Survival Analysis of Time Varying Coefficients Using a Tree-Based Approach
Bootstrap to Correct for Over-optimism due to Adaptive Splitting
Function to Grow the Tree Using the Score Statistic
Finding the Final Tree using the Elbow Method
Finding the Final Tree After Bootstrap
Beta coefficient estimate at each time point
Function to Find the First Cutpoint and its P Value
Summary of coxph.tree output
Plotting of Full Tree and Subtrees
Function to Prune Using the Score Statistic
Estimates time varying regression effects under Cox type models in survival data using classification and regression tree. The codes in this package were originally written in S-Plus for the paper "Survival Analysis with Time-Varying Regression Effects Using a Tree-Based Approach," by Xu, R. and Adak, S. (2002) <doi:10.1111/j.0006-341X.2002.00305.x>, Biometrics, 58: 305-315. Development of this package was supported by NIH grants AG053983 and AG057707, and by the UCSD Altman Translational Research Institute, NIH grant UL1TR001442. The content is solely the responsibility of the authors and does not necessarily represent the official views of the NIH. The example data are from the Honolulu Heart Program/Honolulu Asia Aging Study (HHP/HAAS).