🚀 go-pugleaf

RetroBBS NetNews Server

Inspired by RockSolid Light RIP Retro Guy

Thread View: sci.stat.consult
2 messages
2 total messages Started by Daan Taks Mon, 21 Jan 2002 13:49
How to calculate the hessian???
#3
Author: Daan Taks
Date: Mon, 21 Jan 2002 13:49
11 lines
1662 bytes
In Excel I calculated a variance-covariance (Ht) (2*2) matrix using
the ADC model of Kroner and Ng (1998). Now I want to calculate the
standard errors of the parameters (16 in total) estimated by the
model. I know that I can do that by calculating the hessian, but how
to do that???
The log-likelihood function is as follows:
-0.5*log(determinant of Ht) - 0.5*E'*(inverse of Ht)* E
Where E is an 2*1 vector with return1 and return2 of stock indices.
How can I differentiate this log-likelihood function???
Help would be very appreciated!!!!!
Greetings Daan.
Re: How to calculate the hessian???
#4
Author: Bruno Monastero
Date: Tue, 29 Jan 2002 18:17
15 lines
1971 bytes
"Daan Taks" <blackfiction@hotmail.com> wrote in message
news:3172868c.0201210549.66390229@posting.google.com...
> In Excel I calculated a variance-covariance (Ht) (2*2) matrix using
> the ADC model of Kroner and Ng (1998). Now I want to calculate the
> standard errors of the parameters (16 in total) estimated by the
> model. I know that I can do that by calculating the hessian, but how
> to do that???

Numerical Linear Algebra with Excel is a bad idea, unless you wrote a Linear
Algebra Pack from scratch, I saw determinants greater than zero in singular
matrix 2x2.

Best wishes,
Bruno
Thread Navigation

This is a paginated view of messages in the thread with full content displayed inline.

Messages are displayed in chronological order, with the original post highlighted in green.

Use pagination controls to navigate through all messages in large threads.

Back to All Threads