Rsurrogate

Rsurrogate is an R package that provides functions to estimate the proportion of treatment effect on the primary outcome that is explained by the treatment effect on the surrogate marker.

More details on the method are available in:

• Parast L, McDermott M, and Tian L (2016). Robust Estimation of the Proportion of Treatment Effect Explained by Surrogate Marker Information. Statistics in Medicine, 35(10): 1637-1653. doi:10.1002/sim.6820.
• Parast L, Cai T and Tian L (2017). Evaluating Surrogate Marker Information using Censored Data. Statistics in Medicine, 36(11): 1767-1782. doi:10.1002/sim.7220
• Parast L, Cai T, Tian L (2021). Evaluating Multiple Surrogate Markers Using Censored Data. Biometrics, 77(4): 1315-1327. doi:10.1111/biom.13370
• Parast L, Garcia TP, Prentice RL, Carroll RJ (2022). Robust Methods to Correct for Measurement Error when Evaluating a Surrogate Marker. doi:10.1111/biom.13386

A full written tutorial is available in Parast L (2025). Surrogate Marker Evaluation: A Tutorial Using R. Statistics in Medicine, 44(10-12):e70048. 10.1002/sim.70048 with a follow-up along R markdown available here, and the knitted html here. The Parast (2025) tutorial paper is available in this respository, it is called Parast2025_Tutorial.pdf.

This package also contains a function for surrogate selection proposed in Parast, Freestone, and Tarr (2026). Treatment-Aware Regularization via Multi-Objective Optimization for Surrogate Selection. A tutorial for the function implementing the methods in this paper, as well as code and instructions to reproduce the simulations results in the paper are available at https://github.com/laylaparast/TAR.