riskset: Compute the risk set indicator
In pcoxtime: Penalized Cox Proportional Hazard Model for Time-Dependent Covariates

riskset

R Documentation

Compute the risk set indicator

Description

Identify set of individuals at risk of experiencing the event before event time (failure time), t_i. The risk set, R_i, is the set of individuals, j, who had not experienced the event or had been censored by time t_i. This function identifies this set and computes event times satisfying this.

Usage

riskset(
  formula,
  data,
  contrasts.arg = NULL,
  xlevs = NULL,
  scaleX = TRUE,
  na.action = na.omit
)

Arguments

`formula`	Object of class formula describing the model. The response and terms are specified similar to `Surv` function.
`data`	optional data frame containing variables specified in the formula.
`contrasts.arg`	an optional list. See the contrasts.arg of `[stats]{model.matrix.default}`.
`xlevs`	a named list of character vectors giving the full set of levels to be assumed for each factor. See `[stats]{model.frame}`.
`scaleX`	logical. If TRUE (default), predictors are scaled/standardized. This is used internally.
`na.action`	a function which indicates what should happen when the data contain NAs. See `[stats]{model.frame}`.

Details

Let t_1 < t_2 <, ..., t_m, such that m < n if there are not ties, otherwise m = n. If covariates are time-independent the risk set, R_i, is the set of individuals who are still at risk at time t_i, i.e., individuals with event/censoring time y_j≥ t_i. For time-dependent covariates risk set at time t_i is now defined as R(t_i) = \{j : (y^{stop}_{j} ≥ t_i) \wedge (y^{start}_{j} < t_i)\}. The first condition, (y^{stop}_{j} ≥ t_i), ensures that individual j either experienced the event or was censored at a later time point than t_i, while the second condition, (y^{start}_{j} < t_i), ensures the start time was observed before the event.

Value

A list of survival objects:

`Y`	Surv object defining the event times and event status.
`X`	model matrix of model terms.
`events`	observed events.
`times`	event times defined by risk set condition.
`timevarlabel, eventvarlabel`	time and event variables, respectively.
`scale_sd, scale_mu`	standard deviation and mean of each of the variable used in standardization.