Cox regression ORSF controlSource:
Use the coefficients from a proportional hazards model to create linear combinations of predictor variables while fitting an orsf model.
(character) a character string specifying the method for tie handling. If there are no ties, all the methods are equivalent. Valid options are 'breslow' and 'efron'. The Efron approximation is the default because it is more accurate when dealing with tied event times and has similar computational efficiency compared to the Breslow method.
(double) When using Newton Raphson scoring to identify linear combinations of inputs, iteration continues in the algorithm until the relative change in the log partial likelihood is less than
eps, or the absolute change is less than
sqrt(eps). Must be positive. A default value of 1e-09 is used for consistency with survival::coxph.control.
(integer) iteration continues until convergence (see
epsabove) or the number of attempted iterations is equal to
Further arguments passed to or from other methods (not currently used).
an object of class
'orsf_control', which should be used as
an input for the
control argument of orsf.
code from the survival package was modified to make this routine.
For more details on the Cox proportional hazards model, see coxph and/or Therneau and Grambsch (2000).
Therneau T.M., Grambsch P.M. (2000) The Cox Model. In: Modeling Survival Data: Extending the Cox Model. Statistics for Biology and Health. Springer, New York, NY. DOI: 10.1007/978-1-4757-3294-8_3
linear combination control functions
orsf(data = pbc_orsf, formula = Surv(time, status) ~ . - id, control = orsf_control_cph()) #> ---------- Oblique random survival forest #> #> Linear combinations: Cox regression #> N observations: 276 #> N events: 111 #> N trees: 500 #> N predictors total: 17 #> N predictors per node: 5 #> Average leaves per tree: 25 #> Min observations in leaf: 5 #> Min events in leaf: 1 #> OOB stat value: 0.84 #> OOB stat type: Harrell's C-statistic #> Variable importance: anova #> #> -----------------------------------------