Code for Unrestricted BEKK

If you are seeking RATS code for implementing a particular technique or replicating results from a paper, post your request here. Be sure to include complete citations for any papers or books.

Code for Unrestricted BEKK

Unread postby curiousresearcher » Mon Oct 28, 2019 11:17 am

Hi,

Please share the code for unrestricted BEKK as used in this research paper - https://www.sciencedirect.com/science/a ... 2318308237
curiousresearcher
 
Posts: 42
Joined: Sun May 19, 2019 9:56 pm

Re: Code for Unrestricted BEKK

Unread postby TomDoan » Mon Oct 28, 2019 1:00 pm

That paper is behind a paywall, but what is an "unrestricted" BEKK? A standard BEKK (MV=BEKK on the GARCH instruction) is unrestricted; TBEKK and DBEKK are restricted forms.

You might want to read the article from the April 2019 newsletter:

Spillover/Causality-in-Variance Tests

In BEKK models the "spillover" is sometimes just an artifact of how BEKK handles the covariances.
TomDoan
 
Posts: 7240
Joined: Wed Nov 01, 2006 5:36 pm

Re: Code for Unrestricted BEKK

Unread postby curiousresearcher » Wed Oct 30, 2019 12:11 am

Hello Tom,

When i am using the normal BEKK command as suggested, the results are showing no spillover at all between the cryptocurrencies.

But this paper is showing bi-directional spillover among the

The data i am using matches with that of the paper. So it seems the problem relates to the code used

I am also attaching the data for bitcoin and ether for your reference here used in the paper.

Will appreciate if i can get the code which gets me the result in this paper.

Thanks a lot in advance

* code used is

garch(p=1, q=1,mv=bekk,robusterrors,stdresids=rstd) / BTC ETH
Attachments
data for estima forum.xlsx
(54.41 KiB) Downloaded 423 times
curiousresearcher
 
Posts: 42
Joined: Sun May 19, 2019 9:56 pm

Re: Code for Unrestricted BEKK

Unread postby TomDoan » Wed Oct 30, 2019 9:59 am

Do you actually have the data that they used, or do you have what you think is the same data (based upon their description)?
TomDoan
 
Posts: 7240
Joined: Wed Nov 01, 2006 5:36 pm

Re: Code for Unrestricted BEKK

Unread postby curiousresearcher » Mon Nov 04, 2019 1:23 am

Hi,

I have the data they have used as i have matched by descriptive statistics - mean/median/no of obs. etc with their summary stats in the paper.
curiousresearcher
 
Posts: 42
Joined: Sun May 19, 2019 9:56 pm


Return to Looking for Code?

Who is online

Users browsing this forum: No registered users and 2 guests

cron