I calculated my sample size for a case-control matched study to be 186 (93 pairs). Anticipating a 10% loss to follow-up or missing data, I needed 206 participants. I ended up conducting the study with 200 participants since those were the only eligible, but did not have any loss to follow up or missing data after 6 months of follow up. What justification can I give to using 200 participants instead of the calculated 206
There is no problem with having a sample that is larger than your original calculated size, because that amounts to the minimum size that you would need in order to achieve a given level of power or a desired size for you standard error. If your sample is larger than the minimum, it will improve your power and reduce your standard error.
There's always a chance that the error is minimized, this might not always be the case,
You can justify using 200 instead of calculated 206 by repetition of the conducted experiment and determining that the results obtained previously are very close to that obtained recently,
After having conducted the experiment sufficiently large number of times, the limits can be calculated and it can be affirmed that 200 participants were sufficient for the study.
Although, theoretically the next times when you perform the same, the results must deviate.
- Badges
- Science topic
- Similar topics
- Mathematics
- Statistics
- Sampling Design
- Sample Size