hi, if we are doing a single centered study, can we estimate/calculate sample size based on patients in that hospital?
e.g i want to conduct a research on stroke patients. so my population will be stroke patients in the country or stroke patients in that hospital ?
offcourse if we want to generalize the results, we take whole countrys stroke patients available in literature.
but lets suppose due to lack of time, or economic factors, we want to do single centered study where stroke patients may not be that high ? then how to justify sample size ?
i have seen many papers where sample size in hospitals was 100, 150, 90 etc. but they never mention how did they calculate this. can anyone share some evidence based answer ?
thank you
Sample Size Rule
Sekaran (2013) wrote:
"Roscoe (1975) proposes the following rules of thumb for determining sample size:
1. Sample sizes larger than 30 and less than 500 are appropriate for most research.
2. Where samples are to be broken into sub-samples;(male/females, juniors/seniors, etc.), a minimum sample size of 30 for each category is necessary.
3. In multivariate research (including multiple regression analyses),the sample size should be several times (preferably 10 times or more) as large as the number of variables in the study.
4. For simple experimental research with tight experimental controls (matched pairs, etc.), successful research is possible with samples as small as 10 to 20 in size."
Reference
Sekaran, U., 2003. Research methods for business: A skill building approach. John Wiley & Sons.
Sample Size Rule
Sekaran (2013) wrote:
"Roscoe (1975) proposes the following rules of thumb for determining sample size:
1. Sample sizes larger than 30 and less than 500 are appropriate for most research.
2. Where samples are to be broken into sub-samples;(male/females, juniors/seniors, etc.), a minimum sample size of 30 for each category is necessary.
3. In multivariate research (including multiple regression analyses),the sample size should be several times (preferably 10 times or more) as large as the number of variables in the study.
4. For simple experimental research with tight experimental controls (matched pairs, etc.), successful research is possible with samples as small as 10 to 20 in size."
Reference
Sekaran, U., 2003. Research methods for business: A skill building approach. John Wiley & Sons.
One of the more practical ways I've seen people do sample size calculations based upon number of patients and time available is by using Binomial probabilities. look at the literature and see how many folks you think will change based upon whatever cutoff you assign. Then see Excel to run binomial probabilities. For example, if you have 10 people and you get 8 or more participants who improve, this is significant. Try this approach and see if this helps.
Generally (and ideally) would be to calculate the ideal sample size, this can be done with a free program called Gpower. It suggests that you calculate the sample size based on a pilot test (`a priori`, on a small sample) so the sample size can be estimated to obtain a good sample power (above 80%). For this, the program asks you to fill in some variables (statistical test (t-test for example), alpha value (0.05), effect size (which you can calculate using calculators available online). In the end, the program provides the ideal size of your sample for a sample power 0.8 or more (which is ideal). Or you can estimate with post hoc test, your ideal sample size.
Attached, this is a lecture that we talked about Gpower, you can also find videos on youtube, exemplifying the detailed use of the software.
I am with Alice Câmara . Gpower will be one of the appropriate and professional software for estimating your patient pool. After all, when you decide to publish your research article, you can easily address the comments on calculating sample size risen from the reviewers. All best luck!
- Badges
- Science topic
- Similar topics
- Mathematics
- Statistics
- Sampling Design
- Sample Size