Can a researcher get higher than the desired sample size in one arm of the study?
Example if the sample size is 60 patients (30 in each arm) and one assumes 30% loss to follow up with a total of 78 patients and at the end of the study more patients in the intervention group (31 instead of 30) completed the study, is that scenario acceptable?
Why not, a smaller sample size at the end would be a problem, not a larger one. In this case your power will be higher than that calculated for 60 patients, which is a good thing.
Hello doctor...
In addition to Eliana ,,,
Non-Response Adjustment Formula ( q ) :
Used to increase ↑ the sample size to compensate for the persons (in the study sample) who died , refused to continue..
usually considering 10% possible non-response rate.
My ref. : An Epidemiologic Approach to Reproductive Health
Thank you for answers
Eliana Ibrahimi is there any reference for your answer?
No specific reference! Just some knowledge from the clinical trials courses I took during my studies in biostatistics. You can find a lot of references on this topic online.
Best,
To me this sounds like there is a coding error. If you have 30 from the beginning and end up with 31, check your data coding.
- Badges
- Science topic
- Similar topics
- Mathematics
- Statistics
- Sampling Design
- Sample Size