rsaalen: Fit an extended additive hazards model using relative...
In relsurv: Relative Survival

rsaalen

R Documentation

Fit an extended additive hazards model using relative survival

Description

Fits the Aalen additive hazard model using relative survival. The function can be used for multi-state model data (as in the package mstate; class msdata) by supplying the start and stop times in the Surv object and adding a strata(trans) object in the formula (where trans denotes the transition in the multi-state model).

Usage

rsaalen(
  formula,
  data,
  variance = FALSE,
  var_estimator = "dN",
  ratetable = relsurv::slopop,
  rmap,
  split.transitions
)

Arguments

`formula`	a formula object, with the response as a `Surv` object on the left of a `~` operator, and, if desired, terms separated by the `+` operator on the right.
`data`	a data.frame in which to interpret the variables named in the `formula`.
`variance`	a logical value indicating whether the variances of the hazards should be computed. Default is FALSE.
`var_estimator`	Choose variance estimator, in the same way as in survaalen. The default option 'dN' uses dN(t)-dLambda_P(t) in the variance estimator, equivalent to formula 4.63 in Aalen et al. (2008). Option 'XdB' uses X*dB(t), see formula 4.64 in Aalen et al. (2008).
`ratetable`	a table of event rates, organized as a `ratetable` object, such as `slopop`.
`rmap`	an optional list to be used if the variables are not organized and named in the same way as in the `ratetable` object.
`split.transitions`	only relevant if a multi-state model is fitted. An integer vector containing the numbered transitions that should be split. Use same numbering as in the given transition matrix.

Value

An object of class aalen.model.

Author(s)

Damjan Manevski

Examples


# Survival:
data(rdata)
mod <- rsaalen(Surv(time, cens)~sex+age, data=rdata, ratetable=slopop,
     rmap=list(age=age*365.241))
head(mod$coefficients)
tail(mod$coefficients)

# Multi-state model:
data(ebmt1wide)
# Generate sex and year data (for illustrative purposes since it is not given in the data):
ebmt1wide$sex <- sample(1:2, size = nrow(ebmt1wide), replace = TRUE)
ebmt1wide$year <- as.Date('2010-01-01')

mod <- rsaalen(Surv(Tstart, Tstop, status)~age.1+age.2+age.3+strata(trans), data=ebmt1wide,
                 ratetable = slopop, rmap = list(age=age*365.241), split.transitions = 2:3)
head(mod$coefficients$trans1)
head(mod$coefficients$trans2)
head(mod$coefficients$trans3)

relsurv documentation built on April 3, 2025, 10:56 p.m.