This simulated dataset is to illustrate how to use sace to estimate the SACE, and compare it with other naive methods. In this simulated data, by design, there is confounding between Z and Y caused by X, and confounding between S and Y caused by X.
A data frame with 5000 observations and 7 variables. Z, A, Y, S are 1-dimensional, and X is 3-dimensional. The variables are as follows:
Binary treatment
A factor covariate with 2 levels (1 and -1)
A continuous covariate
A contunuous covariate
The substitution variable which is continuous
The continuous outcome. NA where \(S = 0\)
The survival indicator. 1 means survival and 0 means death.
Linbo Wang, Xiao-Hua Zhou, Thomas S. Richardson; Identification and estimation of causal effects with outcomes truncated by death, Biometrika, Volume 104, Issue 3, 1 September 2017, Pages 597-612, https://doi.org/10.1093/biomet/asx034