Abstract

Multivariate techniques for Benchmarking and Temporal Disaggregation handle systems of time series variables rather than treating each series independently. Unlike traditional univariate methods, multivariate methods can enforce contemporaneous or accounting constraints alongside the temporal ones and have the advantage of using more information in the estimation process. Multivariate benchmarking, or Reconciliation, is applicable when an aggregate and its components are estimated separately (the so-called direct approach), while multivariate temporal disaggregation is typically needed when the disaggregated series are connected through accounting identities, such as in National Accounts.

JDemetra+ is a reference tool for time series analysis supported by Eurostat and specifically designed to address statistical problems encountered in the production of official statistics. The R package rjd3bench provides access to the highly efficient JDemetra+ algorithms for temporal disaggregation and interpolation, as well as for benchmarking, reconciliation and calendarization. This presentation introduces the package through practical examples, with a particular focus on reconciliation and multivariate temporal disaggregation.