"residuals"(object, newdata = NULL, re_formula = NULL, type = c("ordinary", "pearson"), method = c("fitted", "predict"), allow_new_levels = FALSE, incl_autocor = TRUE, subset = NULL, nsamples = NULL, sort = FALSE, summary = TRUE, robust = FALSE, probs = c(0.025, 0.975), ...)brmsfitNULL (default), the orginal data of the model is used.NULL (default), include all random effects;
if NA, include no random effects."ordinary" or "pearson".
More information is provided under 'Details'."fitted"
(predicted values of the regression curve) or
"predict" (predicted response values).
Using "predict" is recommended
but "fitted" is the current default for
reasons of backwards compatibility.FALSE).
Only relevant if newdata is provided.TRUE.NULL (the default), all samples are used.NULL (the default) all samples are used.
Ignored if subset is not NULL.FALSE; default) or in the order of the
time series (TRUE).TRUE.FALSE (the default) the mean is used as
the measure of central tendency and the standard deviation as
the measure of variability. If TRUE, the median and the
median absolute deivation (MAD) are applied instead.
Only used if summary is TRUE.quantile
function. Only used if summary is TRUE.summary = TRUE
this is a N x C matrix and if summary = FALSE
a S x N matrix, where S is the number of samples,
N is the number of observations, and C is equal to
length(probs) + 2.
ordinary
are of the form $R = Y - Yp$, where $Y$ is the observed
and $Yp$ is the predicted response.
Residuals of type pearson are
of the form $R = (Y - Yp) / SD(Y)$,
where $SD(Y)$ is an estimation of the standard deviation
of $Y$.
Currently, residuals.brmsfit does not support
categorical or ordinal models.
## Not run:
# ## fit a model
# fit <- brm(rating ~ treat + period + carry + (1|subject),
# data = inhaler, cluster = 2)
#
# ## extract residuals
# res <- residuals(fit, summary = TRUE)
# head(res)
# ## End(Not run)
Run the code above in your browser using DataLab