How can i calculate sample size for a median survival of 5 months & 95%Ci (4.8-5.1) as revealed from the pilot study?
Many thanks DR, Rayah
My planned study is a longitudinal one comprising one group & the pilot revealed the duration of survival is non-parametric in distribution. I needs a program to calculate sample size using median survival & its 95%CI
Thank you once again
Are you sure?. You just want to report survival of a group and not even comparing between different levels of a variable. If so, there is no need for sample size estimation. The survival duration depends upon the "event" and in most of the time it is skewed.
Many thanks Dr. Kandasamy
The main outcome of interest id the overall survival. Certainly we will compare survival between different levels of many confounders, but there is no primary confounder of interest.
You can use R code to calculate sample size of Cox proportional hazards regression with two covariates for Epidemiological Studies.
install.packages(" powerSurvEpi ")
ssizeEpi.default(power, theta, p, psi, rho2, alpha = 0.05)
power: postulated power.
theta: postulated hazard ratio.
p: proportion of subjects taking value one for the covariate of interest.
psi: proportion of subjects died of the disease of interest.
rho2: square of the correlation between the covariate of interest and the other covariate.
alpha: type I error rate.
- Badges
- Science method
- Similar topics
- Mathematics
- Statistics
- Statistical Techniques
- Meta-Analysis