A novel method for joint modeling of survival data and count data for both simple randomized and cluster randomized data

摘要

The objective of this study was to develop an improved analytical solution for analyzing data with correlated survival and count responses for two common designs of simple randomized and cluster randomized data. The proposed joint model was used for analyzing data from a randomized control trial on Epilepsy where the two responses were the timing of seizures and count of seizures. It was identified that the use of the proposed joint model provides better analysis of the data in terms of identifying and quantifying the risk factors for each response variable and predicting the length time without seizures for the Epilepsy patients.