ah {ivtools}

Fitting semiparametric additive hazards regression models.

Description

ah is a wrapper around the ahaz function in the ahaz package, with a more user-friendly and standard interface. Refer to the manual for ahaz for details.

Usage

ah(formula, data, weights, robust=FALSE)

Arguments

formula

an object of class "formula": a symbolic description of the model to be fitted.

data

a data frame containing the variables in the model.

weights

an optional vector of prior weights to be used in the fitting process.

robust

robust calculation of variance; see manual for ahaz.

Details

See manual for ahaz.

Value

An object of class "ah" is a list containing the same elements as an object of class "ahaz", plus

call

the matched call.

formula

the formula argument.

coefficients

a named vector of estimated coefficients.

vcov

the variance-covariance matrix for the estimated coefficients.

incl

the ahaz function does not allow for missing data. Thus, if data contains rows with missing data on any of the variables in the model, then these rows are excluded before calling ahaz. incl is a vector containing the rownames of those rows that are included in the analysis, that is, the rows with no missing data on any of the variables in the model.

Note

The ahaz function does not allow for ties. Thus, before calling ah any ties have to be manually broken.

Author(s)

Arvid Sjolander.

References

Lin D.Y., Ying Z. (1994). Semiparametric analysis of the additive risk model. Biometrika 81(1), 61-71.

Examples

require(ahaz)

##This example is adapted from the example given for the ahaz function 
##in the ahaz package 

data(sorlie)

# Break ties
set.seed(10101)
sorlie$time <- sorlie$time+runif(nrow(sorlie))*1e-2

# Fit additive hazards model 
fit <- ah(formula=Surv(time, status)~X13+X14+X15+X16+X17+X18+X19+X20+X21+X22, 
  data=sorlie)
summary(fit)