Hi fellows,
I am working on a design of survey about job loss and EI. I intend to use the already available scales for Risk propensity by Meertens and Lion’s (2008) and "Fear of failure" with 5-item scale developed by Conroy, Willow, and Metzler (2002).
In social settings of Pakistan, India etc. I feel that instead of 7 point scale, its better to use 5-point scales to make things simpler and easier for the respondents. What is your experience and opinion about it?
Secondly I guess we need to use consistent scales for both like if one measurement uses 5-point scale the other should also be 5-points scale. Need your experience and opinion about that also.
Thanks.
Hi Shahzad Hanif,
to use five or seven points Likert scale, Hair et al. (2011) recommend to observe the formal eductaion levels of the respondents. If you have to much respondents with few years in schools, you have to use five points (for childrens and olders peoples - use three points) and if you have to much repondents with many years in formal school, you shoud use seven points (for universitary people use eleven points - from zero to ten scores, like the school system of notes).
How much more points do you use, also more variability do you have, but more levels or points can to confuse the respondents. More variability in the answers are desired becose we increase the precision of statistics tests.
Best regards
Dirceu
Hair Jr, J.F., Wolfinbarger, M., Money, A.H., Samouel, S., & Page, M.J. (2011). Essentials of Business Research Methods. 2 ed. edition. New York: Routledge.
Dear Shahzad,
I agree with Dirceu, to choose between 5 or 7 points to use, you need analyze the respondents features.
But I prefer more points in the scale to avoid some common effects in scales with few points. Reading sugestion:
Hartley, J. (2014). Some thoughts on Likert-type scales. International Journal of Clinical and Health Psychology, 14(1), 83-86.
- Badges
- Science method
- Similar topics
- Mathematical Sciences
- Statistics
- Applied Statistics
- Survey Design