The Use of Scales in Surveys ROI

The Use of Scales in Surveys


Table of Contents


Social scientists use different scales to obtain and measure information regarding attitudes, values, and intentions. In the empirical social sciences, methods of scale construction are used to develop scales. Within this article, we will go over some common and established methods of scale construction and will specifically delve into the variety of measurement instruments leveraged in the social sciences.

Transform your insight generation process

Create an actionable feedback collection process.

online survey

Likert Scales

The Likert scale generally takes the form of a five-point scale response format, although seven-point and ten-point versions of it are also commonly used. This scale is commonly used in surveys, owing to its simplicity of use and interpretation. Likert scales provide respondents with a list of statements, from which they can select the one that reflects their opinion about the question or statement that it follows. 

The following is an example of the general format of the Likert scale:

  • How much do you agree with the following statement:

‘There is a disparity in the way men and women are treated in my workplace.’

The Use of Scales in Surveys ROI

The respondents’ answers in terms of the degree of agreement or disagreement are used to weigh the response alternatives. For example, strongly agree carries one point while strongly disagree carries five points. A respondent’s overall score is calculated by summing their points of each item on the questionnaire. 

Scalogram Analysis

Scalogram analysis is used to evaluate statements or items in a measurement instrument to discern whether or not it forms a Guttman scale. This scale is one of the three unidimensional scales, the other two being the Likert scale and the Thurston scale.  Scalogram analysis makes the assumption that items on a scale can be ordered in regard to their degree of complexity. 

We can take the example of examinations. Certain questions in tests and examinations are generally harder to answer than others. Those with limited knowledge on the topic of the exam may only answer a limited amount of questions on the test while those with more knowledge on the topic will be able to answer more. 

Based on the assumption that some questions are harder than others, the tester can sort the exam questions accordingly, with the easier questions at the beginning and the more difficult ones toward the end. 

Scalogram analysis can be understood better by considering the extent of a certain attitude rather than exam knowledge, where some variables achieve lower agreements than other variables, simply because they are easier to respond to.

Thurstone Scale

The Use of Scales in Surveys ROI

The Thurstone scale is a unidimensional scale that is used to measure people’s attitudes, feelings and behaviour toward a particular subject. It involves the use of “agree-disagree” statements that carry various weights. These statements are used to determine how a subject feels toward a particular topic, as well as how strongly they feel toward it. The weights allow researchers to compute an average of their scores to reveal an outcome that indicates how the respondent’s feelings toward the topic.

The following is an example of the general format of the Thurstone scale:

Please indicate which statements you agree with and which statements you disagree with:




I believe that physical exercise is integral to maintaining good health.


I believe that having a strict diet is the key to losing weight.


I want to lead a healthier lifestyle.


See Voxco survey software in action with a Free demo.

Conjoint Analysis

Conjoint analysis is a survey-based statistical technique that is commonly used for market research purposes. There are many different types of conjoint analysis, each with a distinct purpose. 

These are a few types of conjoint analysis: 

  • Choice-Based Conjoint Analysis: Also known as discrete-choice modelling, CBC involves presenting respondents with 3-5 full profile concepts so that they can choose which they prefer most. 
  • Adaptive Conjoint Analysis: Adaptive conjoint analysis varies the choice sets that are shown to respondents based on their responses to the initial questions indicating their preferences. 
  • Full Profile Conjoint Analysis: In this type of conjoint analysis, respondents are shown full product profiles one at a time so that they can evaluate each profile independently.
  • Max-Diff Analysis: MaxDiff analysis involves presenting respondents with a set of items and then asking them to choose their most and least preferred. 

Download Market Research Toolkit

Get market research trends guide, Online Surveys guide, Agile Market Research Guide & 5 Market research Template

Making the most of your B2B market research in 2021 PDF 3 s 1.png

FAQs on Scales used in Surveys

Some scales that are commonly used in social science research are the binary, Likert, semantic, differential, and the Guttman scale.  

The Likert scale generally takes the form of a five-point scale where respondents are presented with a list of statements, from which they can select the one that best reflects their opinion about the question or statement that it follows.

The three main types of unidimensional scales are the Thurstone scale, the Likert scale, and the Guttman scale.

TheThurstonee scale can be defined as a unidimensional scale that is generally used by social scientists to measure people’s attitudes, feelings, and behaviour toward a particular subject.

Explore all the survey question types
possible on Voxco

Read more