Epi (version 2.56)

fit.mult: Fits a multiplicative relative risk model to interval censored data.

Description

Utility function.

The model fitted assumes a piecewise constant baseline rate in intervals specified by the argument breaks, and a multiplicative relative risk function.

Usage

fit.mult( y, rates.frame, cov.frame, start )

Value

A list with three components:

rates

A glm object from a binomial model with log-link, estimating the baseline rates.

cov

A glm object from a binomial model with complementary log-log link, estimating the log-rate-ratios

niter

Nuber of iterations, a scalar

Arguments

y

Binary vector of outcomes

rates.frame

Dataframe expanded from the original data by expand.data, cooresponding to covariates for the rate parameters.

cov.frame

do., but covariates corresponding to the formula argument of Icens

start

Starting values for the rate parameters. If not supplied, then starting values are generated.

Author

Martyn Plummer, , Bendix Carstensen,

Details

The model is fitted by alternating between two generalized linear models where one estimates the underlying rates in the intervals, and the other estimates the log-relative risks.

References

B Carstensen: Regression models for interval censored survival data: application to HIV infection in Danish homosexual men. Statistics in Medicine, 15(20):2177-2189, 1996.

CP Farrington: Interval censored survival data: a generalized linear modelling approach. Statistics in Medicine, 15(3):283-292, 1996.

See Also

Icens fit.add

Examples

  data( HIV.dk )