The Likert scale continues to be a common tool for research scientists, especially in the fields of humanities and media studies. The Likert scale was introduced in the 1930s by its creator, Rensis Likert. The original scale featured five points participants could select from in response to a question, ranging from poor to excellent. Modern scales differ on the number of points and the focus of their measurement. For examples, one survey may measure your experience using a five-point, poor to excellent scale, while others may measure your level of agreement with a particular statement using a seven-point scale, strongly disagree to strongly agree.
- Skill level:
Other People Are Reading
Decide if your survey will be administered in-person or online. Online surveys are suitable if you want to reach a wide number of participants and the survey questions are general and easy to understand. Although in-person surveys may take considerably longer to conduct, they allow participants to ask researchers for clarification and can prevent cases of fraud, multiple submissions and other technical difficulties that may corrupt your results.
Determine if your scale will feature a neutral choice. Scales that use an odd number of choices, a five-point scale for example, allow participants to remain neutral. An even number of choices forces participants to express an active opinion. Research scientists continue to debate which technique is better. Many researchers choose their technique depending on the context of their study. When it is obvious that participants must have an opinion concerning particular questions, it may be advantageous to use an even point scale. On the other hand, forcing participants to choose when they may not have an opinion corrupts your data and creates unnecessary stress on the participants.
Choose the number of points featured in your scale. Scales usually range from four to seven points. Although it is possible to use more or fewer points on your scale, researchers caution against using too many or too few points. Too many points may make it difficult for participants to discern a meaningful difference between two neighbouring points. Too few points may lack the accuracy necessary to really convey participants' feelings.
Use clear labels for all your points. Instead of simply having the numbers one through five, label the choices so that they read poor to excellent or strongly disagree to strongly agree.
Always maintain a single direction throughout the entire survey. For example, if your survey's first question allow participants to answer on a scale that reads from poor to excellent, ensure that all your scales flow from poor to excellent. Including scales later on that flow from excellent to poor will confuse participants and corrupt your data.
- 20 of the funniest online reviews ever
- 14 Biggest lies people tell in online dating sites
- Hilarious things Google thinks you're trying to search for