Invites you to a Econometrics seminar presented by

Jiti Gao
(Monash University)

A Unified Approach to Estimating Time-Varying Trends

Co-authors:
Bin Peng (University of Illinois)

Peter C.B. Philips (Yale University)

Wednesday 26 April 2023

2.00pm – 3.30pm

Zoom: 899 5395 8812

Abstract: Time series models often involve stochastic trending components. In many cases, such stochastic trends are not necessarily observable, and should be treated as latent variables. In the econometrics and statistics literature, two different types of stochastic trends have been specified and then estimated by Bayesian methods for stochastically specified time-varying trends, and by nonparametric methods for deterministically specified time-varying trends. This presentation proposes a unified approach to estimating time-varying trends regardless whether they are stochastically specified or deterministically specified. Such an approach is also unified in terms of capable of dealing with stochastically stationary, locally stationary and nonstationary trends. Novel estimation theory is established with finite—sample evaluations. Empirical applications are in climatology, energy, finance and macroeconomics.

For further information contact: Econometrics seminar series coordinator Dr Ye Lu (ye.lu1@sydney.edu.au)

For all upcoming seminars in School of Economics see Our events and Calendar