subject: How To Use Likert Items In Your Online Surveys [print this page] One of the more frequent survey strategies used on questionnaires is the Likert merchandise; it is a sort of question that measures the respondent's degree of agreement or disagreement with a specific declaration. Every item is comprised of a stem and a scale
For example, look at the subsequent piece...
"The national minimum wage should be increased."
1. Strongly disagree
2. Disagree
3. Undecided
4. Agree
5. Strongly agree
The stem of a Likert item is the declaration (i.e. "The federal minimum wage should be greater."). The item's scale is the selection of probable replies
Though this is a apparently simple strategy for soliciting the feelings of your market, it often leads to skewed data due to poor design.
In this post, we will take a look at some of the issues inherent with using Likert items in your internet surveys. The goal is not to deter you from using them. On the contrary, by revealing the possible traps, you will be ready to stay away from them when creating your surveys.
Potential Problems With Using Likert Items
An important part of developing an effective survey is recognizing the potential dispositions of your audience and reducing their effect on your data. A particularly common phenomenon with Likert items is acquiescence bias. This occurs when answerers communicate a normal inclination to agree with the item's stem. From our previous illustration, participants will be prepared to select choices 4 or 5 ("agree" and "strongly agree," respectively). In case they don't agree with the stem, they may select option 3 ("undecided").
This can happen for a variety of reasons. First, the participant can have an innate penchant for agreeing with others - in this instance, the survey's designer - prompted by a desire to be polite or amenable.
Second, the prejudice may happen due to an attractiveness to presumed authority. That is, the participant could think the surveyor is an authority on the matter, and thus likely to be better informed than he or she. From this perspective, agreement with the stem looks appropriate.
Third, acquiescence bias may happen because of the participant's desire to complete the survey. Disagreement requires more validation than agreement; that requires more effort and time to cautiously consider the feasible responses.
An additional possible problem with using Likert items entails a trend known as social desirability bias; this occurs when the participant's choice is swayed by his or her want to be considered in a positive light by other people. Depending on the stem's matter, this person might be compelled to agree or disagree based on how they comprehend an additional person's anticipations.
Of the 2 types of bias, acquiescence bias is easier to minimize (although difficult to eliminate entirely). Every Likert item's scale should be distributed equally across positive and negative replies to prevent stimulating the participant's bias.
Analyzing Your Results: Interval Versus Ordinal Data
Initially, examining the info from a Likert item appears basic. With a 5-level scale - like the one used in our earlier instance - producing and confirming the results is easy. However, it's worth taking a better look.
A typical mistake is to presume the scale responses reflect interval instead of ordinal data. Interval information assumes the length among responses is equal; that is, option 1 is equidistant from option 2 as 2 is to option 3. While an argument may be made that this is certainly the case for a specific Likert scale, most scale responses reflect ordinal info. This is info that does not imply distance - equal or otherwise - in between responses. Any presumption to the contrary is likely to lend to a misinterpretation of your survey's results.
Likert items are beneficial and ought to be incorporated within your internet surveys; the tip is to create them in a way that minimizes the effect of acquiescence bias, and to prevent presuming the info suggests something it does not.
How To Use Likert Items In Your Online Surveys
By: Vicente Lyons
welcome to Insurances.net (https://www.insurances.net)
