mexhaz-package: Mixed effect parametric excess hazard models

In mexhaz: Mixed Effect Excess Hazard Models

Mixed effect parametric excess hazard models

Description

Fit an (excess) hazard regression model using different shapes for the baseline hazard (Weibull, piecewise constant, exponential of a B-spline of degree 1 to 3, exponential of a restricted cubic spline), with the possibility to include time-dependent effects of variable(s) and a random effect defined at the cluster level. Follow-up time can be entered in the right-censored or counting process input style. The latter allows the modelling of survival data with delayed entries. The time-dependent effect of a covariable is modelled by adding interaction terms between the covariable and a function of time of the same class as the one used for the baseline hazard (in particular, with the same knots for piecewise constant hazards; and with the same degree and the same knots for B-spline or restricted cubic spline functions). The random effect is assumed to be normally distributed with mean 0 and standard deviation sigma. The optimisation process uses adaptive Gaussian quadrature to calculate the cluster-specific marginal likelihoods. The logarithm of the full marginal likelihood, defined as the sum of the logarithms of the cluster-specific marginal likelihoods, is then maximised using an optimisation routine such as nlm (default) or optim. Functions to compute and plot the predicted (excess) hazard and (net) survival are provided. In the case of a random intercept model, three types of predictions can be obtained : marginal (population-averaged), cluster-specific posterior (cluster-averaged), or conditional (for a given quantile of the ditribution of the random effect).

Author(s)

Hadrien Charvat, Aurelien Belot

References

Charvat H, Remontet L, Bossard N, Roche L, Dejardin O, Rachet B, Launoy G, Belot A; CENSUR Working Survival Group. A multilevel excess hazard model to estimate net survival on hierarchical data allowing for non-linear and non-proportional effects of covariates. Stat Med 2016;35(18):3066-3084 (doi: 10.1002/sim.6881)

Charvat H, Belot A. An R package for fitting flexible hazard-based regression models for overall and excess mortality with a random effect. J Stat Softw 2021;98(14):1-36 (doi: 10.18637/jss.v098.i14)

Examples

data(simdatn1)

## Fit of a mixed-effect excess hazard model, with the baseline hazard
## described by a Weibull distribution (without covariables)

Mod_weib_mix <- mexhaz(formula=Surv(time=timesurv,
event=vstat)~1, data=simdatn1, base="weibull",
expected="popmrate", verbose=0, random="clust")


## Examples of syntax for various models (not run)

## Fit of a fixed-effect excess hazard model, with the baseline hazard
## described by a Weibull distribution and with effects of age (agecr),
## deprivation index (depindex) and sex (IsexH) using the optim
## procedure and the BFGS method (see help of optim).

# Mod_weib <- mexhaz(formula=Surv(time=timesurv,
# event=vstat)~agecr+depindex+IsexH, data=simdatn1, base="weibull",
# expected="popmrate", verbose=1000, fnoptim="optim",
# method="BFGS")


## Fit of a mixed-effect excess hazard model, with the baseline hazard
## described by a cubic B-spline with two knots at 1 and 5 year and with
## effects of age (agecr), deprivation index (depindex) and sex (IsexH)

# Mod_bs3_2mix <- mexhaz(formula=Surv(time=timesurv,
# event=vstat)~agecr+depindex+IsexH, data=simdatn1, base="exp.bs",
# degree=3, knots=c(1,5), expected="popmrate", random="clust",
# verbose=1000)


## Fit of a fixed-effect overall hazard model, with the baseline hazard
## described by a piecewise constant function with the following vector
## of knots (defining the endpoints of the intervals on which the hazard
## is constant): (1,3,5,8), and with effects of age (agecr), deprivation
## index (depindex) and sex (IsexH)

# Mod_pw <- mexhaz(formula=Surv(time=timesurv, event=vstat)~
# agecr+depindex+IsexH, data= simdatn1, base="pw.cst", knots=c(1,3,5,8),
# verbose=1000)


## Fit of a fixed-effect excess hazard model, with the baseline hazard
## described by a cubic B-spline with two knots at 1 and 5 year and with
## effects of age (agecr), deprivation index (depindex) and sex (IsexH)

# Mod_bs3_2 <- mexhaz(formula=Surv(time=timesurv,
# event=vstat)~agecr+depindex+IsexH, data=simdatn1, base="exp.bs",
# degree=3, knots=c(1,5), expected="popmrate", verbose=1000)


## Fit of a mixed-effect excess hazard model, with the baseline hazard
## described by a cubic B-spline with two knots at 1 and 5 year and with
## effects of age (agecr), deprivation index (depindex) and sex (IsexH)

# Mod_bs3_2mix <- mexhaz(formula=Surv(time=timesurv,
# event=vstat)~agecr+depindex+IsexH, data=simdatn1, base="exp.bs",
# degree=3, knots=c(1,5), expected="popmrate", random="clust",
# verbose=1000)


## Fit of a mixed-effect excess hazard model, with the baseline hazard
## described by a cubic B-spline with two knots at 1 and 5 year, with
## effects of age (agecr), deprivation index (depindex) and sex (IsexH)
## and with a time-dependent effect for age (agecr) and sex (IsexH).

# Mod_bs3_2mixnph <- mexhaz(formula=Surv(time=timesurv,
# event=vstat)~agecr+depindex+IsexH + nph(agecr+IsexH), data=simdatn1,
# base="exp.bs", degree=3, knots=c(1,5), expected="popmrate",
# random="clust", verbose=1000)

mexhaz documentation built on June 28, 2024, 5:07 p.m.