Comment

Publication Type:
Journal Article
Citation:
International Journal of Forecasting, 2010, 26 (2), pp. 435 - 438
Issue Date:
2010-04-01
Full metadata record
Files in This Item:
Filename Description Size
Thumbnail2010002595OK.pdf233.73 kB
Adobe PDF
The article by Zellner and Ando proposes methods for coping with the excess kurtosis that is often observed in disturbances in applications of the seemingly unrelated regressions (SUR) model. This is an important topic which is of particular relevance in forecasting. However, the proposed methods do not address the problem: the direct Monte Carlo (DMC) algorithm is incorrect and the proposed variant of the Student-t distribution cannot account for thick tails in the distribution of disturbances in the SUR model. © 2010 International Institute of Forecasters.
Please use this identifier to cite or link to this item: