Hii, I am planning to do a cross-sectional survey study to find out supplement prevalence among Sri Lankan university athletes. During the literature survey, I found that similar studies have not done focusing on university athletes but have done focusing on national level athletes.
01. Could I able to consider national level athlete based study as a similar one for my study? because the same objective has achieved from both studies.
02. If the supplement prevalence rate of past study is 75%, what is my P-value in the equation of
n = ZP(1-P)/d2
P 0.75 & 1-P 0.25.
In my opinion, if you don't want to use prevalence reported in national study, then you can use 50%.
Good luck.
Hi Nimesha
Sample size for prevalence surveys depends upon the degre of accuracy you would like to obtain, the %confidence you would like for the results, the expected prevalence, and the size of the target population. If the expected prevalence is unknown, then 50% is used as the largest sample size estimate is at this point, getting smaller as you move away from 50%.
For example, suppose there were 2000 university athletes, you expected 50% of them to take supplements, and you wanted the prevalence estimate to be accurate to +/- 5% with 95% confidence, then you would need to obtain 323 completed questionnaires. If the expected prevalence was 75%, then you would only need 252 completed questionnaires.
Here is a good online site for doing the calculations yourself:
https://www.abs.gov.au/websitedbs/D3310114.nsf/home/Sample+Size+Calculator
- Badges
- Science topic
- Similar topics
- Higher Education
- Universities