- Fix bug that ignored the
group_by argument in
get_teff_obs() and caused at least
new_x() to not work if the subject identifier variable was called something else than
id (see issue #22).
- Add more informative error message if trying to specify a model like
y ~ age + id | age, which should be
y ~ age + age | id, i.e. the continuous covariate on the left of
| and categorical on the right.
- New startup message that prints also
- Update citation information
- Add the
c_hat_pred argument to
pred(), to be used when
f has been sampled and
c_hat is not constant. Previously,
c_hat = 0 was used in all prediction points, which did not make sense in all cases.
- Allow setting
group_by = NA in
new_x() to avoid grouping in plots.
- Allow setting
color_by as the same factor as
- Fix bug which caused an error when trying to define a separate prior for parameters of the same type.
- Internal change for more effective computation of function (component) posterior variances.
- Add option
do_yrng which controls whether to do draws from the predictive distribution. This was previously always done if
TRUE. That is now considered a bug because it is unnecessary work if the
y_rng draws are not needed. So the default is now
do_yrng = FALSE, since
do_yrng = TRUE can cause errors with the negative binomial model due to numerical problems (see here). These problems should be addressed in a future release to allow more stable prior and posterior predictive sampling.
- Small documentation update.
- Fix bug in
get_pred(), which was caused by not adding the GP mean to the sampled signal. This was causing postprocessing functions like
plot_pred() to give erroneous results if the GP mean was not a vector of zeros and
sample_f = TRUE.
- Small edits in documentation and verbose information messages.
plot_pred() work with any response variable name (fixes issue #12).
- Avoid adding
ggplot2::color_scale_manual() if number of colors > 5 (fixes issue #11).
Edit type checking to work more generally on all systems (fixes issue #5).
Fix CITATION to point to new preprint.
Added RcppParallel dependency explicitly.
Added warning if using default prior for input warping steepness.
- More general modeling options, allowing more mixing of different types of kernels/options
- Prior and posterior predictive checks using
ppc(), which interfaces to bayesplot.
Changes and improvements
- Formula syntax where
| indicates interaction terms.
- Alternative advanced formula syntax with
- Beta binomial observation model.
- Categorical covariates must now be specified as factors in data, and don’t have to be numeric.
- Component relevance assessment is now separated from model fitting into the
relevances() function and selection into
- Easier prior specification with
- Better prediction and plotting functionality with
- Extensive argument checking (see
check_positive_all() etc.) to give users informative error messages
- Thorough unit tests using test_that.
- C++ versions of the Stan model functions are now exposed to package namespace and also tested.