The Likert scale was devised by the American social scientist Rensis Likert in 1932 as a method for measuring attitudes in his publication “A Technique for the Measurement of Attitudes.”
We all have come across these scales in various surveys and research studies, where we are asked to indicate our level of agreement or disagreement on a spectrum. Likert scales are used to measure opinions and attitudes in more depth, unlike simple “yes/no” questions.
Psychometrics is a field in psychology involving the development and validation of assessment instruments such as surveys, scales, and questionnaires. A psychometric scale is a scale commonly used in questionnaires and is the most widely used scale in survey research. The most widely used psychrometric scales are Likert scales, which comprise a number of response points, usually 4 to 9, with accompanying verbal anchors.
In this article, you will find everything you want to know about this scale, including topics like Likert scale options, advantages and characteristics of Likert scales, and even how to analyze data from a Likert scale.
What is a Likert scale?
Likert scale definition: A Likert scale is a quantitative analysis data collection tool used in surveys and research to assess individuals’ attitudes, opinions, or perceptions. This scale presents a series of statements or questions to respondents. The responses are assigned numerical values, allowing for quantitative analysis of the data. Likert scales are widely employed in fields such as psychology, sociology, and market research to quantify subjective experiences and gather quantitative insights into people’s attitudes or opinions.
Respondents express their attitudes, opinions, or perceptions on a predetermined scale. For example, the typical Likert scale would range from an option of “strongly agree” to an option of “strongly disagree,” with varying degrees of agreement or disagreement in between. The categories of response may be coded numerically. If so, the numerical values must be defined for that specific study, e.g., 1 = strongly agree, 2 = agree, etc.
What are Likert scale questions?
Coming to the application of Likert scale in research, let’s understand what Likert scale questions are. These questions are a type of research instrument that employs the Likert scale to measure people’s opinions, attitudes, or perceptions. The questions present a statement or assertion, and respondents are asked to indicate their level of agreement or disagreement with that statement. Usually, five or seven options are provided for respondents to choose from. An example of such a question is “How satisfied are you with the results of the dental appliance?” And typical response items would be as follows:
- Very dissatisfied
- Dissatisfied
- Neutral
- Satisfied
- Very satisfied
As you can see, positive options appear on one side and negative options on the other, and the midpoint is typically neutral. The options on the extreme ends are called response anchors.
When to use Likert scale questions?
Likert scale questions are versatile and can be tailored to various topics, making them a popular and effective tool in survey research to measure subjective experiences and opinions. Likert scale questions are appropriate to use in situations where one wants to obtain nuanced responses rather than binary yes/no-type answers. The responses to the former are far more informative and specific.
It is important to ensure that these scales are used appropriately and that the questions are clear, unbiased, and relevant to the research objectives. Here are some common scenarios when such questions might prove useful in research:
- Psychological research: Measuring attitudes, personality traits, and emotional states.
- Social science research: Quantifying attitudes and opinions on societal issues, political views, cultural preferences, etc
- Healthcare research: Assessing patient satisfaction or treatment efficacy.
- Market research: Gauging consumer preferences, brand perceptions, and product satisfaction, aiding businesses in making informed decisions.
Examples of a Likert scale
Here are some examples of Likert scales used in surveys and questionnaires.
Likert scale example for agreement
- Strongly agree
- Agree
- Undecided
- Disagree
- Strongly disagree
Likert scale example for likelihood
- Definitely
- Probably
- Possibly
- Probably not
- Definitely not
Likert scale example for frequency
- Very frequently
- Frequently
- Occasionally
- Rarely
- Very rare
Likert scale example for importance
- Very important
- Important
- Fairly important
- Slightly important
- Not important
Note that the above examples are all 5-point scales. Keep reading to know more about the types of Likert scales.
Types of Likert scales
When using a Likert scale survey, a researcher must consider issues such as categories of response and size and direction of the scale. Broadly, there are two types of Likert scales: odd and even.
Odd Likert scale
The odd Likert scale (e.g., 3-point, 5-point, or 7-point scale) includes a middle point, representing a neutral response. This midpoint can be interpreted differently by different respondents, but it avoids bias.
Odd Likert scales for satisfaction are as follows:
3-point scale
- Satisfied
- Neutral
- Dissatisfied
5-point scale
- Very satisfied
- Satisfied
- Neutral
- Dissatisfied
- Very dissatisfied
7-point scale
- Very dissatisfied
- Moderately dissatisfied
- Slightly dissatisfied
- Neutral
- Slightly satisfied
- Moderately satisfied
- Very satisfied
Even Likert scale
Even Likert scale questions have options without a central point. This means that respondents have to choose from the provided answer options (“forced choice” survey scale). Therefore, this scale is used when obtaining insights on a neutral option is not essential or when biased feedback is expected.
Even Likert scales for satisfaction are as follows:
2-point scale
- Satisfied
- Dissatisfied
4-point scale
- Very satisfied
- Satisfied
- Dissatisfied
- Very dissatisfied
Characteristics of Likert scales
Here are some essential characteristics of a Likert scale that make it a widely used and effective research tool.
- Each response option on a Likert scale is accompanied by unambiguous labels reflecting the intended level of agreement or disagreement.
- Likert scales are ordinal in nature, meaning that the response options have a clear order or ranking. Items have two extreme positions, with gradation between the extremes. The most common type has five items, but the use of more items increases precision and reliability in the results.
- Responses can be assigned numerical values to facilitate quantitative analysis of the data.
- These scales are usually symmetrical, with an equal number of positive and negative response options. This helps maintain balance and reduce response bias.
- These scales are easy to administer in surveys or questionnaires, making them a practical choice for collecting data even on a large scale.
- These scales can be adapted to various topics and contexts, making them versatile for measuring attitudes and opinions in different fields, such as psychology, sociology, business, and education.
How to write Likert scale questions?
- In your Likert scale survey, try to include both questions and statements. This makes the survey engaging.
- Use a mix of positive and negative framing in your questions to avoid bias in any one direction.
- Use concise and clear writing. Avoid ambiguity by avoiding complex syntax, double negatives, and jargon. Use proper word choice and do not include different topics within the same question.
How to write Likert scale responses?
- Decide the number of response options by balancing ease of answering with informativeness. Most researchers include five options.
- Decide between offering unipolar and bipolar options, i.e., measuring a single attribute (e.g., agreement) versus two attributes (e.g., agreement or disagreement).
- Ensure that the options provided are mutually exclusive.
- Avoid confusion by omitting overlapping response items or items with similar meanings.
How to analyze data from a Likert scale ?
To analyze data derived from the Likert scale, you first need to determine the data type. Likert-type data might be considered ordinal-level or interval-level data. An ordinal scale is one where the order matters but not the difference between values, e.g., socio-economic status, income level, satisfaction rating. Meanwhile, an interval scale is one where the difference between two values is meaningful, e.g., temperature, pH, exam scores. Note that Likert-derived data is typically treated as ordinal under the assumption of unequal distance between responses.
Next, you need to choose the descriptive statistics and/or inferential statistics to be used to describe and analyze the Likert-derived data. Descriptive statistics can be used to summarize the collected data in a simple numerical form or a graphical form. Alternatively, inferential statistics may be used to test hypotheses, such as correlations between different responses or patterns in the whole dataset.
Descriptive statistics
- For ordinal data, the mode is identified for each question to provide an overall assessment of the sample. For visualization, bar charts may be created, displaying the frequency of the choices.
- In the case of interval data, scores from each question are totaled for individual participants. The mean and standard deviation of scores across the sample are calculated, which indicate the average and spread, respectively
Inferential statistics
- For ordinal data, a hypothesis may be formed, such as exploring the connection between social media use and awareness of current affairs. A chi-square test of independence is employed to examine the correlation between these attributes.
- For interval data, consider an investigation into the relationship between IQ scores and social media use. Pearson’s correlation is used to determine whether the overall Likert scale score correlates with IQ. The analysis specifies whether data are treated at the ordinal or interval level.
Analysis at the ordinal level
Researchers commonly treat Likert-derived data as ordinal, where response categories are ranked, but equal distance between categories is not assumed. Descriptive statistics, such as the median or mode, are used to summarize data numerically or visually. Bar charts illustrate the frequency of each choice. Appropriate inferential statistics for ordinal data include Spearman’s correlation or a chi-square test for independence.
Analysis at the interval level
Likert-derived data can also be treated at the interval level, presuming equal distances between response categories. Appropriate inferential statistics, like analysis of variance (ANOVA) or Pearson’s correlation, are used, provided the assumption of interval-level data is stated. Descriptive statistics involve totaling scores, calculating the mean, and determining the standard deviation across the sample.
Advantages and disadvantages of Likert scale
The advantages of Likert scale include (i) granular results, allowing for a more detailed understanding of individuals’ perspectives on a given topic, and (ii) quantitative nature, which allows handling and statistical analysis of complex topics. Further, Likert scales are (iii) user-friendly and time-saving as they are closed-ended. Therefore, large samples can be used to obtain data.
The disadvantages of this scale are that it is prone to (i) response bias (i.e., respondents either agree or disagree with statements due to fatigue or social desirability) and (ii) subjective interpretation (owing to variation in interpretation of the items). Moreover, being closed-ended, (iii) Likert-type questions restrict the choices of the respondents.
Frequently asked questions
- What is the 5-point Likert scale?
The 5-point scale is a commonly used rating scale in social science research and survey questionnaires. Respondents are asked to indicate their level of agreement or disagreement with a statements based on five response items.
- What is the best Likert scale for research?
The choice depends on the nature of the research question, target audience, and study objectives. However, the 5-point Likert scale is most commonly used; it is versatile owing to its balanced response options and ease of interpretation. Many researchers are familiar with it, and it is widely accepted in academic and professional settings for analyzing Likert scale data.
- How can I use the Likert scale in research?
Here are step-by-step guidelines on how to use a Likert scale in research:
Begin by defining the objectives of your research. Identify the specific attitudes, opinions, or perceptions you intend to measure using the Likert scale. Select an appropriate scale format, and create clear and unbiased statements and a balanced set of response items. Next, conduct a pilot test or pretest of the scale with a small sample to identify any issues with clarity or response patterns. Use the feedback to refine and improve your scale. Finally, present your findings in a clear and organized manner in your research report or article.
- Are Likert scales quantitative or qualitative?
Likert scales are quantitative in nature. While the data collected from Likert scales are ordinal (meaning there is a clear order or ranking of responses), they are treated as quantitative for statistical analysis purposes because the scales involve assigning numerical values to responses, allowing for the application of various quantitative statistical techniques.
Editage All Access is a subscription-based platform that unifies the best AI tools and services designed to speed up, simplify, and streamline every step of a researcher’s journey. The Editage All Access Pack is a one-of-a-kind subscription that unlocks full access to an AI writing assistant, literature recommender, journal finder, scientific illustration tool, and exclusive discounts on professional publication services from Editage.
Based on 22+ years of experience in academia, Editage All Access empowers researchers to put their best research forward and move closer to success. Explore our top AI Tools pack, AI Tools + Publication Services pack, or Build Your Own Plan. Find everything a researcher needs to succeed, all in one place – Get All Access now starting at just $14 a month!
