How to use the Likert scale in statistical analysis
The Likert scale is commonly used in survey research. It is often used to measure the attitudes of respondents, asking them to what extent they agree or disagree with a particular question or statement. A typical scale could be "strongly agree, unsure/undecided, disagree, strongly disagree". Data from a survey using a Likert scale may seem easy to analyze, but there are important issues to be considered by a data analyst.
Get the data from the list for analysis by coding the responses. For example, say you have a survey asking respondents whether they agree or disagree with a set of positions on the platform of a political party. Each position is a question of the survey, and the scale will use the following answers: strongly disagree = 1, disagree= 2, neutral= 3, agree=4, strongly agree =5.
Remember to differentiate between ordinal and interval data because both types require different analytical approaches. If the data is ordinal, we can say that a score is higher than another. We can't say how high as we can do with interval data, which will tell you the distance between two points. Here's the catch to Likert scale: many researchers will treat it like an interval scale. This means that the differences between each response are equal in distance. The truth is that the Likert scale does not tell us this. It only tells us that people with more answers are more in line with the party's positions than those with the lowers number of answers.
Start analyzing data from the Likert scale with descriptive statistics. Although it may be tempting, resist the urge to take numerical answers and calculate an average. Add an answer "strongly agree" (5) to two "disagree" (2) answers, which would give an average of 4 but, what does this number mean? Fortunately, there are other measures of central tendency that can be used in addition to the average. Using data from the Likert scale, the best measure to use is the mode or most frequent response. This makes the survey's results much easier to interpret for the analyst (not to mention the audience, for your presentation or report). You can also visualize the distribution of responses (percentage of people who agree or disagree, etc.) in a graph, a bar graph or one bar for each response category.
Proceed with inference techniques that test the hypotheses proposed by the researchers. There are many methods available, and the best depends on the nature of the study and the questions they're trying to answer. One popular method is to analyze the responses using analysis of variance techniques such as the Mann Whitney test or the Kruskal Wallis test. Suppose in our example we wanted to analyze the responses to the questions on foreign policy positions with ethnicity as an independent variable. Suppose that our data include these responses: Anglos, African American and Hispanic respondents, so it could analyze the responses among the three groups of respondents with the Kruskal Wallis variance.
Simplify your survey data by combining the four response categories (eg. strongly agree, agree, disagree, strongly disagree) in two nominal categories such as agree/ disagree, accept or reject, etc.). This offers further analysis. The chi square test is an approach to the analysis of the data in this way.
If you want to read similar articles to How to use the Likert scale in statistical analysis, we recommend you visit our University degrees category.
- Remember there are many positions of analysis. Consider your investigation questions to determine the best analysis method for your study.
- Likert scales vary in the number of points on the scale. The five point scale that is used here is the most common, but some Likert scales have 4 points , where the "not sure" category is taken out (indecisive category). Some even have scales of up to 7 points.