10 tips and tricks for using the Likert scale in your studies
Are you looking for a simple way to determine what your participants think of a particular topic? One that’s easy to measure and compare, and with more nuance than a simple ‘yes’ or ‘no’ question?
Enter the Likert scale: a reliable, versatile, user-friendly tool that can help you achieve just that.
Let’s take things back a bit. To understand the Likert scale, you’ll first need to know what a survey scale is.
A survey scale gives participants a set of answer options – either numeric or verbal – covering a range of opinions on a topic. It’s always part of a closed-ended question, which presents respondents with pre-populated answer choices.
Now, onto the Likert scale. Established by the aptly named psychologist Rensis Likert, it’s a widely used method for measuring… well, likes and dislikes.
It’s a scale with typically five or seven points that range from one extreme attitude to another, with a moderate or neutral option in the middle.
Respondents indicate their level of agreement or disagreement with a statement by selecting a point on the scale.
For instance, if you want to find out about pizza toppings preferences, you could ask respondents to rate their agreement with the statement, ‘I enjoy pineapple as a pizza topping,’ on a scale ranging from ‘Normal person’ to ‘Sadist’.
Just kidding. We mean, of course, on a scale from ‘Strongly disagree’ to ‘Strongly agree’.
The Likert scale is perfect for capturing people's attitudes, beliefs, or opinions on a given topic. For example, when:
Now, here are ten steps to follow that’ll help you use the Likert scale effectively.
Structure your questions to stay on the same topic.
This’ll help you obtain more accurate results – when you come to report the data, you can analyze scores that sum up sentiment from a few questions.
For example, if you wanted to know what respondents thought of a particular three-course meal, you could ask: ‘How satisfied or dissatisfied were you with the quality of the dinner you were served tonight?’, followed by questions about their opinion on each course to get a better overall picture of how things went.
Make sure your statements are specific, clear, and easy to comprehend. Avoid using jargon, technical terms, and complex language.
Plus, be careful with your adjectives. There should be no confusion about which grade is bigger or better: is, say, ‘quite a lot’ more than ‘quite a bit’?
Keeping things simple allows respondents to quickly understand the question and focus on their response.
To avoid bias, ensure your questions are written neutrally, and don’t suggest a ‘correct’ answer.
Moreover, make sure your questions really are questions rather than statements. Humans are, on the whole, nice and respectful – and won’t want to disagree with you. (This phenomenon is called acquiescence response bias.)
Scales with an odd number of values will have a midpoint, giving participants the option to sit somewhere in the middle.
A common approach is to use a five- or seven-point scale, with options like ‘Strongly disagree’, ‘Disagree’, ‘Neither agree nor disagree’, ‘Agree’, and ‘Strongly agree’.
If you offer more than seven response choices, people will likely start picking answers randomly, so keep this in mind as your magic number.
Design your Likert scale so it encompasses the entire spectrum of possible opinions. If a question asks how quick your waiter was, and the answers range from ‘extremely fast’ to ‘moderately fast’, respondents who think the waiter was slow won’t know which option to choose.
You’ll also want to think about whether to opt for a bipolar or unipolar scale. Bipolar means attitudes fall on two sides of neutrality: going from ‘love’ to ‘hate’, for example. Unipolar, which is usually preferable, goes from ‘none’ to ‘maximum’: so, ranging from ‘not at all strange’ to ‘extremely strange’. (Like those who enjoy pineapple on their pizza.)
Use ‘skip logic’ so participants can skip questions that aren’t relevant to them.
For example, if you only want feedback from restaurant diners who had a poor experience, those who had a great time don’t need to – and shouldn’t have to – answer.
Before launching your survey, test it with a small group of participants.
This’ll help you identify any confusing questions or statements – especially with things like numbers, where people may be unsure which end of the range is positive and negative.
It’ll also allow you to gauge the time needed to complete the survey.
Maintain a consistent format for your Likert scale questions throughout the survey by using the same number of response options and maintaining the order of scale points.
This cuts confusion and helps to improve your data quality.
Likert scale data is ordinal in nature, meaning that the intervals between scale points may not be equal.
When comparing groups or identifying trends, use non-parametric statistical tests, like the Mann-Whitney U test or the Kruskal-Wallis test.
After analyzing your data, use graphs and charts to show your findings.
Bar charts, pie charts, and box plots are excellent options for visualizing your Likert scale data, making it easy for your audience to pick out the key insights.
Whether you're exploring preferences for pizza toppings or investigating more complex (and arguably less controversial) topics, the Likert scale can provide the insights your research needs.
For more useful tips and tricks, download our complete best practice guide to online research.
Fresh out of YC's Summer 2019 batch, we want to share some of our most interesting learnings. If you're a startup founder or enthusiast and want to learn about product-market fit, growth experimentation and culture setting, you're in the right place!
Today Prolific is turning 5 years old – Happy Birthday to us! 🥳 It's been a remarkable journey so far. 3000+ researchers from science and industry have used Prolific last year, we have 45,000 quarterly active participants, and we've seen 200% year-on-year growth. But we're only getting started. In this post, I'll tell you a little bit about our journey, give credit where it's due!, and tell you about our exciting plans for the future.