rf_shape_para: Paralleled random survival Forest using multivariate longitudinal endogenous covariates

Description

Paralleled random survival Forest using multivariate longitudinal endogenous covariates

Usage

rf_shape_para(
  Longitudinal = NULL,
  Numeric = NULL,
  Factor = NULL,
  timeVar = NULL,
  Y,
  mtry,
  ntree,
  ncores,
  nsplit_option = "quantile",
  nodesize = 1,
  minsplit = 2,
  cause = 1,
  seed = 1234,
  verbose = TRUE
)

Arguments

Longitudinal: A list of longitudinal predictors which should contain: X a dataframe with one row for repeated measurement and as many columns as markers; id is the vector of the identifiers for the repeated measurements contained in X; time is the vector of the measurement times contained in X.
Numeric: A list of numeric predictors which should contain: X a dataframe with as many columns as numeric predictors; id is the vector of the identifiers for each individual.
Factor: A list of categorical predictors which should contain: X a dataframe with as many columns as categorical predictors; id is the vector of the identifiers for each individual.
timeVar: A character indicating the name of time variable
Y: A list of output which should contain: type defines the nature of the output, can be "surv", "numeric" or "factor"; Y is the outcome variable; id is the vector of the identifiers for each individuals, they should be the same as the identifiers of the inputs.
mtry: Number of candidate variables randomly drawn at each node of the trees. This parameter should be tuned by minimizing the OOB error. Default is NULL.
ntree: Number of trees to grow. Default value set to 200.
ncores: Number of cores used to grow trees in parallel. Default value is the number of cores of the computer-1.
nsplit_option: A character indicates how the values are chosen to build the two groups for the splitting rule (only for continuous predictors). Values are chosen using deciles (nsplit_option="quantile") or randomly (nsplit_option="sample"). Default value is "quantile".
nodesize: Minimal number of subjects required in both child nodes to split. Cannot be smaller than 1.
minsplit: (Only with survival outcome) Minimal number of events required to split the node. Cannot be smaller than 2.
cause: (Only with competing events) Number indicates the event of interest.
seed: Seed to replicate results
verbose: A logical controlling the function progress. Default is TRUE