benefit_cv: Cross validated c index and c for benefit
In tbalan/cbenefit: Cross Validated C-Index and C-Index for Benefit

Description Usage Arguments Value Examples

Cross validated c index and c for benefit

1
2
3

benefit_cv(model_fit, treat_name, folds = 10, times = 10,
  reproducible = FALSE, match_by = "benefit", data = NULL,
  replace = FALSE, matchit_args = list())

`model_fit`	An object as returned by model_fit or model_fit_glmnet
`treat_name`	The name of the treatment variable as a string
`folds`	Number of folds for k-fold cross validation
`times`	Number of repetitions of the cross validation
`reproducible`	Logical. If 'TRUE', then at each repetition of the cross validation and every time 'matchit' is called the seed is fixed.
`match_by`	One of "benefit" or "covariates" - what should the matching be based on?
`data`	Must only be specified if match_by = "covariates", the data frame.
`replace`	Logical, whether matching should be done with replacement. Default is 'FALSE'. This argument is passed to MatchIt::matchit and overrides the parameters given in the 'matchit_args' argument.
`matchit_args`	A list with other arguments that are passed on to matchit. See ?MatchIt::matchit for options like distance or method of matching.

An object of class cbenefit

1
2
3

m1 <- model_fit(Surv(time, status) ~  treat + x1 + x2 + x3 + x4 + x5 + x6 + x7 + x8,
dat_toy, model = "coxph")
benefit_cv(m1, "treat", folds = 5, times = 3)