter Share on linkedin Table of Contents Planning an event is no

Read More »

Customer 360 solutions

Customer 360 solutions SHARE THE ARTICLE ON Share on facebook Share on twitter Share on linkedin Table of Contents What is customer 360 view? Customer

Read More »
Shopping Basket
Great Research
Fast Insights
Best-in-class ROI

Voxco’s platform helps you gather omnichannel feedback, measure sentiment, uncover insights and act on them.

Join 500 + global clients across 40+ countries

Great Research
Fast Insights
Best-in-class ROI

Voxco’s platform helps you gather omnichannel feedback, measure sentiment, uncover insights and act on them.

Join 500 + global clients across 40+ countries