Research Repository

An alternative numerical method for estimating large-scale time-varying parameter seemingly unrelated regressions models

Hadjiantoni, Stella and Kontoghiorghes, Erricos J (2021) 'An alternative numerical method for estimating large-scale time-varying parameter seemingly unrelated regressions models.' Econometrics and Statistics. ISSN 2452-3062 (In Press)

[img] Text
TimeVaryingParametersModel_accepted.pdf - Accepted Version
Restricted to Repository staff only until 20 January 2022.
Available under License Creative Commons Attribution Non-commercial No Derivatives.

Download (395kB) | Request a copy

Abstract

A novel numerical method for the estimation of large-scale time-varying parameter seemingly unrelated regression (TVP-SUR) models is proposed. The updating and smoothing estimates of the TVP-SUR model are derived within the context of generalised linear least squares and through numerically stable orthogonal transformations which allow the sequential estimation of the model. The method developed is based on computationally efficient strategies. The computational cost is reduced by exploiting the special sparse structure of the TVP-SUR model and by utilising previous computations. The proposed method is also extended to the rolling window estimation of the TVP model. Experimental results show the effectiveness of the new updating, rolling window and smoothing strategies in high dimensions when a large number of covariates and regressions are included in the TVP-SUR model, and in the presence of an ill-conditioned data matrix.

Item Type: Article
Uncontrolled Keywords: time-varying coefficients, recursive estimation, updating, rolling window estimation,matrix algebra
Divisions: Faculty of Science and Health > Mathematical Sciences, Department of
Depositing User: Elements
Date Deposited: 10 Dec 2020 12:34
Last Modified: 20 Jan 2021 17:15
URI: http://repository.essex.ac.uk/id/eprint/29186

Actions (login required)

View Item View Item