model_diagnostics.surv_explainer: Dataset Level Model Diagnostics

In survex: Explainable Machine Learning in Survival Analysis

Dataset Level Model Diagnostics

Description

This function calculates martingale and deviance residuals.

Usage

model_diagnostics(explainer)

## S3 method for class 'surv_explainer'
model_diagnostics(explainer)

Arguments

explainer

an explainer object - model preprocessed by the explain() function

Value

An object of class c("model_diagnostics_survival"). It's a list with the explanations in the result element.

Examples

library(survival)
library(survex)

cph <- coxph(Surv(time, status) ~ ., data = veteran, model = TRUE, x = TRUE, y = TRUE)
rsf_ranger <- ranger::ranger(Surv(time, status) ~ .,
  data = veteran,
  respect.unordered.factors = TRUE,
  num.trees = 100,
  mtry = 3,
  max.depth = 5
)

cph_exp <- explain(cph)

rsf_ranger_exp <- explain(rsf_ranger,
  data = veteran[, -c(3, 4)],
  y = Surv(veteran$time, veteran$status)
)

cph_residuals <- model_diagnostics(cph_exp)
rsf_residuals <- model_diagnostics(rsf_ranger_exp)

head(cph_residuals$result)
plot(cph_residuals, rsf_residuals, xvariable = "age")
plot(cph_residuals, rsf_residuals, plot_type = "Cox-Snell")

survex documentation built on Oct. 25, 2023, 1:06 a.m.