Research Seminar: Department of Econometrics and Business Statistics
The Department of Econometrics and Business Statistics invites you to a research seminar 'Improved Methods for Combining Point Forecasts for an Asymmetrically Distributed Variable' presented by Professor Shaun Vahey from Warwick Business School.
No RSVP is required.
Abstract summary
Many studies have found that combining forecasts improves forecast accuracy. An often-used approach developed by Granger and Ramanathan (GR, 1984) utilises a linear-Gaussian regression model to combine point forecasts. This paper generalises their approach for an asymmetrically distributed target variable. Our copula point forecast combination methodology involves fitting marginal distributions for the target variable and the individual forecasts being combined; and then estimating the correlation parameters capturing linear dependence. If the target variable is Gaussian distributed, the copula point combination collapses to the GR combination. We illustrate our methodology with two applications based on macroeconomic variables that are asymmetrically distributed. The first application examines real-time forecasts for the Federal Funds rate. The second application considers forecasts for US output growth. The copula point combinations outperform the individual forecasts and conventional GR combinations in both applications.
Authors: Ozer Karagedikli (Reserve Bank of New Zealand and CAMA), Shaun P. Vahey (University of Warwick and CAMA), Elizabeth C. Wakerly (EPS and CAMA)
Event Details
- Date:
- 9 November 2018 at 11:30 am – 12:30 pm
- Venue:
- Clayton Campus, Robert Menzies building, Room E4.57
- Categories:
- Econometrics and Business Statistics
Description
The Department of Econometrics and Business Statistics invites you to a research seminar 'Improved Methods for Combining Point Forecasts for an Asymmetrically Distributed Variable' presented by Professor Shaun Vahey from Warwick Business School.
No RSVP is required.
Abstract summary
Many studies have found that combining forecasts improves forecast accuracy. An often-used approach developed by Granger and Ramanathan (GR, 1984) utilises a linear-Gaussian regression model to combine point forecasts. This paper generalises their approach for an asymmetrically distributed target variable. Our copula point forecast combination methodology involves fitting marginal distributions for the target variable and the individual forecasts being combined; and then estimating the correlation parameters capturing linear dependence. If the target variable is Gaussian distributed, the copula point combination collapses to the GR combination. We illustrate our methodology with two applications based on macroeconomic variables that are asymmetrically distributed. The first application examines real-time forecasts for the Federal Funds rate. The second application considers forecasts for US output growth. The copula point combinations outperform the individual forecasts and conventional GR combinations in both applications.
Authors: Ozer Karagedikli (Reserve Bank of New Zealand and CAMA), Shaun P. Vahey (University of Warwick and CAMA), Elizabeth C. Wakerly (EPS and CAMA)