This is intended as an intuitive single-number measure of how much a hazard function changes over time. The hazard is computed on an equally-spaced fine grid between the boundary knots. The ratio between a "high" and "low" one of these hazard values is computed. For example, if the hazard is constant over time, then this hazard ratio will be 1.
Usage
hrtime(
x,
newdata = NULL,
niter = NULL,
summ_fns = NULL,
hq = c(0.1, 0.9),
sample = FALSE
)
Arguments
- x
A fitted model object as returned by
survextrap
- newdata
Data frame of covariate values to compute the output for. If there are covariates in the model and this is not supplied, the following default is used:
(a) if the only covariate is one factor variable, then the output is computed for each level of this factor.
(b) if there are multiple covariates, or any numeric covariates, then the output is computed at the mean of each numeric covariate in the original data, and at the baseline level of each factor covariate.
Note caution is required about how treatment groups (for example) are stored in your data. If these are coded as numeric (0/1), then if
newdata
is not specified only one output will be shown, which relates to the average value of this numeric variable over the data, which doesn't correspond to either of the treatment groups. To avoid this, a treatment group should be stored as a factor.- niter
Number of MCMC iterations to use to compute credible intervals. Set to a low value to make this function quicker, at the cost of some approximation error (which may not be important for plotting or model development).
- summ_fns
A list of functions to use to summarise the posterior sample. This is passed to
posterior::summarise_draws
. By default this islist(median=median, ~quantile(.x, probs=c(0.025, 0.975)))
. If the list is named, then the names will be used for the columns of the output.- hq
Quantiles which define the "low" and "high" values of a time-varying quantity (hazard in
prior_haz_sd
and the hazard ratio inprior_hr_sd
). The ratio between the high and low values will be summarised, as a measure of time-dependence. By default, this isc(0.1, 0.9)
, so that the 10% and 90% quantiles are used respectively.- sample
If
TRUE
then the MCMC samples are returned instead of being summarised as a median and 95% credible intervals.
Value
A summary of the posterior distribution of this hazard
ratio from the fitted model, as a data frame with one row per
covariate value requested in newdata
, and one column for each
posterior summary statistic.
Or if sample=TRUE
, an array with dimensions
1
, niter
, and nrow(newdata)
, giving the
incremental RMST evaluated at different MCMC iterations
and covariate values respectively.