rjd3filters 2.3.0.9000
All notable changes to this project will be documented in this file.
The format is based on Keep a Changelog, and this project adheres to Semantic Versioning.
Unreleased
Added
- New method
underlying_forecasts().
Changed
Correction in internal functions when filtering series with NA and the beginning and not and the end of the series.
For polynomial methods, default I/C ratio fixed to 3.5 (as in X-11 for H-13).
implicit_forecast()function renamed toimplicit_forecasts().
2.3.0 - 2025-04-24
2.2.0 - 2025-03-01
Added
New function
polynomial_matrix()to create a matrix of polynomial terms.New function
mmsre_filter()to compute the general Proietti and Luati (2008) filter with extension for non symmetric filters and with Timeliness criterion.New parameter to
confint_filter()to specify if the variance should be estimated for each asymmetric filters (default) instead of using the variance associated the symmetric estimates.
Changed
-
filter()correction when the length of the series equals the length of the filter. -
confint_filter()uses by default a Student distribution instead of a Normal distribution.
2.1.1 - 2024-07-12
Changed
-
cross_validation()function renamed tocve(),cross_validation()is now deprecated. - New .jar files added (related to v2.2.0)
Added
- New functions to compute functions to compute diagnostics and goodness of fit of filtered series: cross validation (
cv()) and cross validate estimate (cve()), leave-one-out cross validation estimate (loocve), CP statistic (cp()) and Rice’s T statistics (rt()). - New function
confint_filter()to compute confidence intervals for filtered series. - New function
is.finite_filters(). - New parameter
zero_as_naincbind.moving_average, boolean indicating if trealing and leading zeros added to have a matrix form should be replaced byNA.