GMM estimation for International / world CAPM

For technical questions regarding estimation of single equations, systems, VARs, Factor analysis and State Space Models in EViews. General econometric questions and advice should go in the Econometric Discussions forum.

Moderators: EViews Gareth, EViews Moderator

TheTACT
Posts: 1
Joined: Tue Jul 20, 2010 10:18 am

GMM estimation for International / world CAPM

Postby TheTACT » Tue Jul 20, 2010 1:13 pm

Hi,

I am trying to rebuild Dumas/Solnik 1995 The World Price of Foreign Exchange Risk. I understand the mathematics and how to do a GMM estimation in Eviews, how to write a system etc., however I don't get the inputs right. In the attached picture the delta and theta estimates are to be estimated by GMM, the Z_t-1 vector are the instruments (6 instruments, including the constant) and lambda_0, t-1 is a constant, while lambda_l, t-1 are rewards per unit of risk for exchange rate risk (for the countries in the sample) and lambda_m is interpreted as market risk aversion.

My question is: how do I proceed to estimate the system? Do I have to give inputs for the lambda, and if so, what are these? I thought the excess FX returns would be the right choice, but then I can't get an overview on all 24 theta (3 countries + world market = 4 x 6 instruments) and 6 delta (one for each instrumental variable). Has anyone worked on this problem before and can give me at least a hint what the right procedure is, respectively which inputs belong where?

Many, many thanks in advance!

TACT
Attachments
formula.png
p.450, Equation 5
formula.png (4.35 KiB) Viewed 1606 times

Return to “Estimation”

Who is online

Users browsing this forum: No registered users and 2 guests