IMPORTANT CHANGE IN THE API OF THE reconc_*
functions: they now require the aggregation matrix A and not the summing matrix S.
The examples section of the reconc_TDcond
now contains an example showing how to handle the case of an unbalanced hierarchy.
Added reconc_MixCond
, the implementation of Mixed conditioning for the reconciliation of mixed-type hierarchical forecasts.
Added reconc_TDcond
, the implementation of Top-down conditioning for the reconciliation of mixed-type hierarchical forecasts.
Vignette "Reconciliation of M5 hierarchy with mixed-type forecasts".
Added functions PMF.get_mean
, PMF.get_quantile
, PMF.get_var
, PMF.sample
, PMF.summary
that return point estimates and samples from a probability mass function object.
Added the dataset M5_CA1_basefc
which contains the base forecasts for the store "CA1" of the hierarchical time series in the M5 competition.
Vignette "Properties of the reconciled distribution via conditioning".
Added option in reconc_BUIS
to pass some base forecast as parameters and some as samples.
Added option in reconc_BUIS
to input a list of distributions instead of a string.
Fixed bugs and closed github issues.
Vignette "Probabilistic Reconciliation via Conditioning with bayesRecon".
Added the schaferStrimmer_cov
function.
Fixed bugs.
Added a NEWS.md
file to track changes to the package.
Fixed issue that could cause test fails on some machines.
Any scripts or data that you put into this service are public.
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.