The optimal number of response categories in the Likert scales

#1
Hi, everyone.
I want some advice on using the Likert scale. I have some questions that need your help in answering.

1. Is neutral choice (middle point) necessary on the Likert scale? Why? Because I found that some researchers used odd points while the others used even points on the Likert scale.
2. I know that the Likert scale has variations in response categories from 2-point to 10-point scales. What is the optimal number of response categories that is preferable to use? Why?

Thank you.
 

Karabiner

TS Contributor
#2
You surely have done some web search, which gives results such as here.
So, what can we add to this?

With kind regards

Karabiner
 
Last edited:
#3
@Karabiner, thank you for providing me with the link.
Parallel with the post here, I am also doing some literature research regarding the Likert scale. I am a little bit confused about deciding the number of responses for the Likert scale. Should I use odd responses? How many points should I use, 3-point scale, 5-point scale, or 7-point scale? But some researchers said that a neutral category gives respondents an easy way to avoid answering sensitive questions.

I need your advice to help me decide the best way to use the Likert scale.
Thank you.
 

AngleWyrm

Active Member
#4
The best implementation of a Likert scale that I've seen is used by the software distribution platform Steam.
It uses a 2-point scale, yay or nay. The aggregation of votes on a purchased product constitute the user rating, which categorizes the tally as
{ very positive, somewhat positive, mixed, somewhat negative, very negative } as a result of only votes of the form thumbs up or thumbs down.
 

Karabiner

TS Contributor
#6
https://pubmed.ncbi.nlm.nih.gov/10769936/ recommends at least 5 point and not more than 10 point response formats.

Cox in "The optimal number of response alternatives for a scale: a review" (1980) wrote:
  • scales with only two or three response options are inadequate because these scales are not capable of transmitting much information.
  • using more than nine alternatives does not pay off either.
  • an odd number of alternatives are preferable, assuming that a neutral positon makes sense
  • comprehensible instructions and labeling of response alternatives are crucial.
He also cited Cronbach that increasing the number of points can induce extreme responding, thus decreasing the validity.

Lozano, García-Cueto and Muñiz in "Effect of the number of response categories on the reliability and validity of rating scales" (2008) found that reliabilty and construct validity improved with more points, but only up to 7 points.

These sources seem to indicate that 5 to 7 point formats are the best, and whether you prefer 6 or prefer 7, depends on whether you find a midpoint useful or not.
 
Last edited: