Likert scale & surveys – best practices
November 20, 2007
I’ve been looking into the best practices for using the Likert scale type of question, probably the most widely used response scale featured in surveys – often used to measure attitudes and other factors (e.g. “Excellent” to “Poor”). Created by Rensis Likert (pictured above) in the 1930s, his original scale featured five points. Over time, there has been many discussions and disagreements focused on one central question: What works best with the Likert scale to give you the most accurate responses?
I have read a number of studies on this question (sorry, I don’t link to them as they are all books or academic journals (that require a fee) but if you are interested write to me and I’ll give you the references) and the following are the points that most (but not all) scholars agree on:
More than seven points on a scale are too much. Studies show that people are not able to place their point of view on a scale greater than seven. So go for seven or less. What is the perfect number? Studies are not conclusive on this, most commonly mentioned are five, four or three point scales.
Numbered scales are difficult for people. For example, scales that are marked “1 to 5, with 5 being the highest” result in less accurate results than scales with labels such as “good” or “poor”. If numbered scales are used, signposts are recommended (e.g. put “poor” above 1, “satisfactory” above 3 and “excellent” above 5).
Labelled scales need to be as accurate as possible. Commonly uses labels such as “often” or “sometimes” often result in inaccurate responses. As these terms mean different notions of engagement from person to person, culture to culture (not to add the complexity of translating these terms). Scholars recommend using time-bound labels for frequency measures such as “once a week” (although problems of correct recall are also an issue). In addition, studies show that people find it difficult to differentiate between “very good” and “good” – better to use “good” and “excellent”.
And that’s it! Basically, there are inconclusive results on the use of a middle or neutral point (e.g. four point vs. a five point scale). Some scholars advocate a five point scale where respondents can have a “neutral” middle point whereas others prefer to “force” people to select a negative or positive position with a four point scale. In addition, the use of a “don’t know” option is inconclusive. I personally believe that a “don’t know” option is essential on some scales where people may simply not have an opinion. However, studies are inconclusive on if a “don’t know” option increases accuracy of responses.
Further information on the Likert Scale:
Examples of commonly-used Likert Scales >>
More examples of commonly-used Likert Scales >>
“Designing a useful Likert Scale” (pdf)>>
Glenn
Entry Filed under: Evaluation methodology, Evaluation tools (surveys, interviews..). .
71 Comments Add your own
Leave a Comment
Some HTML allowed:
<a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <pre> <del datetime=""> <em> <i> <q cite=""> <strike> <strong>
Trackback this post | Subscribe to the comments via RSS Feed
1.
Michael Blowers | November 20, 2007 at 9:01 am
Hi Glenn, this is really interesting and ties in with some reseach I have playing with over the years regarding the spotting of tone for media coverage. I have always defaulted to the accepted groupings of ‘positive’, ‘neutral’ and ‘negative’, but have always been slightly uneasy allocating a neutral rating to a media item which just mentions a company’s name – this must have a value? A post on my blog regarding this is at: http://mediaevaluation.blogspot.com/
All the best, Michael
2.
Glenn | November 20, 2007 at 9:17 am
Hi Michael, I see what you mean. After reading your post, it did make me think about the concept of neutral rating of a media item – actually it’s so commonly accepted that no one’s challenged it before! But it goes back to two points: is there ever really a neutral point on an issue and is the mere mention of a company in terms of visibility a “positive” result in itself?
Requires more thought…
Glenn
3. The magical number seven,&hellip | November 27, 2007 at 7:28 am
[...] an earlier post on best practices for likert scale questions, I made reference to an article “The Magical Number [...]
4.
anila bardai | December 3, 2007 at 5:22 am
please send article or formate of questionier on likert scale
5.
Glenn | December 3, 2007 at 7:53 am
Hello,
Please consult the links at the end of my post – clicking on these links will lead you to plenty of articles and examples of the likert scale.
Glenn
6. writing open-ended questi&hellip | December 11, 2007 at 7:23 am
[...] previously written about best practices for using likert scale questions in surveys, I’d like to say something in favour of using open-ended questions. An open-ended [...]
7. Likert scales, frequency &hellip | March 11, 2008 at 9:36 am
[...] “never”. etc. However, these scales often provide inaccurate responses as I’ve written about before. Why is that so? Well, describing frequency differs enormously from person to person. This [...]
8.
Elham | March 12, 2008 at 6:45 pm
please send more examples of three point scale and the adavantage & disadvantage of 3 or 5 or 7 scales
9.
dian | March 19, 2008 at 8:19 am
hi glen, in my thesis i use four point scales, could you tell me what is the name: “likert with four point scale”. .. i had read many books but so far i cant find the name yet. would you help me..
thank you.
10.
Glenn | March 20, 2008 at 1:51 pm
Hi Dian,
For a likert scale with four scales, there is no given name as far as I know. I’ve seen the likert scale vary from 2 to 10 points on a scale. But there is no particular name for for a four point likert scale – it’s a four point scale without a central point (an even number).
Glenn
p.s. Elham, for more examples of Likert scale, see the links at the end of my post above.
11.
Harry | March 23, 2008 at 1:49 am
Hi Glen,
The original scholars used 5 point likert scale but my boss proposed that I should use 7 point likert scale so that this appears consistent with other variables which I intend to measure. But at the moment still can’t find any back up for this. Do you have one?
Many thanks
Harry
12.
Zoe | March 29, 2008 at 5:26 pm
Your page on Likert scaling is very useful. I wonder if you have any information regarding Likert scaling for questions to be answered by primary aged children. I need some scales that they would understand. Thanks
13.
Glenn | March 31, 2008 at 7:25 pm
Hello Zoe,
That’s a good question. There are some studies that exist on using likert scales with children, notably the following one:
“Adaptation of Likert Scaling for Use with Children”.
Occupational Therapy Journal of Research, v5 n1 p59-69 Jan 1985
http://www.eric.ed.gov/ERICWebPortal/custom/portlets/recordDetails/detailmini.jsp?_nfpb=true&_&ERICExtSearch_SearchValue_0=EJ317880&ERICExtSearch_SearchType_0=no&accno=EJ317880
However, I have not read this study so I am not familiar with its recommendations.
From what I know, I would say likert scales for children should have a limited number of points on the scale (between 3 – 5) and use simple terms (good, bad, etc.) or graphics (smiley/sad faces) above each point. Numbered scales would work less well in my opinion and some studies recommend using a visual analogue scale (but not for children under 7). A visual analogue scale (used for health issues often) is where you ask the child to put a mark on a line with two end points (see this example, once you see it – all will be clear!:)
http://www.blackwellpublishing.com/specialarticles/jcn_10_706.pdf
And of course, it all depends on how much guidance you give a child – I guess in most cases you need to guide a young child through the questions.
I hope this information is of use,
Kind regards,
Glenn
14.
dian | April 4, 2008 at 9:00 am
hi Glen.
thanks a lot for your answer, it’s very helping me.
I have another problem, i’m sure that you will help me again. I face some trouble with making questioner used likert scale answer. My questions in the questioner bias with yes/no questions although i had try hard to make statements but the result are still similar with yes/no questions.
Could you give some tips for changing question into statement in questioner with ikert scale measurement?
thank you very much.
15.
Allen | April 11, 2008 at 11:17 pm
http://ourworld.compuserve.com/homepages/jsuebersax/likert.htm
A good article by Dr. Uebersax about the confusion around the concept of a “Likert scale”.
Have a nice day,
Allen
16.
Glenn | April 13, 2008 at 1:01 pm
Thank you for that Allen. It does look an interesting article with some important points – I will make reference to it in a future post.
Kind regards
Glenn
17.
Glenn | April 13, 2008 at 1:02 pm
HI Dian,
That’s a good one also! let me think about that I’ll get back to you…
Glenn
18.
Glenn | April 13, 2008 at 1:26 pm
Dian, further to your question, actually some questions are more suited to a yes/no response and others are more suited to a Likert scale. For example, “have you ever done XY?” is suitable for yes/no. but “how favourable are you for XY?” is more suitable for likert style format. The likert scale is more for where you can imagine responses on a scale of frequency/intensity. For some questions this may not be appropriate.
I think if you are working with questioners doing the surveying for you, then you just have to guide them further with the response model written on your survey.
Glenn
19.
Glenn | April 13, 2008 at 1:37 pm
Dear Harry,
Apologies, I just saw your comment now. Actually most studies are not conclusive on the difference between 5 and 7 points on a scale. In other words, both 5 & 7 point would provide you with accurate and reliable responses. In the article listed below, they conclude that as you add more points, a scale becomes more reliable – but only up to a certain point (higher than 11 is too much for most people). Consequently, they argue that 7 is slightly more reliable than 5.
I would recommend that you use a 7 point scale, particularly if you have other comparative variables that you are going to measure on a 7 point scale – it makes it much easier to compare and avoids having to re-calculate your results.
The article I mentioned:
Alwin, D & Krosnick, J, “The reliability of survey attitude measurement: The influence of questions and respondent attributes”, Sociological Methods Research, 1991; 20; 139
http://smr.sagepub.com/cgi/content/abstract/20/1/139
Kind regards,
Glenn
20.
Kisha | May 19, 2008 at 8:56 pm
I am completing my dissertation. I was told I would have better success if I found a survey comprable to the one I am attempting to create. Does anyone know of a site that provides a listing of various Likert scale surveys?
21.
Glenn | May 20, 2008 at 1:13 pm
Hello Kisha,
I am not sure you will be able to find a survey that precisely matches the one of your dissertation, but you can certainly check the scales you use with scales used by others:
http://www.gifted.uconn.edu/siegle/research/Instrument%20Reliability%20and%20Validity/Likert.html
http://dataguru.org/ref/survey/responseoptions.asp
Glenn
22.
rachana | May 30, 2008 at 5:36 am
Hi ,your article help me a lot in my market research first step. i need your immediate help for my research.i want to learn all the interpretation of factor and cluster analysis.this is my humble request to you.and i hope you will definitely help me.
Thanks.
23.
Ruby | June 6, 2008 at 12:00 pm
Could you please help me out with the advantages of using a four point likert scale as opposed to using the five point one.
24.
donny | June 28, 2008 at 9:47 am
hi glenn,i’m doing my final assignment now about service quality in a retail store. i’m little bit confuse about using likert scale. I’m confuse whether to use 5 or 7 Likert scale.
Can you mention some advantages and disadvantages of both 5 and 7 likert scale?
thx before..
25.
John Dawes | June 30, 2008 at 7:10 am
I recently published a study that used a ’split sample’ experiment to see if the number of scale points has any effect on survey data. I split respondents into three groups, one answered using a 5-point scale, another group used a 7-point scale and the third, answered using a 10-point scale. I “re-scaled” the data using a simple bit of arithmetic, and the three scales produced almost identical results in terms of mean scores and variation about the mean. If anyone would like to look at a draft copy of the study, and does not have access to the journal, you can email me. Otherwise, the reference is Dawes, John. “Do Data Characteristics Change According to the Number of Scale Points Used ?” International Journal of Market Research Vol 50, No.1, 2008.
26.
Glenn | June 30, 2008 at 8:31 am
Many thanks for those comments John & Donny. From what I’ve read, studies show there is little difference in reliability in using 5 or 7 point scales – studies on the whole tend to favour 5 over 7 – but not all agree. Most agree that more than 7 point scales are difficult for respondents to handle. Personally, I use 5 point scales often in surveys as I find 3 points too little and 7 points too many.
Glenn
27.
Asante bright Owusu | July 14, 2008 at 3:34 pm
could U please send me more examples of the allpication of the likert scale ?, I am on my Mpil thesis and I would like to use it to achieve one of my objectives.
thank you
28.
Naveen | July 21, 2008 at 4:51 pm
Dear Glenn,
Thanks a lot for your time and kind information on measuremnts. I have a doubt too. My present research questionnaire is on the the following
1.Existing woring conditions of employees in XXX Spinning Mill – Satisfactory or Unsatisfactory.
2.Positive or negative change in lives of employees after employment in the Spinning Industry.
My research covers both those questions and I plan to use questionnaires. My doubt is can I ask questions regarding both those areas in one questionnaire with the first half having Yes/No Questions and the second half having Linkert Scale.
If my questionnaire uses both the scales, i.e. Yes/No Questions and Linkert Scale, will I still be able to do analysis such as Chi-Square etc.
Thanks a lot in advance.
29.
Glenn | July 23, 2008 at 6:40 am
Hello Asante,
The following websites have many examples:
http://www.gifted.uconn.edu/siegle/research/Instrument%20Reliability%20and%20Validity/Likert.html
http://dataguru.org/ref/survey/responseoptions.asp
Glenn
30.
Glenn | July 23, 2008 at 6:56 am
Dear Naveen,
The use of different types of scales in surveys is recommended (such as likert scale and yes/no – a binary scale).This use of both scales shouldn’t be a problem to undertake such analysis as Chi-square.
Glenn
31.
ong | July 27, 2008 at 6:54 am
Dear Glenn,
I am in the process of writing my chapter 3 thesis, I don’t how to write why I will used 5 point Likert scale. my study is regarding the student and teacher perception on the effectivenss of clinical teaching. could kindly give some suggestion TQ
Ong
32.
Gillian | May 2, 2009 at 8:53 pm
I am interested in the references used for this Likert article.
Thank you in advance!
Gillian
33.
Glenn | July 30, 2008 at 8:32 pm
Dear Ong,
Simply put, although still debated, studies show that scales of 5 -7 are the most accurate (as compared to smaller or larger scales). You can read more in this article:
Alwin, D & Krosnick, J, “The reliability of survey attitude measurement: The influence of questions and respondent attributes”, Sociological Methods Research, 1991; 20; 139
http://smr.sagepub.com/cgi/content/abstract/20/1/139
kind regards
Glenn
34. Cultural issues in evalua&hellip | August 1, 2008 at 3:36 pm
[...] and usefulness of the evaluation and to be careful in the use of questionnaire types (such as the Likert scale) which may be misunderstood in some [...]
35.
lina | August 4, 2008 at 10:29 am
Dear Glenn
Your article and responses were very informative. Could you kindly clarify a doubt i have. I am doing a comparitive case study using questionnaire that has likert scale questions. How could i analyze the likert scale questions.
Another doubt is regarding sampling- could i generalize a dispropotionate stratified sampling to the population? What is weight?
I would be much grateful if you could answer my questions.
Leena
36.
musonge mpah | September 2, 2008 at 11:16 am
please i need to know the importance of linkert,and guthman scales used in research methods
37.
Aziz | September 12, 2008 at 9:03 am
From a marketing perspective, is there any literature to suggest the benefit of a 5 point as opposed to a 4 point scale. The assumption I have is that if you’d like to win over a group, it will be those in neutral that are more likely to be won over. Do you have any study to back this assumption?
38.
Glenn | September 18, 2008 at 2:34 pm
Dear Aziz, I have not read anything that supports the argument that you put forward – there is a difference of opinion as to whether 4 point or a 5 point scale works better.
Glenn
39.
Glenn | September 18, 2008 at 2:36 pm
Dear Musonge, please see above for information on the Likert scale. A quick search on the web will bring up many resources and explanations about the Guthman scale.
Glenn
40.
Glenn | September 18, 2008 at 2:39 pm
Dear Leena,
Apologies, I somehow missed seeing your comment on my blog.
To compare Likert scales are very easy – but they must be “comparable” – for example using the same scale, e.g. poor, good, excellent. etc. If not it is difficult to compare. For the weighting, I’m really not the right person to ask – sorry!
Glenn
41.
Stuart | September 23, 2008 at 2:07 am
Can you comment on using a mixture of 5pt and 7pt scales in the same survey? Any concerns…
Thanks
42.
Glenn | September 23, 2008 at 12:48 pm
Dear Stuart, the main issue with using 5 and 7pt scales is if the questions using these scales need to be compared. If they don’t then it’s not a problem. If they do it is possible but more of a hassle as you have to make some calculations to make them comparable and it doesn’t allow to make a quick comparison. I would generally recommend using the same number of points in a survey (but not necessarily the same response options) – although that’s sometimes not possible.
Glenn
43.
Preeya | October 7, 2008 at 10:08 am
Hi Glen,
You’ve said above, ‘However, studies are inconclusive on if a “don’t know” option increases accuracy of responses.’
Can you please provide me with some references I can look up to investigate this further?
many thanks
44.
Glenn | October 9, 2008 at 1:28 pm
Hello Preeya,
This is discussed in the following article:
1) Alwin, D & Krosnick, J, “The reliability of survey attitude measurement: The influence of questions and respondent attributes”, Sociological Methods Research, 1991; 20; 139
http://smr.sagepub.com/cgi/content/abstract/20/1/139
45.
Toyin Taiwo | October 21, 2008 at 6:57 am
I am writing up my thesis and my supervisor requested I state the reason for using a 4-Likert scale. I find the article and comments posted here very useful and educative.
46. Survey responses - do the&hellip | November 4, 2008 at 3:02 pm
[...] written before about survey respones and the use of “don’t know” as an option on a Likert scale. [...]
47.
ambrina | November 12, 2008 at 9:11 pm
Hi thanks fot the very helpful information, if possible could you please give me references. Thanks again
Ambrina -x-
48.
Glenn | November 13, 2008 at 9:27 am
Thank you Ambrina, I’ve just sent them to you.
Glenn
49.
arnie manlapas | December 3, 2008 at 1:24 am
i would want to know your references for all the information you have cited above. i’ll be needing them for my thesis. if you got more about Thurstone Scaling. please send me the list of references or i would appreciate more if you could send me copies of research journal articles about them. thanks
50.
Joan | December 4, 2008 at 4:02 am
Could you pls give me the references about the Likert scale for all the information that you’ve cited above?
Thanks for sharing the valuable information.
51.
Glenn | December 4, 2008 at 9:08 pm
Thank you Joan & Arnie, I’ve sent you the references.
Glenn
52.
Michelle | January 23, 2009 at 3:01 pm
This is very useful information! Many thanks! It’s possible you could send me the references as well? I need them for my thesis…
Michelle
53.
Dan B | January 27, 2009 at 4:02 pm
Hi Glenn,
thank you for a very informative and useful piece. I just wondered if you had ever found any information or knew anything regarding the order of the scale – should the scale be positive to negative left to right or the reverse? Is there any evidence advocating the use of one approach over the other? Anybody?
Thanks,
Dan B
54.
Glenn | February 2, 2009 at 7:51 pm
thanks Michelle, I’ve sent them to your email.
Hi Dan, That’s a question I’ve often asked myself – but I can’t find any *hard* academic reference on it (although I do remember reading something somewhere supporting negative to postive (left to right) but I can’t recall where it was).
I’ve written about this earlier to another reader, I quote:
“I believe it’s better to go from the negative to the positive, left to right. It seems more logic to me and some automated survey software mark your answers and calculate the responses for graphs on this basis, e.g. that the first point is the lowest. But I’ve had clients argue that it should be the opposite way around – put positive to negative, left to right – as people will click on the first point by default – which I personally don’t believe. I’ve never found any academic reference supporting either way but looking at all examples in academic articles, 95% are written as negative to positive, left to right.”
55.
Shynnette | February 3, 2009 at 7:15 am
Hi Glenn
I am doing a research and my adviser told me to use Likert scal but I don’t know how to analyze the data using the scale. it’s about effectiveness. hope you can help give directions to my study. thanks in advance.
56.
jewel | March 10, 2009 at 12:47 am
i’m working on my thesis and i have to compare data from 3 point and 6 point likert type scales. it was suggested that i recode the 6 point to 3 point does anyone have any idea of how to do this and what research supports this? thanks
57.
Glenn | March 11, 2009 at 8:14 am
Hello Jewel, That doesn’t sound very difficult as all you have to do is halve the data of the 6 point (e.g. 6 becomes 3, 5 becomes 2.5 ,etc). Only issue will be that you will have half points that would not exist in a three point scale – putting in question the comparable nature of the data. You may want to ask a statistics expert their opinion.
58.
David McBride | March 14, 2009 at 11:25 pm
Hi Glenn, great site, I happened upon it when looking at research methods for my MBA dissertation. Intuitively I wanted to use a six point scale to force people to adopt a position, even if that is a mild one. My theory is that everyone has an unspoken opinion, however mild on matters of importance to them. The uncomfortable feeling of having to make a positive or negative statement makes people consider their responses more carefully. The advantage of having a central starting point of 0 with +VE and -VE values is considerable. Social desirabilty bias must also be factored in as individuals are influenced by the desired norms of their social, cultural and political groupings.
Your blog seems to focus on 5, 7 or even 3 point scales but 4 and in my view a 6 point scale is worth a look.
Is there any good academic literature that you can point me to?
Thanks for the great website
59.
Glenn | March 18, 2009 at 1:25 pm
Hi David, thanks for the compliments. As you state I favour more the 3 or 5 point approach in order to produce a middle point. But as you propose – to select an even number – 6 – to force people to adopt an opinion – is another point of view on the subject of attitudes and scales. There are some, like myself that believe that people simply may not have an opinion on certain issues and shouldn’t be forced to choose. Yet there are others that argue that people do have *hidden* opinions on everything..
This is probably the best academic article I’ve read to date which sums up these issues and will lead you to other resources in this area:
Alwin, D & Krosnick, J, “The reliability of survey attitude measurement: The influence of questions and respondent attributes”, Sociological Methods Research, 1991; 20; 139
http://smr.sagepub.com/cgi/content/abstract/20/1/139
Glenn
60.
Steve | April 7, 2009 at 10:22 pm
Hi Glenn, i am looking at the weaknesses of using a 5 point likert scale in a school survey. Basically, i need as much info against likert scales as possible! Also, any references you could could provide would be great!
Thanks
Steve
61.
bilal | April 13, 2009 at 10:14 am
Hi Glenn, i am working on my MS thesis using a survey. I have used five point likert scale. Now i am confused how to treat the data. it will be treated as Ordinal or interval. As different people have different opinions in this regard. If you can please guide me or give me any refrence it will be very helpful for me.
Thanks
Bilal
62.
genevacom | April 15, 2009 at 7:18 am
HI Steve, That’s a good question, the main disadvantage of the Likert scale is matching the points of the scale to the feelings of the people responding – the problem is that people sometimes are not able to accurately place their sentiments on a scale at a particular point. But then again, a scale is better than a simple yes/no (you have more choice).
63.
Glenn | April 16, 2009 at 6:47 pm
Hi Bilal,
That really depends upon what is in your scales – as they can be either interval OR ordinal.
Ordinal scales are where the order matters but not the difference between values. Typically scales of satisfaction, preference or agreement. For example, you might ask people to rate their level of happiness on a scale of 1 to 10. A score of 7 means more happiness than a score of 5, and that is more than a score of 3. But the difference between the 7 and the 5 may not be the same as that between 5 and 3. The values simply express an order.
Interval scales are where the order matters but the difference is meaningful in “real terms”. Typically scales of salary, temperature or age. Here if someone is paid $50,000 and someone $45,000, that’s a “real” difference of $5000.
So how you analyse the data and what techniques you use depends upon the above differences.
Glenn
64. Lickertskalor och dataniv&hellip | May 6, 2009 at 12:37 pm
[...] bra och seriös bloggpost finns på Likert scale & surveys – best practices Vi har stöd i vårt resonemang om att mer än 7 är för mycket, att det är svårt med siffror [...]
65.
Mark | May 12, 2009 at 9:47 am
Glenn
I would also appreciate a list of references.
Thanks
Mark
66.
Glenn | May 12, 2009 at 5:51 pm
Thank you Gillian and Mark, I have sent you the references.
Glenn
67. Daily Links « Jason&hellip | May 15, 2009 at 3:03 am
[...] Likert scale & surveys – best practices From intelligent measurment blog [...]
68.
ida damayanti | May 27, 2009 at 5:05 am
Hi
I need to finish my magister psycology research on student career choices of Holland hexagon personality theory. I faind verry difficult to make an item instrument in Likert Scale. I would be appreciate if you could help me to send an coppy of that item pleasse.
cheers
Ida
69.
ida damayanti | May 27, 2009 at 5:20 am
hi
I need to finish my magister psychology research on student career choice. I need to make an item instrumen of Likert scale to do this research. I would be apreciate if you could help me to do this please
cheers
ida
70.
Sam | July 10, 2009 at 1:28 am
Hi Glenn
I am developing a questionnaire for children in hospital and is planning to use Likert scale. I read in this site that for children, the number of anchoring points should be limited. Can you direct me to a reference to support this view?
Thanks. Sam
71.
mona | July 15, 2009 at 1:09 am
Dear Glenn,
I would like to ask if you know any Likert Scale regarding Sexual Behavior of Adolescents?