Functional Regression with Nonstationary and Error Contamination: Application to the Economic Impact of Climate Change

Speaker: Dr Won-Ki Seo

Affiliation: University of Sydney

Location: Room 101, Chamberlain Building (#35), St Lucia Campus

Zoom: https://uqz.zoom.us/j/82603079317

Abstract: This paper studies a functional regression model in which the nonstationary stochastic trend(s) of a dependent functional variable are explained by those of an explanatory functional variable. The model extends the cointegrating regression framework from conventional time series analysis. We develop novel autocovariance-based estimation and inference methods for this setting. The methodology is broadly applicable to economic and statistical functional time series with nonstationary dynamics. As an illustration—and due to its intrinsic importance—we apply it to assess the economic impact of climate change.