I am planning a study which involves 7 hospitals. three hospitals used A for the treatment of a disease; and the remaining four hospitals used B. The aim of the study is to investigate the different efficacy of A and B. The outcome is the occurrence of outcome event E.
Exposure A and B are clustered within hospitals and the sample size calculation may be influenced by this. Can you tell me is there any reference or materials discussing this issue? ideally, Can I make such calculations in R?
Hi,
please check publication below:
https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4521133/
I hope this helps,
Nikos
https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4521133/
@Nikolaos Pandis, Thank you for your reply, but that is a cluster RCT. in our design it is an observational study that preclude the use of randomization procedure. is there any difference in sample size and power calculation between this two designs?
Maybe you can use the epi.clustersize from the epiR package assuming an expected incidence of E in your cohorts
Hence, in a two-stage cluster design analitic study, assuming an estimate prevalence to be 0.20 and we expect rho to be in the order of 0.02.
We want to take sufficient samples to be 95% certain that our estimate of prevalence is within 5% of the true population value (that is, a relative error of 0.05 / 0.20 = 0.25).
Assuming 20 responses from each cluster, how many clusters do we need to be sample?
epi.clustersize(p = 0.20, b = 20, rho = 0.02, epsilon.r = 0.25,conf.level = 0.95)
A. We need to sample 18 clusters (360 samples in total).
Hopes this help, best, S
- Badges
- Science topic
- Similar topics
- Mathematics
- Statistics
- Sampling Design
- Sample Size