This function resamples observations in the data set to obtain approximate CIs for different terms and coefficient functions that correct for the effects of dependency and heteroskedasticity of the residuals along the index of the functional response, i.e., it aims for correct inference if the residuals along the index of the functional response are not i.i.d.
coefboot.pffr( object, n1 = 100, n2 = 40, n3 = 20, B = 100, ncpus = getOption("boot.ncpus", 1), parallel = c("no", "multicore", "snow"), cl = NULL, conf = c(0.9, 0.95), type = "percent", method = c("resample", "residual", "residual.c"), showProgress = TRUE, ... )
number of bootstrap replicates, defaults to (a measly) 100
boot. Defaults to
getOption("boot.ncpus", 1L) (like
desired levels of bootstrap CIs, defaults to 0.90 and 0.95
type of bootstrap interval, see
boot.ci. Defaults to "percent" for percentile-based CIs.
either "resample" (default) to resample response trajectories, or "residual" to resample responses as fitted values plus residual trajectories or "residual.c" to resample responses as fitted values plus residual trajectories that are centered at zero for each gridpoint.
a list with similar structure as the return value of
coef.pffr, containing the
original point estimates of the various terms along with their bootstrap CIs.