Files in this item



application/pdf3017121.pdf (7MB)Restricted to U of Illinois
(no description provided)PDF


Title:Multiproduct Nonconstant and Time -Varying Hedge Ratio Estimation by Locally Polynomial Kernel Applied to the Hog Complex
Author(s):Kim, Min-Kyoung
Doctoral Committee Chair(s):Leuthold, Raymond M.
Department / Program:Agricultural Economics
Discipline:Agricultural Economics
Degree Granting Institution:University of Illinois at Urbana-Champaign
Subject(s):Economics, Finance
Abstract:Multiproduct hedge ratios generated by locally polynomial kernel are recommended to use when the futures market is utilized to manage price risks because they are found to take account of more information inflow on prices than GARCH-type models. Estimated hedge ratios using past information might not be relevant to hog producers to manage their price risks in reality. Thus, hedge ratios are one-step ahead forecasted, ex ante hedge ratios, and evaluated for an out-of-sample period. Multiproduct hedging using LPK is suggested for use when the futures market is needed to hedge price risks in a forthcoming period, which gives risk minimizing hedge ratios with higher mean return than other hedging strategies. In addition, this study evaluates the selective hedging using forecasted prices by LPK, which has smaller forecasting errors than the vector autoregression model, and found that the unhedged variance of return is substantially reduced by selective hedging, but not reduced as much as by full hedging strategies. Meanwhile, the return by selective hedging increases considerably relative to full hedging. Thus, the selective hedging is a good alternative to hog producers who do not want to sacrifice mean return as much as when full hedging is used, and want to retain a lower variance of return.
Issue Date:2000
Description:153 p.
Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 2000.
Other Identifier(s):(MiAaPQ)AAI3017121
Date Available in IDEALS:2015-09-25
Date Deposited:2000

This item appears in the following Collection(s)

Item Statistics