Activity Number:
|
332
- Estimation and Survey
|
Type:
|
Contributed
|
Date/Time:
|
Tuesday, August 9, 2022 : 2:00 PM to 3:50 PM
|
Sponsor:
|
Government Statistics Section
|
Abstract #322900
|
|
Title:
|
High-Dimensional Temporal Disaggregation and Nowcasting: Examination of Trade-In-Services Throughout the Brexit Transition Period
|
Author(s):
|
Luke Mosley* and Alex Gibberd and Kaveh Salehzadeh Nobari
|
Companies:
|
Lancaster University and Lancaster University and Imperial College London
|
Keywords:
|
Time Series;
Temporal Disaggregation;
Nowcasting;
High Dimensional;
Mixed Frequency ;
Official statistics
|
Abstract:
|
We consider the task of temporally disaggregating quarterly trade-in-services data from the UK throughout the Brexit transition period. The paper demonstrates a novel temporal disaggregation framework that can work with many indicator series, including novel fast-indicators, to simultaneously select and estimate linear combinations of data-streams to use in a high-frequency approximation. Alongside, retrospective temporal disaggregation, we also demonstrate the utility of methods in providing simple near-time nowcasts for trade statistics at the latent monthly frequency. Our experimental results suggest utility of the method in tracking short-term dynamics and interpretation into the driving forces behind monthly trade. A more extensive version of this paper will investigate dynamics across 12 different types of service.
|
Authors who are presenting talks have a * after their name.