Methods of temporal disaggregation are used to obtain high frequency time series from the same low frequency time series — so-called disaggregation—with respect to some additional consistency conditions between low and high frequency series. Conditions depend on the nature of the data — e.g., stack, flow, average and may pertain to the sum, the last value and the average of the obtained high frequency series, respectively. Temporal disaggregation methods are widely used all-over the world to disaggregate for example quarterly GDP. These methods are usually two-stage methods which consist of regression and benchmarking. In this article we propose a method which performs regression and benchmarking at the same time and allows to set a trade-off between them.
Citation rules
Licence
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.