pexels photo 3184338 L

What are Scales of measurement?

Try a free Voxco Online sample survey!

SHARE THE ARTICLE ON

Table of Contents

What is Systematic Sampling?

Scientific market research studies require careful measurements, using well-chosen instruments. This is where scales come in. 

See Voxco in action

What is a scale?

A scale is a measurement tool used to grade a variable in terms of its magnitude or quality.

What's a variable?

A variable is any characteristic (which is being observed or measured) whose value can change.

[Free Webinar Recording]

Want to know how to increase your survey response rates?

Learn how to meet respondents where they are, drive survey completion while offering a seamless experience, Every Time!

What are variables used for?

Studying any phenomena 

How do we study phenomena using variables? Researchers studying any phenomena attempt to explain the causes & relations driving them by using variables. Variables are used to capture any repeatable patterns that show up when observing such phenomena. Researchers segregate variables into dependent & independent variables. This can be for market research as well as social/customer research. Then they attempt to run controlled experiments by varying only the independent variable to test their hypothesis about how those variables are related to the dependent variables. 

What are the different scales of measurement?

Scales of measurement

There are four different scales of measurement. This means that the data gathered or observed can fall under one of the four scales. The four types of scales are:

  • Nominal Scale
  • Ordinal Scale
  • Interval Scale
  • Ratio Scale

Nominal, Ordinal, Interval & Ratio refer to the four scales of measurement used to define variables or numbers in statistics

A nominal scale uses numbers to classify & assign objects or items to categories (numbers such as 1 or 2 are used as labels). Numbers do not mean that one item is better or worse than the other; they are simply being used for classification. 

For example in the case of gender, an individual may either be male or female. If we assign the number 1 to male & 2 to female, the numbers only function as tags to mark individuals as falling in either category 1 or 2. The categories cannot be ordered or ranked as better or worse than the other. They serve only a descriptive function. 

In others words, the nominal scale is only qualitative in nature & not quantitative. The scale only indicates the presence or absence of a particular quality. 

Examples – Nationality, literacy, gender, marital status etc 

 

Characteristics of Nominal scale :

  • Nominal scale is only descriptive or qualitative in nature & not quantitative. The numbers used have no significance quantification wise and the sole goal of using numbers is to assign variables to different categories. For example – American 2. Non-American
  • Since the Nominal Scale is only used for classification purposes, the data gathered or variables observed are classified in either/or form. When the variables fall only into two categories such as answering yes/no, the scale is referred to as dichotomous.
  • The only measure of central tendency that is applicable in the nominal scale is mode.

 Ordinal Scale – refers to the second level of measurement as items falling on the scale are not just described but also ranked in an ‘order’. The scale captures the magnitude of a variable relative to others. 

For example Ranks of athletes in a race – 1st, 2nd & 3rd capture that the first was faster than the second who was in turn faster than the third. 

However, the scale does not indicate the interval properties. For example In the above case, The ranking of athletes does not capture their lap timings or the difference in their timings. 

Therefore, it fails to indicate how much quicker the winner of the race is than the person assigned the rank 2. Numbers in the ordinal scale represent the rank order but do not convey any info regarding the amount of quantity or degree of quality. 

Characteristics of Ordinal scale:

  • The ordinal scale makes it possible to not only classify & describe the variables but also captures their relative order or rank.
  • One does not know anything about the difference between two adjacent numbers in the ordinal scale – Interval properties are not known
  • The ordinal scale is widely used to capture survey responses which measure satisfaction, happiness, likelihood & frequency of occurrence

Interval Scale

An interval Scale refers to the third of measurement where numbers form a continuum and the difference between them is meaningful, but the scale lacks a true zero. The difference between any two numbers that are side by side is the same & known. If a zero is used, it is chosen arbitrarily for reference’s sake. Lack of a true zero means that the zero here does not denote the complete absence of the property being measured.

For eg. Temperature scales such as those in degree Fahrenheit & Celsius represent interval scales. They lack a true zero as 0 °F and 0 °C do not indicate an absence of temperature.

Characteristics of interval scale

  1. The interval properties are equal & known in this scale. The difference between two adjacent numbers is the same and meaningful here. Therefore this scale is quantitative as opposed to the nominal & ordinal scale. 
  2. This scale lacks a true zero – An arbitrary zero is chosen here for reference purposes but zero here does not indicate the absence of the property being measured. 
  3. The variables can be ranked here. The interval scale has the ordering property of the ordinal scale. 
  4. This scale allows you to calculate both the mean & median. 
  5. This scale is helpful in measuring feelings & sentiments in surveys as they can be graded in magnitude with meaningful differences.

Ratio Scales

Ratio Scale refers to the fourth level of measurement where numbers have all the properties of interval Scale as well as a true zero. True zero means refers to a complete absence of the characteristic being measured. This makes it an effective tool in market research software.

For eg. Height & weight. A score of 0 in either means a complete absence of height or weight. A beam  6 feet tall is two-thirds as tall as a 9 feet tall one. Similarly, a rod weighing 20kg is half as heavy as one weighing 40 kg.

Read more

ludde lorentz YfCVCPMNd38 unsplash scaled

Ratio Data

Ratio Data : Definition, Examples, Survey Questions & more Transform your insight generation processUse our in-depth online survey guide ...

MARKET SIZING1

Market sizing

Market sizing SHARE THE ARTICLE ON Share on facebook Share on twitter Share on linkedin Voxco is trusted by 450+ Global Brands in ...

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