Dataset from simulated regression survival model #2 as described in Dazard et al. (2015). Here, the regression function uses some informative predictors. The rest represent un-informative noisy covariates, which are not part of the design matrix. Survival time was generated from an exponential model with rate parameter λ (and mean frac{1}{λ}) according to a Cox-PH model with hazard exp(eta), where eta(.) is the regression function. Censoring indicator were generated from a uniform distribution on [0, 3]. In this synthetic example, all covariates are continuous, i.i.d. from a multivariate uniform distribution on [0, 1].
Dataset from simulated regression survival model #1b as described in Dazard et al. (2015). Here, the regression function uses all of the predictors, which are also part of the design matrix. In this example, the signal is limited to a box-shaped region R of the predictor space. Survival time was generated from an exponential model with rate parameter λ (and mean frac{1}{λ}) according to a Cox-PH model with hazard exp(eta), where eta(.) is the regression function. Censoring indicator were generated from a uniform distribution on [0, 3]. In this synthetic example, all covariates are continuous, i.i.d. from a multivariate uniform distribution on [0, 1].
Dataset from simulated regression survival model #1 as described in Dazard et al. (2015). Here, the regression function uses all of the predictors, which are also part of the design matrix. Survival time was generated from an exponential model with rate parameter λ (and mean frac{1}{λ}) according to a Cox-PH model with hazard exp(eta), where eta(.) is the regression function. Censoring indicator were generated from a uniform distribution on [0, 3]. In this synthetic example, all covariates are continuous, i.i.d. from a multivariate uniform distribution on [0, 1].
Dataset from simulated regression survival model #3 as described in Dazard et al. (2015). Here, the regression function does not include any of the predictors. This means that none of the covariates is informative (noisy), and are not part of the design matrix. Survival time was generated from an exponential model with rate parameter λ (and mean frac{1}{λ}) according to a Cox-PH model with hazard exp(eta), where eta(.) is the regression function. Censoring indicator were generated from a uniform distribution on [0, 3]. In this synthetic example, all covariates are continuous, i.i.d. from a multivariate uniform distribution on [0, 1].
Dataset from simulated regression survival model #4 as described in Dazard et al. (2015). Here, the regression function uses 1/10 of informative predictors in a p > n situation with p = 1000 and n = 100. The rest represents non-informative noisy covariates, which are not part of the design matrix. Survival time was generated from an exponential model with rate parameter λ (and mean frac{1}{λ}) according to a Cox-PH model with hazard exp(eta), where eta(.) is the regression function. Censoring indicator were generated from a uniform distribution on [0, 2]. In this synthetic example, all covariates are continuous, i.i.d. from a multivariate standard normal distribution.
providing 
.