Using Likert Scales in Psychology

A Likert Scale is a type of psychometric scale frequently used in psychology questionnaires. It was developed by and named after organizational psychologist Rensis Likert. Self-report inventories are one of the most widely used tools in psychological research. On a Likert scale, respondents are asked to rate the level to which they agree with a statement. Such scales are often used to assess personality, attitudes, and behaviors.

On a survey or questionnaire, a typical Likert item usually takes the following format:

1. Strongly disagree
2. Disagree
3. Neither agree nor disagree
4. Agree
5. Strongly agree

It is important to note that the individual questions that take this format are known as Likert items, while the Likert scale is the sum of several of these items.

In addition to looking at how much respondents agree with a statement, Likert items may also focus on things such as likelihood, frequency or importance. In such cases, survey takers would be asked to identify how likely they believe something to be true (Always true, Usually true, Sometimes true, Usually not true, Never true), how frequently they engage in a behavior or experience a particular thought (Very frequently, Frequently, Occasionally, Rarely, or Never) or how important they feel that something is to them (Very important, Important, Somewhat important, Not very important, Not important).

In some cases, experts who are very knowledgeable about the subject matter might develop items on their own. Oftentimes, it is helpful to have a group of experts help brainstorm different ideas to include on a scale.

1. Start by creating a large pool of potential items to draw from.
2. Select a group of judges to score the items.
3. Sum the item scores given by the judges.
4. Calculate intercorrelations between paired items.
5. Eliminate items that have a low correlation between the summed scores.
6. Find averages for the top quarter and the lowest quarter of judges and do a t-test of the means between the two. Eliminate questions with low t-values, which indicates that they score low in the ability to discriminate.

After weeding out the questions that have been deemed irrelevant or not relevant enough to include, the Likert scale is then ready to be administered.

Because Likert items are not simply yes or no questions, researchers are able to look at the degree to which people agree or disagree with a statement.

However, as with other forms of assessment, Likert scales can also be influenced by the need to appear socially desirable or acceptable. People may not be entirely honest or forthright in their answers or may even answer items in ways to make themselves appear better than they really are. This effect can be particularly pronounced when looking at behaviors that are viewed as socially unacceptable.

If you've ever taken a psychology course, chances are that you've probably heard the term pronounced "lie-kurt." Since the term is named after Rensis Likert, the correct pronunciation should be "lick-urt."