I am planning a cross-over design study (RCT) on effect of a certain supplement/medicine on post-exercise muscle pain. There hasn't been any similar study to recent date on the effect of this medicine (or similar medicines) on post-exercise muscle pain. However, some studies have been conducted for effect of this medicine on certain conditions such as hypertension.
As long as I have been searching formulas for estimating sample size, they need information (such as standard deviation, mean, effect size, etc.) from some similar kind of studies which was conducted before.
Is there anyway to estimate a sample size for my RCT with the aforementioned conditions?
Dear Mohammad
It is always difficult when there is no previous research. I would choose to make a power calculation based on study/studies which most resembles the one you want to conduct. Power calculations are based on the outcome, and if the outcome is pain then the calculation should NOT be based on hypertension as the outcome. I would find studies which have applied other medicine/interventions for lowering post exercise muscle pain, preferably with the same measure. If there are no studies at all on supplements/medicine (which I would think is highly unlikely) then I guess the calculation could be based on some other intervention for lowering pain. The calculation then becomes less meaningful, but at least you have some indication of the sample size.
Hope this was helpful.
For a power calculation you design a study to detect an effect size that you would like to be able to detect (sometimes termed the smallest effect size of interest or SESOI) not the effect you think exists. So the question becomes what would be a meaningful change in pain on the scale/measure you are using (probably in terms of clinical benefit). That gives you the mean difference you are looking for. Then you can look at other studies that have used the same outcome measure in a simple population to the one you are sampling and look at the typical ranges of SDs. That suggests a range of standardised mean differences that you can then look at. (Best to consider ranges of plausible values as SD in particular is not precisely measured in most studies). After that factor in things like likely drop-out or the impact of covariates (e.g., collinearity).
You may sample randomly, even though you have to take a number like 10,but maybe this is more related to plants and not animal cells. You may still do for animal cells. I do have my doubts it is for this kind of experiment
There are sites that calculate the sample size for a community that you can search for with the help of Google
This is a good application of sequential blinded sample size re-estimation. After a small number (say 5), estimate the variance and estimate the sample size. This estimate may not be too good but it is better than nothing. After another 5 observations, re-estimate the variance and re-estimate the sample size. If it is a blinded study, remain blinded as the analysis probably assumes equal variances.
- Badges
- Science topic
- Similar topics
- Mathematics
- Statistics
- Sampling Design
- Sample Size