Compute infinitesimal jackknife pseudo observations

Assuming that the censoring depends on covariates with a finite set of levels, the pseudo observations are calculated with the infinitesimal jackknife approach stratified on those covariates. If no covariates are specified in the censoring model, then the pseudo observations are calculated under the completely independent censoring assumption. This function allows survival objects with entry and exit times, thus multi-state models, recurrent events, and delayed entry/left truncation. With delayed entry, the pseudo observation approach theoretically works under the assumption that the entry time is independent of covariates.

pseudo_infjack(
  formula,
  time,
  cause = 1,
  data,
  type = c("cuminc", "survival", "rmean"),
  formula.censoring = NULL,
  ipcw.method = NULL
)

Arguments

formula

A formula specifying the outcome model. The left hand side must be a Surv object specifying a right censored survival, competing risks, counting process, or multistate outcome. The status indicator, normally 0=alive, 1=dead. Other choices are TRUE/FALSE (TRUE = death) or 1/2 (2=death). For competing risks and multi state models, the event variable will be a factor, whose first level is treated as censoring. The right hand side is the usual linear combination of covariates.

time

Numeric constant specifying the time at which the cumulative incidence or survival probability effect estimates are desired.

cause

Numeric or character constant specifying the cause indicator of interest.

data

Data frame in which all variables of formula can be interpreted.

type

One of "survival", "cuminc", or "rmean"

formula.censoring

A optional right-sided formula specifying which variables to stratify on. All variables in this formula must be categorical.

ipcw.method

Not used with this method

Value

A vector of pseudo observations

See also

survfit

Examples

POi <- pseudo_infjack(Surv(time, status) ~ 1, 1500, cause = 1,
  data = colon, type = "survival", formula.censoring = ~ sex)

mean(POi)
#> [1] 0.5801007