Confidence intervals for the difference between two median survival times for clustered survival data

ABSTRACT

Clustered survival data arise often in clinical trial design, where the correlated subunits from the same cluster are randomized to different treatment groups. Under such design, we consider the problem of constructing confidence interval for the difference of two median survival time given the covariates. We use Cox gamma frailty model to account for the within-cluster correlation. Based on the conditional confidence intervals, we can identify the possible range of covariates over which the two groups would provide different median survival times. The associated coverage probability and the expected length of the proposed interval are investigated via a simulation study. The implementation of the confidence intervals is illustrated using a real data set.

KEYWORDS:

• Clustered survival data
• confidence interval
• Cox gamma frailty model
• median survival time
• within-cluster correlation

Additional information

Funding

This work was supported by the Ministry of Science and Technology of Taiwan under Grant MOST 103-2118-M-029-004.