Compute posterior predictive samples averaged across models. Weighting can be done in various ways, for instance using Akaike weights based on information criteria or marginal likelihoods.
# S3 method for brmsfit
pp_average(x, ..., weights = "loo2",
method = c("predict", "fitted", "residuals"), nsamples = NULL,
summary = TRUE, probs = c(0.025, 0.975), robust = FALSE,
model_names = NULL, control = list(), seed = NULL)pp_average(x, ...)
A fitted model object.
More fitted model objects or further arguments passed to the underlying post-processing functions.
Name of the criterion to compute weights from.
Should be one of "loo", "waic", "kfold",
"loo2" (current default), or "marglik".
For the former three options, Akaike weights will be computed
based on the information criterion values returned by
the respective methods. For "loo2", method
loo_model_weights will be used to obtain weights.
For "marglik", method post_prob
will be used to compute weights based on log marginal
likelihood values (make sure to specify reasonable priors in
this case). Alternatively, weights can be a numeric vector
of pre-specified weights.
Type of predictions to average. Should be one of
"predict" (default), "fitted", or "residuals".
Total number of posterior samples to use.
Should summary statistics
(i.e. means, sds, and 95% intervals) be returned
instead of the raw values? Default is TRUE.
The percentiles to be computed by the quantile
function. Only used if summary is TRUE.
If 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 deviation (MAD) are applied instead.
Only used if summary is TRUE.
If NULL (the default) will use model names
derived from deparsing the call. Otherwise will use the passed
values as model names.
Optional list of further arguments
passed to the function specified in weights.
A single numeric value passed to set.seed
to make results reproducible.
Same as the output of the method specified
in argument method.
Weights are computed with the model_weights method.
# NOT RUN {
# model with 'treat' as predictor
fit1 <- brm(rating ~ treat + period + carry, data = inhaler)
summary(fit1)
# model without 'treat' as predictor
fit2 <- brm(rating ~ period + carry, data = inhaler)
summary(fit2)
# compute model-averaged predicted values
(df <- unique(inhaler[, c("treat", "period", "carry")]))
pp_average(fit1, fit2, newdata = df)
# compute model-averaged fitted values
pp_average(fit1, fit2, method = "fitted", newdata = df)
# }
# NOT RUN {
# }
Run the code above in your browser using DataLab