If you have been around survey research for any length of time you have come across the ubiquitous Likert scale. But, do you ever wonder what the Likert scale really is? This question format and its strongly agree to strongly disagree framework is a staple for in the pantry of questions we use on surveys. In the years I have been involved in constructing surveys and teaching market research I have seen many techniques and question types rise and fall in favor, yet the Likert scale holds its own.
The scale was developed by organizational psychologist Rensis Likert in order to measure the level of agreement or disagreement of a symmetric agree-disagree scale. The area of interest, be it a marketing or a social science construct, is assessed using a series of statements, each designed to view the construct from a slightly different angle.
- People come to me for information on new products.
- I enjoy sharing information with others.
- I consider myself knowledgeable on a variety of issues.
- Ted’s Pizza has excellent customer service.
- You get a lot of food for the price at Ted’s Pizza.
The first four statements were centered on the individual and might be part of an opinion leader or early adopter scale. The latter two statements measure the customer’s perceptions about the business. Just as easily you can create a scale with items that touch upon social topics, religious aspects, or other important issues.
The scales are usually five, seven or nine points, with five and seven point measures being the most common. For example – Strongly Agree, Agree, No opinion, Disagree and Strongly Disagree. Adding “Somewhat” to both sides creates the sixth and seventh points. The anchor points (the strongly agree/disagree) can be on either end. There is some research that indicates having the agree side shown first will inflate the scores. This can be tested by alternating the anchor points within a survey wave and comparing scores in the data analysis stage.
One of the critical aspects to remember is that Likert scales are designed to measure attitudes and by nature are multi-item. This point needs further elaboration. Basic research tells us that multiple-item measures of a construct are inherently more stable and subject to less random variability than single-item measures. How many items is enough? If you are creating a new scale then you should create as many items as possible and let subsequent analysis narrow the field for you. This can be done through brainstorming sessions, focus groups or extensive review of existing literature.
There are several methods to ensure that scales are measuring one dimension including reliability analysis and factor analysis. These techniques require a higher-level of analytical skill and will be discussed in later posts.
Written by Greg Timpany