Scales, Likert Statement

Overview and Use

The Likert scale was developed by psychologist Rensis Likert in 1932 as a method for measuring attitudes. It is a bipolar approach to scaling that measures responses to statements along a positive-to-negative dimension. Traditional Likert scales include the following features: declarative statements that express clearly positive or negative attitudes, five ordered response options (known as the response set), an equal number of positive and negative response options, descriptive labels for each of the response options ranging from strongly agree to strongly disagree, and numeric values assigned to each response option for analysis purposes (e.g., 1 = strongly disagree; 5 = strongly agree). An example of a Likert scale item is as follows: “Please indicate the extent to which you agree or disagree with the following statement: I feel that I can be completely honest with my best friend; 1 = strongly disagree, 2 = disagree, 3 = neither agree nor disagree, 4 = agree, 5 = strongly agree.” Any adaptation to the Likert scale, such as using different categories for responses (e.g., never to always, or most important to least important), or using a different number of response categories (e.g., a 4- or 7-point scale) creates a Likert-type scale.

Likert and Likert-type scales are scored by assigning numeric values to the response categories, starting with 1 at one end of the scale and assigning consecutively higher numbers to the categories (2, 3, etc.) toward the other end of the scale (up to 5 in the traditional Likert scale). Higher numbers typically indicate greater agreement with the statement (or more positive ratings). The scores for the individual items can then be summed to create a total score for the set of items, or in some cases, averaged for a mean score of agreement.

Researchers in the social sciences generally consider Likert scales to be an interval-level measure, meaning there are equal distances between each consecutive point along the scale. There is some disagreement, however, as to whether the scales are more appropriately defined as ordinal measures; that is, ordered categories for which equal distances between categories cannot be assumed. Some scholars argue that it is unlikely that participants perceive the distances between all of the points along the Likert scale to be equal (e.g., the difference between strongly disagree and disagree is the same as that between neutral and agree), particularly when there are only five response options.

...