s-news
[Top] [All Lists]

Finmetrics Internal Error

To: "S-News (E-mail)" <s-news@lists.biostat.wustl.edu>
Subject: Finmetrics Internal Error
From: "Burbidge, Robert" <robert.burbidge@csfb.com>
Date: Wed, 21 Aug 2002 17:27:37 +0100
Dear S+ers,

I hope someone can help me with an infuriating problem I have.  I am trying to 
model a bivariate GARCH using the Finmetrics module Version 1.0, S+ v6.1 for 
Windoze Professional Trial Edition Release 1.  The explanation is a bit long; 
I've tried to be explicit, since it seems to be an implemenation issue.

The following works fine (either from the command line, or within a function):

"
> len   <-      100
> prices<-      matrix(runif(300), 100, 3)
>
> r     <-      matrix(0, len-1, 3)             
> r     <- apply(log(prices), 2, diff)/1000     # this is 99x3 matrix of log 
> returns, same scale and size as real data
>
> garchOut      <- mgarch(r~ar(1), ~dvec(1, 1), trace=T)        

Iteration   0  Step Size = 0.00235530  Likelihood = -4.97080 
...
Iteration  51  Step Size = 0.00315935  Likelihood = -4.80712 

Convergence R-Square = 0.007055362 
Function value convergence.

> summary(garchOut)
..."

However, when I use the same code with some real prices, the code executes 
silently (from command line, or within a function), but /any/ command line call 
then gives:

"Problem: internal error: trying to set internal exit action in frame 0, must 
be between 1 and 5, while calling subroutine arc
"hresid 
"Use traceback() to see the call stack
"
"Error during wrapup: Invalid frame number (0) in set_frame
"Engine connection failure - shutting down S-PLUS recommended"

And subsequent commands, including traceback() or even q(), give:

"Problem: internal error: trying to set internal exit action in frame 1, must 
be between 1 and 0 
"Use traceback() to see the call stack
"Engine connection failure - shutting down S-PLUS recommended"

The object garchOut doesn't appear in Object Explorer. Closing down S+ then 
leads predictably to an Application Error.  I'm having difficulty locating the 
problem, as I have to restart S+ whenever I try a new avenue.  S+ Univariate 
garch works fine on the same prices data.  Note that the real 'r' is ~0.001.

My guess is that mgarch is generating some warning since 'r' cannot be 
successfully modelled, but that this is having some odd knock-on effect with a 
bug.  Any help would be much appreciated.

Thanks

Robert

This message is for the named person's use only. It may contain sensitive and 
private proprietary or legally privileged information. No confidentiality or 
privilege is waived or lost by any mistransmission. If you are not the intended 
recipient, please immediately delete it and all copies of it from your system, 
destroy any hard copies of it and notify the sender. You must not, directly or 
indirectly, use, disclose, distribute, print, or copy any part of this message 
if you are not the intended recipient. CREDIT SUISSE GROUP and each legal 
entity in the CREDIT SUISSE FIRST BOSTON or CREDIT SUISSE ASSET MANAGEMENT 
business units of CREDIT SUISSE FIRST BOSTON reserve the right to monitor all 
e-mail communications through its networks. Any views expressed in this message 
are those of the individual sender, except where the message states otherwise 
and the sender is authorized to state them to be the views of any such entity.
Unless otherwise stated, any pricing information given in this message is 
indicative only, is subject to change and does not constitute an offer to deal 
at any price quoted. Any reference to the terms of executed transactions should 
be treated as  preliminary only and subject to our formal written confirmation.



<Prev in Thread] Current Thread [Next in Thread>
  • Finmetrics Internal Error, Burbidge, Robert <=