Leni Novita wrote:

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.

Morning Leni,

There are may views on this but to answer your questions. And there are always exceptions to every rule!!

1) I usually always include a neutral point because the reality is that sometimes thats how people think and thats we want to capture, reality. Its also a type of 'opt out' and 'NA' option that doesnt give missing data. 

That said sometimes we do want to force a choice, but rarely - in which case we dont have the neutral point.

2) Generally 5 is the minimum. Some people use up to 11. For the general public 5 is usually sufficient, anything else starts adding in sampling error i.e. if you asked them to rerate in a week even if nothing has changed there would be differences in responses. However experts being asked their expert opinion can handle a bit more than 5 consistently.  You might sneak in 2 extra and have 7 and get away with it, this is also related to research suggesting 7 is about the max number of categories people can hold in memory at any 1 time, and is why Best/Worst (aka Max Diff) is recomended when ranking more thas 7 things since people tend to estimate the middle ranks with a lot of noise once you get over 7. 

No matter how many you use try to anchor all points with text i.e. dont just anchor the ends. The exception to this rule might be if you have 11 and then you might have a gap between anchors, but if you do this expect fewer people to use those categories.