Return-Path: <maiser@efs.mq.edu.au>
Received: from corot.bc.edu (corot.bc.edu [136.167.2.209])
by monet.bc.edu (8.8.7/8.8.7) with ESMTP id QAA50522
for <baum@monet.bc.edu>; Wed, 1 Sep 1999 16:00:19 -0400
From: maiser@efs.mq.edu.au
Received: (from root@localhost)
by corot.bc.edu (8.8.7/8.8.7) with X.500 id QAA214692
for baum@mail1.bc.edu; Wed, 1 Sep 1999 16:00:18 -0400
Received: from baldrick.ocs.mq.edu.au (baldrick.ocs.mq.edu.au [137.111.1.12])
by corot.bc.edu (8.8.7/8.8.7) with ESMTP id QAA182278
for <baum@bc.edu>; Wed, 1 Sep 1999 16:00:04 -0400
Received: from efs1.efs.mq.edu.au (efs1.efs.mq.edu.au [137.111.64.8])
by baldrick.ocs.mq.edu.au (8.9.2/8.9.2) with ESMTP id FAA25456
for <baum@bc.edu>; Thu, 2 Sep 1999 05:59:58 +1000 (EST)
Received: from EFS1/SpoolDir by efs1.efs.mq.edu.au (Mercury 1.40);
2 Sep 99 06:02:29 GMT+1000
Received: from SpoolDir by EFS1 (Mercury 1.40); 2 Sep 99 06:02:28 GMT+1000
To: baum@bc.edu
Date: Thu, 2 Sep 99 6:02:28 GMT+1000
Subject: Re:
Message-ID: <1666C9B7E5F@efs1.efs.mq.edu.au>
From: Thamana Lekprichakul <thamana@hawaii.edu>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Please help
Date: Sat, 31 Jul 1999 17:42:34 -1000
Errors-to: <rats-l-owner@efs.mq.edu.au>
Reply-to: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Sender: Maiser@efs1.efs.mq.edu.au
X-listname: <RATS-L@efs1.efs.mq.edu.au>
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; charset=US-ASCII
X-Mailer: Mercury MTS (Bindery) v1.40
Dear RATS Users
I try to compute mean for each column of a matrix and all I got is NA. Can
any one please help pointing out any error I may have made? RATS does not
seem to
recognize any syntax error. Here is my list of commands:
Do i=1,%Cols(TE)
Com SumTE = 0.0
Do j=1,%Rows(TE)
Com SumTE = TE(i,j) + SumTE
End Do J
Dis 'SumTE =' SumTE
Com MeanTE = SumTE/%Rows(TE)
Dis 'Mean =' MeanTE
Com TEBar(I) = MeanTE
End Do I
Dis 'Mean ='
Write TEBar
where TE is a rectangular matrix of dimension 89 x 5 and it is not emplty.
Also, is it possible to re-define values in a column of a matrix as a
series in RATS?
Many thanks in advance for your kind assistance.
Regards,
/Thamana
========================================================================
* Thamana LEKPRICHAKUL (Ph)1+808+944-7425 *
* East-West Center-Population Program (Fax)1+808+944-7490 *
* 1601 East-West Rd. E-Mail: thamana@hawaii.edu *
* Honolulu, Hawaii 96848-1601 *
* USA. *
========================================================================
---------- End of message ----------
From: Christopher F Baum <baum@bc.edu>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Re: Please help
Date: Sun, 01 Aug 1999 10:52:46 -0400
Errors-to: <rats-l-owner@efs.mq.edu.au>
Reply-to: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Sender: Maiser@efs1.efs.mq.edu.au
X-listname: <RATS-L@efs1.efs.mq.edu.au>
X-Mailer: Mulberry (MacOS) [1.4.4, s/n P020-300786-009] (via Mercury MTS (Bindery) v1.40)
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
Why not just multiply by a vector of (1/%rows(te))?
Kit Baum
--On Sat, Jul 31, 1999 17:42 -1000 Thamana Lekprichakul
<thamana@hawaii.edu> wrote:
> Dear RATS Users
>
> I try to compute mean for each column of a matrix and all I got is NA. Can
> any one please help pointing out any error I may have made? RATS does not
> seem to
> recognize any syntax error. Here is my list of commands:
>
> Do i=1,%Cols(TE)
> Com SumTE = 0.0
> Do j=1,%Rows(TE)
> Com SumTE = TE(i,j) + SumTE
> End Do J
> Dis 'SumTE =' SumTE
> Com MeanTE = SumTE/%Rows(TE)
> Dis 'Mean =' MeanTE
> Com TEBar(I) = MeanTE
> End Do I
> Dis 'Mean ='
> Write TEBar
>
> where TE is a rectangular matrix of dimension 89 x 5 and it is not emplty.
> Also, is it possible to re-define values in a column of a matrix as a
> series in RATS?
>
> Many thanks in advance for your kind assistance.
>
> Regards,
> /Thamana
>
>
> ========================================================================
> * Thamana LEKPRICHAKUL (Ph)1+808+944-7425 *
> * East-West Center-Population Program (Fax)1+808+944-7490 *
> * 1601 East-West Rd. E-Mail: thamana@hawaii.edu *
> * Honolulu, Hawaii 96848-1601
> * * USA.
> *
> ========================================================================
>
---------- End of message ----------
From: szuniga@entelchile.net (SERGIO ZUNIGA JARA)
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: RE: Please help
Date: Sun, 1 Aug 1999 13:02:20 -0600
Errors-to: <rats-l-owner@efs.mq.edu.au>
Reply-to: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Sender: Maiser@efs1.efs.mq.edu.au
X-listname: <RATS-L@efs1.efs.mq.edu.au>
MIME-Version: 1.0
Content-Type: text/plain;
Content-Transfer-Encoding: 7bit
X-Mailer: Microsoft Outlook Express 4.72.3110.5 (via Mercury MTS (Bindery) v1.40)
>Also, is it possible to re-define values in a column of a matrix as a
>series in RATS?
* example
dec rect TE2
dim TE2(3,2)
comp TE2 = ||1.0 , 2.0| 3.0,5.0| 6.5, 8.0||
all 3
comp start = 1
do i=1,3
comp end = start
set serie1 start end = TE2(i,1)
set serie2 start end = TE2(i,2)
comp start = start + 1
end
print /
ENTRY SERIE1 SERIE2
1 1.0000000000000 2.0000000000000
2 3.0000000000000 5.0000000000000
3 6.5000000000000 8.0000000000000
Cheers,
***************************************************
Sergio Zuniga szuniga@entelchile.net
Universidad Catolica del Norte
Larrondo 1281
Coquimbo - Chile
Tel.: 56-51-327248
***************************************************
---------- End of message ----------
From: <laurent.ferrara@ratp.fr>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: RE: Please help
Date: Mon, 2 Aug 1999 12:26:00 +0100
Errors-to: <rats-l-owner@efs.mq.edu.au>
Reply-to: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Sender: Maiser@efs1.efs.mq.edu.au
X-listname: <RATS-L@efs1.efs.mq.edu.au>
MIME-Version: 1.0
X-Mailer: Internet Mail Service (5.5.2448.0) (via Mercury MTS (Bindery) v1.40)
Content-Type: text/plain;
Content-Transfer-Encoding: quoted-printable
Why don't you use the function %sum()?
For instance:
dec vec TEbar(%cols(TE))
do i=3D1,%cols(TE)
com TEbar(i) =3D %sum(%xcol(TE,i))/%rows(TE)
end do i
write TEbar
Laurent Ferrara
RATP - Commercial Department
----------
De: Thamana Lekprichakul
A: RATS Discussion List
Objet: Please help
Date: dimanche 1 ao=FBt 1999 04:42
Dear RATS Users
I try to compute mean for each column of a matrix and all I got is NA. =
Can
any one please help pointing out any error I may have made? RATS does =
not
seem to
recognize any syntax error. Here is my list of commands:
Do i=3D1,%Cols(TE)
Com SumTE =3D 0.0
Do j=3D1,%Rows(TE)
Com SumTE =3D TE(i,j) + SumTE
End Do J
Dis 'SumTE =3D' SumTE
Com MeanTE =3D SumTE/%Rows(TE)
Dis 'Mean =3D' MeanTE
Com TEBar(I) =3D MeanTE
End Do I
Dis 'Mean =3D'
Write TEBar
where TE is a rectangular matrix of dimension 89 x 5 and it is not =
emplty.
Also, is it possible to re-define values in a column of a matrix as a
series in RATS?
Many thanks in advance for your kind assistance.
Regards,
/Thamana
=
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=
* Thamana LEKPRICHAKUL (Ph)1+808+944-7425 =
*
* East-West Center-Population Program (Fax)1+808+944-7490 =
*
* 1601 East-West Rd. E-Mail: thamana@hawaii.edu =
*
* Honolulu, Hawaii 96848-1601 =
*
* USA. =
*
=
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=
---------- End of message ----------
From: "scdoong" <scdoong@fcu.edu.tw>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: GARCH model
Date: Tue, 3 Aug 1999 10:36:58 +0800
Errors-to: <rats-l-owner@efs.mq.edu.au>
Reply-to: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Sender: Maiser@efs1.efs.mq.edu.au
X-listname: <RATS-L@efs1.efs.mq.edu.au>
X-Mailer: Microsoft Internet Mail 4.70.1155 (via Mercury MTS (Bindery) v1.40)
MIME-Version: 1.0
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: 7bit
Dear Sam,
May I have the code for the bivariate GARCH model ( the error follow the
GED)? Thanks.
By the way, good to hear that you'll come back soon.
Daniel
---------- End of message ----------
From: Rob Trevor <robt@efs.mq.edu.au>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: MacOS 8.6 and MacRATS 4.35
Date: Thu, 5 Aug 1999 17:40:39 +1000
Errors-to: <rats-l-owner@efs.mq.edu.au>
Reply-to: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Sender: Maiser@efs1.efs.mq.edu.au
X-listname: <RATS-L@efs1.efs.mq.edu.au>
Mime-Version: 1.0
Content-Type: text/plain; charset="us-ascii" ; format="flowed"
X-Mailer: Mercury MTS (Bindery) v1.40
Hi
Anyone had any problems running MacRATS (latest) under MacOS 8.6?
I've got a fairly big job which runs fine under 8.1 on an old PPC
laptop (and Windows and Unix), but bombs on a new 'bronze keyboard'
400MHz G3 PowerBook running 8.6. (Even when I start with all
extensions disabled.)
If anyone has noticed any problems, could you please let me know. It
may help me track down what my problem is.
Thanks
Rob Trevor
robt@efs.mq.edu.au
---------- End of message ----------
From: "Carl Moss" <carl@cueball.demon.co.uk>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Re: MacOS 8.6 and MacRATS 4.35
Date: Thu, 05 Aug 1999 21:06:22 +0100
Errors-to: <rats-l-owner@efs.mq.edu.au>
Reply-to: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Sender: Maiser@efs1.efs.mq.edu.au
X-listname: <RATS-L@efs1.efs.mq.edu.au>
X-Mailer: Microsoft Outlook Express Macintosh Edition - 4.5 (0410) (via Mercury MTS (Bindery) v1.40)
Mime-version: 1.0
Content-type: text/plain; charset="US-ASCII"
Content-transfer-encoding: 7bit
> Hi
>
> Anyone had any problems running MacRATS (latest) under MacOS 8.6?
>
> I've got a fairly big job which runs fine under 8.1 on an old PPC
> laptop (and Windows and Unix), but bombs on a new 'bronze keyboard'
> 400MHz G3 PowerBook running 8.6. (Even when I start with all
> extensions disabled.)
>
> If anyone has noticed any problems, could you please let me know. It
> may help me track down what my problem is.
>
> Thanks
>
> Rob Trevor
> robt@efs.mq.edu.au
I've not had similar with MacRATS, but I've been told that applications
under OS8.6 generally need more memory. Try increasing the memory
allocations by 300k - select the MacRATS application in the Finder, pull up
Get Info (Command-I) and select the option 'Memory' from the drop-down list
menu of things to show.
I've had to do this with a few applications to get them to work reliably.
The fact that it won't run with extensions disabled but used to work under
8.1 makes me think this is the most likely problem.
Regards
Carl
--
Carl Moss carl@cueball.demon.co.uk
---------- End of message ----------
From: Jason Morris <jasonwm@email.com>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Using logical operators on a series
Date: Mon, 9 Aug 1999 11:44:17 -0400 (EDT)
Errors-to: <rats-l-owner@efs.mq.edu.au>
Reply-to: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Sender: Maiser@efs1.efs.mq.edu.au
X-listname: <RATS-L@efs1.efs.mq.edu.au>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Mailer: mail.com (via Mercury MTS (Bindery) v1.40)
Hi,
I'm a final year postgrad econ student at the University of the West Indies,
Mona, Jamaica.
I'm having problems getting RATs to check each entry of a series and
performing the relevant logical operation.
E.g, look at the code below;
SET avg = 2485.7437
IF bdos>=avg.AND.bdos<(2*avg)
SET bdos = (avg+2*(SQRT(bdos-avg)))
ELSE IF bdos>=(2*avg).AND.bdos<(3*avg)
SET bdos = (avg+2*(SQRT(avg))+3*((bdos-(2*avg))**1./3.))
ElSE
PRINT / bdos
bdos is the series from 1986:1 to 95:1
The trouble is, the PRINT command either gives me nothing or gives me the
original series, depending on what I do.
When I run the code as above, I get the original bdos sereis. When I use
another name say, "SET NEWBDOS=...." in the SET statement instead of "SET
BDOS=..." I get nothing from the "PRINT / NEWBDOS" command. The program
doesn't crash or give me an error, it just gives me nothing!
The operation of the second ElSE If statement should be my output(all the
values of BDOS lie in htis range), but it doesn't work.
Apparently, it is using bdos as a matrix or something and NOT TESTING EACH
INDIVIDUAL VALUE OF BDOS, to see if the conditions hold true. I tried to
use a DO and DOFOR loops, but they just returned "tried to use integer
value, got matrix instead" error.
So how do I test each value in the series, short of working each value by
hand?
Thanks!
Jason W. Morris
Email : jasonwm@email.com or nosajwm@yahoo.co.uk
Homepage : http://go.to/jasonwm
-----------------------------------------------
FREE! The World's Best Email Address @email.com
Reserve your name now at http://www.email.com
---------- End of message ----------
From: szuniga@entelchile.net (SERGIO ZUNIGA JARA)
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: RE: Using logical operators on a series
Date: Mon, 9 Aug 1999 21:43:31 -0600
Errors-to: <rats-l-owner@efs.mq.edu.au>
Reply-to: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Sender: Maiser@efs1.efs.mq.edu.au
X-listname: <RATS-L@efs1.efs.mq.edu.au>
MIME-Version: 1.0
Content-Type: text/plain;
Content-Transfer-Encoding: 7bit
X-Mailer: Microsoft Outlook Express 4.72.3110.5 (via Mercury MTS (Bindery) v1.40)
>I'm having problems getting RATs to check each entry of a series and
>performing the relevant logical operation.
You may use only one SET instruction.
Here you have an numerical example (see pag. 1-28):
ALL 3
DATA(UNIT=INPUT) / bdos
100. 105. 110.
stat(noprint) bdos
dis %mean
105.00000
set mean = %mean
*if bdos<mean then bdos2=bdos+100
*if bdos=mean then bdos2=bdos+200
*if bdos>mean then bdos2=bdos+500
clear bdos2
set bdos2 = %if(bdos<mean, bdos+100., %if(bdos==mean,bdos+200, bdos+500))
print / bdos2
ENTRY BDOS2
1 200.00000000000
2 305.00000000000
3 610.00000000000
Cheers,
***************************************************
Sergio Zuniga szuniga@entelchile.net
Universidad Catolica del Norte
Coquimbo - Chile - Tel.: 56-51-327248
***************************************************
---------- End of message ----------
From: <jean-philippe.belloteau@ratp.fr>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: RE: Using logical operators on a series
Date: Tue, 10 Aug 1999 16:41:00 +0100
Errors-to: <rats-l-owner@efs.mq.edu.au>
Reply-to: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Sender: Maiser@efs1.efs.mq.edu.au
X-listname: <RATS-L@efs1.efs.mq.edu.au>
MIME-Version: 1.0
X-Mailer: Internet Mail Service (5.5.2448.0) (via Mercury MTS (Bindery) v1.40)
Content-Type: text/plain;
Content-Transfer-Encoding: quoted-printable
Dear Jason,
Try to use a test in a loop
For instance:
com avg =3D 2485.7437 ; * where avg is a constant
inquire(series=3Dbdos) deb fin ; * finding the first observation (i.e =
deb =3D
1986:1) and last observation (i.e fin =3D 1995:1)
DO t=3Ddeb,fin
IF (bdos(t)>=3Davg).AND.(bdos(t)<2*avg)
com bdos(t) =3D avg+2*SQRT(bdos(t)-avg)
ELSE IF (bdos(t)>=3D2*avg).AND.(bdos(t)<3*avg)
com bdos(t) =3D (avg+2*SQRT(avg)) + 3*((bdos(t)-2*avg)**(1./3.))
ENDDO
PRINT / bdos
Jean-Philip Bellotteau
RATP - Commercial Department
----------
De: Jason Morris
A: RATS Discussion List
Objet: Using logical operators on a series
Date: lundi 9 ao=FBt 1999 16:44
Hi,
I'm a final year postgrad econ student at the University of the West =
Indies,
Mona, Jamaica.
I'm having problems getting RATs to check each entry of a series and
performing the relevant logical operation.
E.g, look at the code below;
SET avg =3D 2485.7437
IF bdos>=3Davg.AND.bdos<(2*avg)
SET bdos =3D (avg+2*(SQRT(bdos-avg)))
ELSE IF bdos>=3D(2*avg).AND.bdos<(3*avg)
SET bdos =3D (avg+2*(SQRT(avg))+3*((bdos-(2*avg))**1./3.))
ElSE
PRINT / bdos
bdos is the series from 1986:1 to 95:1
The trouble is, the PRINT command either gives me nothing or gives me =
the
original series, depending on what I do.
When I run the code as above, I get the original bdos sereis. When I =
use
another name say, "SET NEWBDOS=3D...." in the SET statement instead of =
"SET
BDOS=3D..." I get nothing from the "PRINT / NEWBDOS" command. The =
program
doesn't crash or give me an error, it just gives me nothing!
The operation of the second ElSE If statement should be my output(all =
the
values of BDOS lie in htis range), but it doesn't work.
Apparently, it is using bdos as a matrix or something and NOT TESTING =
EACH
INDIVIDUAL VALUE OF BDOS, to see if the conditions hold true. I tried =
to
use a DO and DOFOR loops, but they just returned "tried to use integer
value, got matrix instead" error.
So how do I test each value in the series, short of working each value =
by
hand?
Thanks!
Jason W. Morris
Email : jasonwm@email.com or nosajwm@yahoo.co.uk
Homepage : http://go.to/jasonwm
-----------------------------------------------
FREE! The World's Best Email Address @email.com
Reserve your name now at http://www.email.com
---------- End of message ----------
From: "Maurice A. Harris" <maharr17@mailbox.syr.edu>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Phillips-Perron Unit Root Test
Date: Tue, 10 Aug 1999 12:20:11 -0400
Errors-to: <rats-l-owner@efs.mq.edu.au>
Reply-to: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Sender: Maiser@efs1.efs.mq.edu.au
X-listname: <RATS-L@efs1.efs.mq.edu.au>
Organization: Syracuse University, Finance Department
X-Mailer: Mozilla 4.61 [en] (Win95; I) (via Mercury MTS (Bindery) v1.40)
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
I would like to conduct the Phillips-Perron unit root test. For the
desired output, I need the mean reversion parameter estimate as well as
the associated test statistic. I've tried many of the routines posted
on the Estima web site but I've found that they only output the test
statistic. Any suggestions?
Thanks in advance.
---------- End of message ----------
From: "Christopher F. Baum" <baum@bc.edu>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Re: Phillips-Perron Unit Root Test
Date: Tue, 10 Aug 1999 12:39:24 -0400
Errors-to: <rats-l-owner@efs.mq.edu.au>
Reply-to: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Sender: Maiser@efs1.efs.mq.edu.au
X-listname: <RATS-L@efs1.efs.mq.edu.au>
X-Mailer: Mulberry (MacOS) [1.4.4, s/n P020-300786-009] (via Mercury MTS (Bindery) v1.40)
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
FInd the piece you want within ppunit.src and add a 'display' line
within the code! If you want it passed back, enter it as an additional
element of the formal parameter sequence, and declare it with a '*' prefix
to denote that it is a return.
--On Tue, Aug 10, 1999 12:20 PM -0400 "Maurice A. Harris"
<maharr17@mailbox.syr.edu> wrote:
> I would like to conduct the Phillips-Perron unit root test. For the
> desired output, I need the mean reversion parameter estimate as well as
> the associated test statistic. I've tried many of the routines posted
> on the Estima web site but I've found that they only output the test
> statistic. Any suggestions?
>
> Thanks in advance.
>
-----------------------------------------------------------------
Kit Baum baum@bc.edu http://fmwww.bc.edu/ec-v/baum.fac.html
---------- End of message ----------
From: "Jun Tomida" <jtomida@bc.mbn.or.jp>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Out-of-sumple forecast in VAR model with error-correction model
Date: Fri, 13 Aug 1999 16:14:15 +0900
Errors-to: <rats-l-owner@efs.mq.edu.au>
Reply-to: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Sender: Maiser@efs1.efs.mq.edu.au
X-listname: <RATS-L@efs1.efs.mq.edu.au>
MIME-Version: 1.0
Content-Type: multipart/mixed;
X-Mailer: Microsoft Outlook Express 5.00.2014.211 (via Mercury MTS (Bindery) v1.40)
This is a multi-part message in MIME format.
------=_NextPart_000_0015_01BEE5A6.E640F0A0
Content-Type: multipart/alternative;
boundary="----=_NextPart_001_0016_01BEE5A6.E640F0A0"
------=_NextPart_001_0016_01BEE5A6.E640F0A0
Content-Type: text/plain;
charset="iso-2022-jp"
Content-Transfer-Encoding: 7bit
Dear RATS Users:
I am constructing a VAR model with error-correction term using HP filtered
data.
After having estimated the model using 80:1 to 95:4 data , I tried to do
STEPS for
out-of-sumple forecast 96:1 to 99:2 in order to get forecasted "DRDMS"
using
"real" two dataseriese "DDMSSS" and "DDMSPR" , which were so-called
independent variables). But I couldn't get forecasted values 96:1 to 99:2.
Because I couldn't get residuals "RESIDDMS" from 96:1 to 99:2 , which were
calculated from the long-run equilibrium relationship equation "LRDMSEQ".
How can I get forecasted values?
I would really appreciate any help or advice.
Sincerely,
Jun Tomida
Sanwa Asset Management Co., Ltd.
1-1-3,OTEMACHI,CHIYODA-KU
TOKYO,100-0004
JAPAN
e-mail : jtomida@bc.mbn.or.jp
voice : 81-3-3214-3887
This is the program.
***************************************
CAL 1980 1 4
ALL 1999:2
OPEN DATA D:\WINRATS\WORK\NATREXTX.RAT
DATA(FORMAT=RAT) / BDSS BDPRBB USSS USPR RDMS
SEASONAL SEASONS 1980:1 2001:3
SET DMSPR = LOG(USPR)-LOG(BDPRBB)
SET LRDMS = LOG(RDMS)
SET DMSSS = USSS/BDSS
SMPL 80:1 95:4
SOURCE(NOECHO) D:\WINRATS\HPFILTER.SRC
@HPFILTER BDSS 80:1 95:4 HPBDSS
@HPFILTER USSS 80:1 95:4 HPUSSS
@HPFILTER DMSPR 80:1 95:4 HPDMSPR
SET HPDMSSS = HPUSSS/HPBDSS
LINREG(DEFINE=LRDMSEQ) LRDMS / RESIDDMS ;*
estimating the long-run equilibrium relationship equation "LRDMSEQ"
# HPDMSSS HPDMSPR
DIFF RESIDDMS 80:2 95:4 DRESIDDM
DIFF LRDMS 80:2 95:4 DRDMS
DIFF HPDMSSS 80:2 95:4 DDMSSS
DIFF HPDMSPR 80:2 95:4 DDMSPR
SYSTEM 1 TO 3
;* estimating the error-correction model using residuals from "LRDMSEQ"
VARIABLES DDMSSS DDMSPR DRDMS
LAGS 1 TO 8
DET CONSTANT RESIDDMS{1} ;*SEASONS{-2 to 0}
END(SYSTEM)
DEC VECT[SERIES] RESIDS(3)
ESTIMATE(OUTSIGMA=V) / RESIDS(1)
*PRINT / RESIDS(1) RESIDS(2) RESIDS(3)
SMPL 80:1 99:2
print / bdss usss
@HPFILTER BDSS 80:1 99:2 HPBDSS
@HPFILTER USSS 80:1 99:2 HPUSSS
@HPFILTER DMSPR 80:1 99:2 HPDMSPR
SET HPDMSSS = HPUSSS/HPBDSS
print / hpbdss hpusss hpdmsss lrdms
DIFF RESIDDMS 80:2 99:2 DRESIDDM
DIFF LRDMS 80:2 99:2 DRDMS
DIFF HPDMSSS 80:2 99:2 DDMSSS
DIFF HPDMSPR 80:2 99:2 DDMSPR
print / dresiddm drdms ddmsss ddmspr
STEPS(PRINT) 1 69 1982:2
;* doing STEPS for out-of-sumple forecast 96:1 to 99:2
# 3 DRDMSESHORT
GRAPH(KEY=UPLEFT,HEADER='') 2 ;* change the header
# DRDMS
# DRDMSESHORT
This is the output.
***********************************************************************
ENTRY DRESIDDM DRDMS DDMSSS DDMSPR
1980:01 NA NA NA NA
1980:02 -0.038315394774 -0.048957037018 -0.007023459482 -0.001574487662
1980:03 0.016192379132 0.005508572183 -0.007020438543 -0.001588083140
1980:04 0.104167795740 0.093343967071 -0.007032478287 -0.001627997370
1981:01 0.052245805116 0.041138922365 -0.007084090388 -0.001702172966
1981:02 0.099821716776 0.088286810779 -0.007177850333 -0.001810586453
1981:03 0.004225968338 -0.007821908274 -0.007288022945 -0.001941053373
1981:04 -0.026383563114 -0.038931466895 -0.007348006504 -0.002079597754
1982:01 0.056144520454 0.043136225188 -0.007349102366 -0.002220139150
1982:02 0.027584358433 0.014226865877 -0.007243911775 -0.002352148166
1982:03 0.046943245913 0.033376367400 -0.006997575333 -0.002475215897
1982:04 -0.010159667822 -0.023827380425 -0.006612706871 -0.002598259624
1983:01 -0.017223810839 -0.030922562865 -0.006110389906 -0.002728063548
1983:02 0.085065262973 0.071423822699 -0.005523197872 -0.002851140456
1983:03 0.047603266140 0.034114597179 -0.004908758483 -0.002951500113
1983:04 0.049734091054 0.036487187855 -0.004307145403 -0.003021501354
1984:01 -0.059579879933 -0.072543698561 -0.003759794895 -0.003065769596
1984:02 0.064509106251 0.051847710355 -0.003300644680 -0.003082869452
1984:03 0.105810858473 0.093431374115 -0.002947382809 -0.003080715409
1984:04 0.035566676229 0.023444174378 -0.002682071480 -0.003064921481
1985:01 0.095705354613 0.083919694834 -0.002462778408 -0.003013468351
1985:02 -0.099513498548 -0.110888821851 -0.002266520086 -0.002933771496
1985:03 -0.046841620769 -0.057775671454 -0.002086703394 -0.002840382833
1985:04 -0.124009435368 -0.134503085495 -0.001914315888 -0.002745148136
1986:01 -0.098566869757 -0.108663801348 -0.001754090817 -0.002659984652
1986:02 -0.011455199855 -0.021221008979 -0.001615560078 -0.002589275602
1986:03 -0.060216318247 -0.069740929189 -0.001498133679 -0.002540569465
1986:04 -0.008825707897 -0.018193210806 -0.001387956275 -0.002515377729
1987:01 -0.077938910524 -0.087240789253 -0.001279828857 -0.002517190191
1987:02 -0.008066931727 -0.017412378848 -0.001197184135 -0.002545803025
1987:03 0.002075233666 -0.007432597417 -0.001171685715 -0.002596583193
1987:04 -0.108414089748 -0.118144995656 -0.001191328669 -0.002654667559
1988:01 0.028888287573 0.018883708778 -0.001250439799 -0.002718377831
1988:02 0.057457831317 0.047167571820 -0.001339988715 -0.002778153573
1988:03 0.073744356912 0.063194352674 -0.001429910645 -0.002829693660
1988:04 -0.072529660171 -0.083292062298 -0.001518114976 -0.002867080992
1989:01 0.081939239350 0.071030356934 -0.001586556075 -0.002889118040
1989:02 0.081452483513 0.070469538635 -0.001626094501 -0.002896197722
1989:03 -0.005644329968 -0.016633624980 -0.001634961358 -0.002890410141
1989:04 -0.141942995353 -0.152862332074 -0.001598316237 -0.002872945686
1990:01 0.002017669040 -0.008734415795 -0.001495013984 -0.002842755456
1990:02 0.001255209521 -0.009224364639 -0.001317306198 -0.002799605671
1990:03 -0.076901293509 -0.086997695734 -0.001061400452 -0.002743144255
1990:04 -0.041159304673 -0.050781637215 -0.000722411387 -0.002681018652
1991:01 0.075368705390 0.066319937242 -0.000289324411 -0.002613719844
1991:02 0.119723657179 0.111297852424 0.000220919778 -0.002553049443
1991:03 -0.041771764214 -0.049617533877 0.000764338974 -0.002517323948
1991:04 -0.053230942275 -0.060652900652 0.001302100066 -0.002532572187
1992:01 0.075694289220 0.068475106461 0.001811253918 -0.002613861008
1992:02 -0.055701574578 -0.062960143985 0.002274128634 -0.002764220424
1992:03 -0.040036098006 -0.047608090399 0.002687680466 -0.002993497225
1992:04 0.068873742828 0.060654823501 0.003028976263 -0.003315264837
1993:01 0.068713530660 0.059501943388 0.003292325231 -0.003732775528
1993:02 -0.002419997431 -0.012928488337 0.003476236951 -0.004233824181
1993:03 -0.012879109302 -0.024884163402 0.003597900231 -0.004791285377
1993:04 0.086776005794 0.073224189034 0.003670497798 -0.005363240789
1994:01 0.005411506014 -0.009604068873 0.003703389865 -0.005911652584
1994:02 -0.018925330015 -0.035235560241 0.003693350076 -0.006409649928
1994:03 -0.039901129420 -0.057268907284 0.003650458968 -0.006838777173
1994:04 0.031820299196 0.013670057853 0.003575802168 -0.007187266081
1995:01 -0.099812149241 -0.118462651311 0.003478502772 -0.007454287045
1995:02 0.028556203186 0.009654694406 0.003353730066 -0.007647423154
1995:03 0.073475310830 0.054470472630 0.003202349702 -0.007796005140
1995:04 -0.012287926970 -0.031309344974 0.003015696087 -0.007913968295
1996:01 NA 0.020835637967 0.002786330227 -0.008015538310
1996:02 NA 0.030500749977 0.002510789730 -0.008102504283
1996:03 NA -0.012863441628 0.002207681635 -0.008166350997
1996:04 NA 0.019759076304 0.001898090778 -0.008198398036
1997:01 NA 0.091647112304 0.001588866538 -0.008191434086
1997:02 NA 0.021368688232 0.001286180312 -0.008149209972
1997:03 NA 0.008663045451 0.001000498189 -0.008072793068
1997:04 NA 0.002015865642 0.000752004353 -0.007966230289
1998:01 NA 0.025015166778 0.000554133177 -0.007839213891
1998:02 NA 0.001792988771 0.000403357287 -0.007705880603
1998:03 NA -0.072284321789 0.000297989907 -0.007580205800
1998:04 NA -0.016253453901 0.000247653004 -0.007479596033
1999:01 NA 0.073283326658 0.000233723064 -0.007413853924
1999:02 NA 0.051639565704 0.000234176558 -0.007387913962
Entry DRDMS
1982:02 0.026427733533
0.014226865877
1982:03 0.038110847223
0.033376367400
1982:04 -0.012595589943
-0.023827380425
1983:01 0.018336975395
-0.030922562865
1983:02 0.048820730447
0.071423822699
1983:03 0.016771876548
0.034114597179
1983:04 0.013818105905
0.036487187855
1984:01 -0.009732713324
-0.072543698561
1984:02 0.034938761305
0.051847710355
1984:03 0.035805230492
0.093431374115
1984:04 0.019995820288
0.023444174378
1985:01 0.018404836697
0.083919694834
1985:02 -0.059558711181
-0.110888821851
1985:03 -0.022461411844
-0.057775671454
1985:04 -0.115368100103
-0.134503085495
1986:01 -0.128413312068
-0.108663801348
1986:02 -0.058167288840
-0.021221008979
1986:03 -0.072595771003
-0.069740929189
1986:04 -0.014372375061
-0.018193210806
1987:01 -0.083650034318
-0.087240789253
1987:02 -0.024007269181
-0.017412378848
1987:03 -0.029970243870
-0.007432597417
1987:04 -0.033372063771
-0.118144995656
1988:01 0.053995077278
0.018883708778
1988:02 0.023061541894
0.047167571820
1988:03 0.051901674771
0.063194352674
1988:04 -0.027286596166
-0.083292062298
1989:01 0.046114368132
0.071030356934
1989:02 0.038586732798
0.070469538635
1989:03 -0.075022083148
-0.016633624980
1989:04 -0.146966529641
-0.152862332074
1990:01 -0.038014768733
-0.008734415795
1990:02 0.018541779077
-0.009224364639
1990:03 -0.080324638015
-0.086997695734
1990:04 -0.025051956681
-0.050781637215
1991:01 0.067602464865
0.066319937242
1991:02 0.075365571817
0.111297852424
1991:03 -0.079240191578
-0.049617533877
1991:04 -0.017395860241
-0.060652900652
1992:01 0.049963961301
0.068475106461
1992:02 0.023365568555
-0.062960143985
1992:03 -0.010989279312
-0.047608090399
1992:04 0.056660361018
0.060654823501
1993:01 0.103276127488
0.059501943388
1993:02 -0.003828780110
-0.012928488337
1993:03 -0.022816154615
-0.024884163402
1993:04 0.072738039274
0.073224189034
1994:01 -0.005637608796
-0.009604068873
1994:02 -0.085731334357
-0.035235560241
1994:03 -0.060384276078
-0.057268907284
1994:04 0.000602285096
0.013670057853
1995:01 -0.011021685649
-0.118462651311
1995:02 0.006668122988
0.009654694406
1995:03 0.026525632964
0.054470472630
1995:04 -0.083586088165
-0.031309344974
1996:01 -0.198780401663
0.020835637967
1996:02 NA
0.030500749977
1996:03 NA
-0.012863441628
1996:04 NA
0.019759076304
1997:01 NA
0.091647112304
1997:02 NA
0.021368688232
1997:03 NA
0.008663045451
1997:04 NA
0.002015865642
1998:01 NA
0.025015166778
1998:02 NA
0.001792988771
1998:03 NA
-0.072284321789
1998:04 NA
-0.016253453901
1999:01 NA
0.073283326658
1999:02 NA
0.051639565704
------=_NextPart_001_0016_01BEE5A6.E640F0A0
Content-Type: text/html;
charset="iso-2022-jp"
Content-Transfer-Encoding: quoted-printable
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">
<HTML><HEAD>
<META content=3D"text/html; charset=3Diso-2022-jp" =
http-equiv=3DContent-Type>
<META content=3D"MSHTML 5.00.2014.210" name=3DGENERATOR>
<STYLE></STYLE>
</HEAD>
<BODY bgColor=3D#ffffff>
<DIV><FONT size=3D2>Dear RATS Users:</FONT></DIV>
<DIV> </DIV>
<DIV><FONT size=3D2>I am constructing a VAR model with error-correction =
term using=20
HP filtered data</FONT><FONT size=3D2>.</FONT></DIV>
<DIV><FONT size=3D2>After having estimated the model using 80:1 to =
95:4 data=20
, I tried to do STEPS f</FONT><FONT size=3D2>or </FONT></DIV>
<DIV><FONT size=3D2>out-of-sumple forecast 96:1 to 99:2 in order to get =
forecasted=20
"DRDMS" ( using </FONT></DIV>
<DIV><FONT size=3D2>"real" two dataseriese "DDMSSS" </FONT><FONT =
size=3D2>and=20
</FONT><FONT size=3D2>"DDMSPR" , which were so-called </FONT></DIV>
<DIV><FONT size=3D2>independent variables). But I couldn't get =
</FONT><FONT=20
size=3D2>forecasted values 96:1 to 99:2.</FONT><FONT size=3D2> =
</FONT></DIV>
<DIV><FONT size=3D2>Because I couldn't get residuals</FONT><FONT =
size=3D2>=20
"RESIDDMS" </FONT><FONT size=3D2>from 96:1 to 99:2 , which =
were</FONT><FONT=20
size=3D2> </FONT></DIV>
<DIV><FONT size=3D2>calculated from the long-run equilibrium =
</FONT><FONT=20
size=3D2>relationship equation "LRDMSEQ".</FONT></DIV>
<DIV><FONT size=3D2></FONT> </DIV>
<DIV><FONT size=3D2>How can I get forecasted values?</FONT></DIV>
<DIV><FONT size=3D2>I would really appreciate any help or =
advice.</FONT></DIV>
<DIV><FONT size=3D2></FONT> </DIV>
<DIV><FONT size=3D2>Sincerely,</FONT></DIV>
<DIV><FONT size=3D2></FONT> </DIV>
<DIV><FONT size=3D2></FONT> </DIV>
<DIV><FONT size=3D2>Jun Tomida<BR>Sanwa Asset Management Co.,=20
Ltd.<BR>1-1-3,OTEMACHI,CHIYODA-KU<BR>TOKYO,100-0004<BR>JAPAN<BR>e-mail : =
<A=20
href=3D"mailto:jtomida@bc.mbn.or.jp">jtomida@bc.mbn.or.jp</A><BR>voice : =
81-3-3214-3887=20
<DIV><FONT size=3D2></FONT> </DIV>
<DIV><FONT size=3D2></FONT> </DIV>
<DIV><FONT size=3D2>
<DIV><FONT size=3D2></FONT> </DIV><FONT size=3D2>
<DIV>This is the program.</DIV>
<DIV>***************************************</DIV>
<DIV>CAL 1980 1 4<BR>ALL 1999:2</DIV>
<DIV> </DIV>
<DIV>OPEN DATA D:\WINRATS\WORK\NATREXTX.RAT</DIV>
<DIV> </DIV>
<DIV>DATA(FORMAT=3DRAT) / BDSS BDPRBB USSS USPR RDMS<BR>SEASONAL SEASONS =
1980:1=20
2001:3</DIV>
<DIV> </DIV>
<DIV>SET DMSPR =3D LOG(USPR)-LOG(BDPRBB)<BR>SET LRDMS =3D =
LOG(RDMS)<BR>SET DMSSS =3D=20
USSS/BDSS</DIV>
<DIV> </DIV>
<DIV>SMPL 80:1 95:4</DIV>
<DIV> </DIV>
<DIV>SOURCE(NOECHO) D:\WINRATS\HPFILTER.SRC<BR>@HPFILTER BDSS 80:1 95:4=20
HPBDSS<BR>@HPFILTER USSS 80:1 95:4 HPUSSS<BR>@HPFILTER DMSPR 80:1 95:4=20
HPDMSPR<BR>SET HPDMSSS =3D HPUSSS/HPBDSS</DIV>
<DIV> </DIV>
<DIV>LINREG(DEFINE=3DLRDMSEQ) LRDMS /=20
RESIDDMS  =
; =20
;* estimating the =
long-run=20
equilibrium <FONT size=3D2>relationship equation "LRDMSEQ"</FONT><BR># =
HPDMSSS=20
HPDMSPR</DIV>
<DIV> </DIV>
<DIV>DIFF RESIDDMS 80:2 95:4 DRESIDDM<BR>DIFF LRDMS 80:2 95:4 =
DRDMS<BR>DIFF=20
HPDMSSS 80:2 95:4=20
DDMSSS &=
nbsp; &n=
bsp; &nb=
sp; =20
<BR>DIFF HPDMSPR 80:2 95:4 DDMSPR</DIV>
<DIV> </DIV>
<DIV>SYSTEM 1 TO=20
3 =
&=
nbsp; &n=
bsp; &nb=
sp; &nbs=
p;  =
;=20
;* estimating the error-correction model using residuals from=20
"LRDMSEQ" <BR>VARIABLES DDMSSS DDMSPR DRDMS <BR>LAGS 1 TO =
8<BR>DET=20
CONSTANT RESIDDMS{1} ;*SEASONS{-2 to=20
0}<BR>END(SYSTEM)<BR>DEC VECT[SERIES] =
RESIDS(3)<BR>ESTIMATE(OUTSIGMA=3DV) /=20
RESIDS(1)<BR>*PRINT / RESIDS(1) RESIDS(2) RESIDS(3)</DIV>
<DIV> </DIV>
<DIV>SMPL 80:1 99:2<BR>print / bdss usss<BR>@HPFILTER BDSS 80:1 99:2=20
HPBDSS<BR>@HPFILTER USSS 80:1 99:2 HPUSSS<BR>@HPFILTER DMSPR 80:1 99:2=20
HPDMSPR<BR>SET HPDMSSS =3D HPUSSS/HPBDSS<BR>print / hpbdss hpusss =
hpdmsss=20
lrdms<BR>DIFF RESIDDMS 80:2 99:2 DRESIDDM<BR>DIFF LRDMS 80:2 99:2 =
DRDMS<BR>DIFF=20
HPDMSSS 80:2 99:2=20
DDMSSS &=
nbsp; &n=
bsp; &nb=
sp; <BR>DIFF=20
HPDMSPR 80:2 99:2 DDMSPR<BR>print / dresiddm drdms ddmsss =
ddmspr<BR>STEPS(PRINT)=20
1 69=20
1982:2 &=
nbsp; &n=
bsp; &nb=
sp; &nbs=
p; =20
;* doing STEPS <FONT size=3D2>for out-of-sumple forecast 96:1 =
to=20
99:2</FONT><BR># 3 DRDMSESHORT</DIV>
<DIV> </DIV>
<DIV>GRAPH(KEY=3DUPLEFT,HEADER=3D'') 2 ;* change the =
header<BR>#=20
DRDMS<BR># DRDMSESHORT<BR></DIV>
<DIV> </DIV>
<DIV><FONT size=3D2></FONT> </DIV>
<DIV><FONT size=3D2>This is the output.</FONT></DIV>
<DIV>********************************************************************=
***</DIV>
<DIV><FONT =
size=3D2> ENTRY =20
DRESIDDM =20
DRDMS =20
DDMSSS =20
DDMSPR<BR> 1980:01 =20
NA  =
; =20
NA  =
; =20
NA  =
; =20
NA<BR> 1980:02 -0.038315394774 -0.048957037018 =
-0.007023459482=20
-0.001574487662<BR> 1980:03 0.016192379132 =
0.005508572183=20
-0.007020438543 -0.001588083140<BR> 1980:04 =20
0.104167795740 0.093343967071 -0.007032478287=20
-0.001627997370<BR> 1981:01 0.052245805116 =
0.041138922365=20
-0.007084090388 -0.001702172966<BR> 1981:02 =20
0.099821716776 0.088286810779 -0.007177850333=20
-0.001810586453<BR> 1981:03 0.004225968338 =
-0.007821908274=20
-0.007288022945 -0.001941053373<BR> 1981:04 -0.026383563114=20
-0.038931466895 -0.007348006504 =
-0.002079597754<BR> 1982:01 =20
0.056144520454 0.043136225188 -0.007349102366=20
-0.002220139150<BR> 1982:02 0.027584358433 =
0.014226865877=20
-0.007243911775 -0.002352148166<BR> 1982:03 =20
0.046943245913 0.033376367400 -0.006997575333=20
-0.002475215897<BR> 1982:04 -0.010159667822 -0.023827380425=20
-0.006612706871 -0.002598259624<BR> 1983:01 -0.017223810839=20
-0.030922562865 -0.006110389906 =
-0.002728063548<BR> 1983:02 =20
0.085065262973 0.071423822699 -0.005523197872=20
-0.002851140456<BR> 1983:03 0.047603266140 =
0.034114597179=20
-0.004908758483 -0.002951500113<BR> 1983:04 =20
0.049734091054 0.036487187855 -0.004307145403=20
-0.003021501354<BR> 1984:01 -0.059579879933 -0.072543698561=20
-0.003759794895 -0.003065769596<BR> 1984:02 =20
0.064509106251 0.051847710355 -0.003300644680=20
-0.003082869452<BR> 1984:03 0.105810858473 =
0.093431374115=20
-0.002947382809 -0.003080715409<BR> 1984:04 =20
0.035566676229 0.023444174378 -0.002682071480=20
-0.003064921481<BR> 1985:01 0.095705354613 =
0.083919694834=20
-0.002462778408 -0.003013468351<BR> 1985:02 -0.099513498548=20
-0.110888821851 -0.002266520086 -0.002933771496<BR> 1985:03 =20
-0.046841620769 -0.057775671454 -0.002086703394=20
-0.002840382833<BR> 1985:04 -0.124009435368 -0.134503085495=20
-0.001914315888 -0.002745148136<BR> 1986:01 -0.098566869757=20
-0.108663801348 -0.001754090817 -0.002659984652<BR> 1986:02 =20
-0.011455199855 -0.021221008979 -0.001615560078=20
-0.002589275602<BR> 1986:03 -0.060216318247 -0.069740929189=20
-0.001498133679 -0.002540569465<BR> 1986:04 -0.008825707897=20
-0.018193210806 -0.001387956275 -0.002515377729<BR> 1987:01 =20
-0.077938910524 -0.087240789253 -0.001279828857=20
-0.002517190191<BR> 1987:02 -0.008066931727 -0.017412378848=20
-0.001197184135 -0.002545803025<BR> 1987:03 =
0.002075233666=20
-0.007432597417 -0.001171685715 -0.002596583193<BR> 1987:04 =20
-0.108414089748 -0.118144995656 -0.001191328669=20
-0.002654667559<BR> 1988:01 0.028888287573 =
0.018883708778=20
-0.001250439799 -0.002718377831<BR> 1988:02 =20
0.057457831317 0.047167571820 -0.001339988715=20
-0.002778153573<BR> 1988:03 0.073744356912 =
0.063194352674=20
-0.001429910645 -0.002829693660<BR> 1988:04 -0.072529660171=20
-0.083292062298 -0.001518114976 =
-0.002867080992<BR> 1989:01 =20
0.081939239350 0.071030356934 -0.001586556075=20
-0.002889118040<BR> 1989:02 0.081452483513 =
0.070469538635=20
-0.001626094501 -0.002896197722<BR> 1989:03 -0.005644329968=20
-0.016633624980 -0.001634961358 -0.002890410141<BR> 1989:04 =20
-0.141942995353 -0.152862332074 -0.001598316237=20
-0.002872945686<BR> 1990:01 0.002017669040 =
-0.008734415795=20
-0.001495013984 -0.002842755456<BR> 1990:02 =
0.001255209521=20
-0.009224364639 -0.001317306198 -0.002799605671<BR> 1990:03 =20
-0.076901293509 -0.086997695734 -0.001061400452=20
-0.002743144255<BR> 1990:04 -0.041159304673 -0.050781637215=20
-0.000722411387 -0.002681018652<BR> 1991:01 =20
0.075368705390 0.066319937242 -0.000289324411=20
-0.002613719844<BR> 1991:02 0.119723657179 =20
0.111297852424 0.000220919778 =
-0.002553049443<BR> 1991:03 =20
-0.041771764214 -0.049617533877 0.000764338974=20
-0.002517323948<BR> 1991:04 -0.053230942275 =
-0.060652900652 =20
0.001302100066 -0.002532572187<BR> 1992:01 =
0.075694289220 =20
0.068475106461 0.001811253918 =
-0.002613861008<BR> 1992:02 =20
-0.055701574578 -0.062960143985 0.002274128634=20
-0.002764220424<BR> 1992:03 -0.040036098006 =
-0.047608090399 =20
0.002687680466 -0.002993497225<BR> 1992:04 =
0.068873742828 =20
0.060654823501 0.003028976263 =
-0.003315264837<BR> 1993:01 =20
0.068713530660 0.059501943388 0.003292325231=20
-0.003732775528<BR> 1993:02 -0.002419997431 =
-0.012928488337 =20
0.003476236951 -0.004233824181<BR> 1993:03 -0.012879109302=20
-0.024884163402 0.003597900231=20
-0.004791285377<BR> 1993:04 0.086776005794 =20
0.073224189034 0.003670497798 =
-0.005363240789<BR> 1994:01 =20
0.005411506014 -0.009604068873 0.003703389865=20
-0.005911652584<BR> 1994:02 -0.018925330015 =
-0.035235560241 =20
0.003693350076 -0.006409649928<BR> 1994:03 -0.039901129420=20
-0.057268907284 0.003650458968=20
-0.006838777173<BR> 1994:04 0.031820299196 =20
0.013670057853 0.003575802168 =
-0.007187266081<BR> 1995:01 =20
-0.099812149241 -0.118462651311 0.003478502772=20
-0.007454287045<BR> 1995:02 0.028556203186 =20
0.009654694406 0.003353730066 =
-0.007647423154<BR> 1995:03 =20
0.073475310830 0.054470472630 0.003202349702=20
-0.007796005140<BR> 1995:04 -0.012287926970 =
-0.031309344974 =20
0.003015696087=20
-0.007913968295<BR> 1996:01  =
;=20
NA 0.020835637967 =20
0.002786330227=20
-0.008015538310<BR> 1996:02  =
;=20
NA 0.030500749977 =20
0.002510789730=20
-0.008102504283<BR> 1996:03  =
;=20
NA -0.012863441628 =20
0.002207681635=20
-0.008166350997<BR> 1996:04  =
;=20
NA 0.019759076304 =20
0.001898090778=20
-0.008198398036<BR> 1997:01  =
;=20
NA 0.091647112304 =20
0.001588866538=20
-0.008191434086<BR> 1997:02  =
;=20
NA 0.021368688232 =20
0.001286180312=20
-0.008149209972<BR> 1997:03  =
;=20
NA 0.008663045451 =20
0.001000498189=20
-0.008072793068<BR> 1997:04  =
;=20
NA 0.002015865642 =20
0.000752004353=20
-0.007966230289<BR> 1998:01  =
;=20
NA 0.025015166778 =20
0.000554133177=20
-0.007839213891<BR> 1998:02  =
;=20
NA 0.001792988771 =20
0.000403357287=20
-0.007705880603<BR> 1998:03  =
;=20
NA -0.072284321789 =20
0.000297989907=20
-0.007580205800<BR> 1998:04  =
;=20
NA -0.016253453901 =20
0.000247653004=20
-0.007479596033<BR> 1999:01  =
;=20
NA 0.073283326658 =20
0.000233723064=20
-0.007413853924<BR> 1999:02  =
;=20
NA 0.051639565704 =20
0.000234176558 -0.007387913962</FONT></DIV>
<DIV> </DIV>
<DIV><FONT size=3D2></FONT> </DIV>
<DIV> </DIV>
<DIV><FONT size=3D2> =20
Entry =20
DRDMS<BR> 1982:02 =20
0.026427733533<BR> &=
nbsp; =20
0.014226865877<BR> 1982:03 =20
0.038110847223<BR> &=
nbsp; =20
0.033376367400<BR> 1982:04 =20
-0.012595589943<BR> =
=20
-0.023827380425<BR> 1983:01 =20
0.018336975395<BR> &=
nbsp; =20
-0.030922562865<BR> 1983:02 =20
0.048820730447<BR> &=
nbsp; =20
0.071423822699<BR> 1983:03 =20
0.016771876548<BR> &=
nbsp; =20
0.034114597179<BR> 1983:04 =20
0.013818105905<BR> &=
nbsp; =20
0.036487187855<BR> 1984:01 =20
-0.009732713324<BR> =
=20
-0.072543698561<BR> 1984:02 =20
0.034938761305<BR> &=
nbsp; =20
0.051847710355<BR> 1984:03 =20
0.035805230492<BR> &=
nbsp; =20
0.093431374115<BR> 1984:04 =20
0.019995820288<BR> &=
nbsp; =20
0.023444174378<BR> 1985:01 =20
0.018404836697<BR> &=
nbsp; =20
0.083919694834<BR> 1985:02 =20
-0.059558711181<BR> =
=20
-0.110888821851<BR> 1985:03 =20
-0.022461411844<BR> =
=20
-0.057775671454<BR> 1985:04 =20
-0.115368100103<BR> =
=20
-0.134503085495<BR> 1986:01 =20
-0.128413312068<BR> =
=20
-0.108663801348<BR> 1986:02 =20
-0.058167288840<BR> =
=20
-0.021221008979<BR> 1986:03 =20
-0.072595771003<BR> =
=20
-0.069740929189<BR> 1986:04 =20
-0.014372375061<BR> =
=20
-0.018193210806<BR> 1987:01 =20
-0.083650034318<BR> =
=20
-0.087240789253<BR> 1987:02 =20
-0.024007269181<BR> =
=20
-0.017412378848<BR> 1987:03 =20
-0.029970243870<BR> =
=20
-0.007432597417<BR> 1987:04 =20
-0.033372063771<BR> =
=20
-0.118144995656<BR> 1988:01 =20
0.053995077278<BR> &=
nbsp; =20
0.018883708778<BR> 1988:02 =20
0.023061541894<BR> &=
nbsp; =20
0.047167571820<BR> 1988:03 =20
0.051901674771<BR> &=
nbsp; =20
0.063194352674<BR> 1988:04 =20
-0.027286596166<BR> =
=20
-0.083292062298<BR> 1989:01 =20
0.046114368132<BR> &=
nbsp; =20
0.071030356934<BR> 1989:02 =20
0.038586732798<BR> &=
nbsp; =20
0.070469538635<BR> 1989:03 =20
-0.075022083148<BR> =
=20
-0.016633624980<BR> 1989:04 =20
-0.146966529641<BR> =
=20
-0.152862332074<BR> 1990:01 =20
-0.038014768733<BR> =
=20
-0.008734415795<BR> 1990:02 =20
0.018541779077<BR> &=
nbsp; =20
-0.009224364639<BR> 1990:03 =20
-0.080324638015<BR> =
=20
-0.086997695734<BR> 1990:04 =20
-0.025051956681<BR> =
=20
-0.050781637215<BR> 1991:01 =20
0.067602464865<BR> &=
nbsp; =20
0.066319937242<BR> 1991:02 =20
0.075365571817<BR> &=
nbsp; =20
0.111297852424<BR> 1991:03 =20
-0.079240191578<BR> =
=20
-0.049617533877<BR> 1991:04 =20
-0.017395860241<BR> =
=20
-0.060652900652<BR> 1992:01 =20
0.049963961301<BR> &=
nbsp; =20
0.068475106461<BR> 1992:02 =20
0.023365568555<BR> &=
nbsp; =20
-0.062960143985<BR> 1992:03 =20
-0.010989279312<BR> =
=20
-0.047608090399<BR> 1992:04 =20
0.056660361018<BR> &=
nbsp; =20
0.060654823501<BR> 1993:01 =20
0.103276127488<BR> &=
nbsp; =20
0.059501943388<BR> 1993:02 =20
-0.003828780110<BR> =
=20
-0.012928488337<BR> 1993:03 =20
-0.022816154615<BR> =
=20
-0.024884163402<BR> 1993:04 =20
0.072738039274<BR> &=
nbsp; =20
0.073224189034<BR> 1994:01 =20
-0.005637608796<BR> =
=20
-0.009604068873<BR> 1994:02 =20
-0.085731334357<BR> =
=20
-0.035235560241<BR> 1994:03 =20
-0.060384276078<BR> =
=20
-0.057268907284<BR> 1994:04 =20
0.000602285096<BR> &=
nbsp; =20
0.013670057853<BR> 1995:01 =20
-0.011021685649<BR> =
=20
-0.118462651311<BR> 1995:02 =20
0.006668122988<BR> &=
nbsp; =20
0.009654694406<BR> 1995:03 =20
0.026525632964<BR> &=
nbsp; =20
0.054470472630<BR> 1995:04 =20
-0.083586088165<BR> =
=20
-0.031309344974<BR> 1996:01 =20
-0.198780401663<BR> =
=20
0.020835637967<BR> =20
1996:02 =20
NA<BR> &=
nbsp; =20
0.030500749977<BR> =20
1996:03 =20
NA<BR> &=
nbsp; =20
-0.012863441628<BR> =20
1996:04 =20
NA<BR> &=
nbsp; =20
0.019759076304<BR> =20
1997:01 =20
NA<BR> &=
nbsp; =20
0.091647112304<BR> =20
1997:02 =20
NA<BR> &=
nbsp; =20
0.021368688232<BR> =20
1997:03 =20
NA<BR> &=
nbsp; =20
0.008663045451<BR> =20
1997:04 =20
NA<BR> &=
nbsp; =20
0.002015865642<BR> =20
1998:01 =20
NA<BR> &=
nbsp; =20
0.025015166778<BR> =20
1998:02 =20
NA<BR> &=
nbsp; =20
0.001792988771<BR> =20
1998:03 =20
NA<BR> &=
nbsp; =20
-0.072284321789<BR> =20
1998:04 =20
NA<BR> &=
nbsp; =20
-0.016253453901<BR> =20
1999:01 =20
NA<BR> &=
nbsp; =20
0.073283326658<BR> =20
1999:02 =20
NA<BR> &=
nbsp; =20
0.051639565704</FONT></DIV>
<DIV> </DIV>
<DIV><FONT =
size=3D2><BR></FONT> </DIV></FONT></FONT></DIV> =20
</FONT></DIV>
<DIV><FONT size=3D2> </FONT></DIV></BODY></HTML>
------=_NextPart_001_0016_01BEE5A6.E640F0A0--
------=_NextPart_000_0015_01BEE5A6.E640F0A0
Content-Type: application/octet-stream;
name="natrextx.rat"
Content-Transfer-Encoding: base64
Content-Disposition: attachment;
filename="natrextx.rat"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------=_NextPart_000_0015_01BEE5A6.E640F0A0--
---------- End of message ----------
From: Myrvin Anthony <m.l.anthony@strath.ac.uk>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Generation of a reverse realisation of a time series.
Date: Mon, 16 Aug 1999 18:28:40 +0100
Errors-to: <rats-l-owner@efs.mq.edu.au>
Reply-to: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Sender: Maiser@efs1.efs.mq.edu.au
X-listname: <RATS-L@efs1.efs.mq.edu.au>
X-Mailer: Microsoft Internet E-mail/MAPI - 8.0.0.4211 (via Mercury MTS (Bindery) v1.40)
Dear Rats users,
I would like to generate the reverse realisations of several monthly and
quarterly time series that I am working with. This is my problem. I have a
time series Y(t), t = 1,....,T, and I want to generate a Z(t), t=1,...,T as
Z(1) = Y(T), Z(2) = Y(T-1),....., Z(T) = Y(1). (Thus Z(t) is the reverse
realisation of Y(t)).
Can anyone suggest how I may go about doing this?
Sincerely
Myrvin Anthony
---------- End of message ----------
From: "Tom Maycock" <tomm@estima.com>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Re: Generation of a reverse realisation of a time series.
Date: Mon, 16 Aug 1999 16:41:12 -0600
Errors-to: <rats-l-owner@efs.mq.edu.au>
Reply-to: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Sender: Maiser@efs1.efs.mq.edu.au
X-listname: <RATS-L@efs1.efs.mq.edu.au>
Organization: Estima
MIME-Version: 1.0
Content-type: text/plain; charset=US-ASCII
Content-transfer-encoding: 7BIT
X-mailer: Pegasus Mail for Win32 (v3.11) (via Mercury MTS (Bindery) v1.40)
> I would like to generate the reverse realisations of several monthly and
> quarterly time series that I am working with. This is my problem. I have a
> time series Y(t), t = 1,....,T, and I want to generate a Z(t), t=1,...,T as
> Z(1) = Y(T), Z(2) = Y(T-1),....., Z(T) = Y(1). (Thus Z(t) is the reverse
> realisation of Y(t)).
>
Myrvin:
There are a couple of ways to do this. First, you can always use SET
and the "T" subscript (or lag/lead notation). For example, this
sample program creates Y (as a trend sereis so you can see the
results easily), and then sets Z as the reverse of Y:
all 10
compute lastobs = 10
set Y = t
set Z = Y(lastobs-t+1)
print
You can also use the ORDER command to flip the ordering of a series.
Just define a trend series, set Z equal to Y, use order to sort the
trend series in descending order, and include your Z series on the
list of additional series to be sorted along with the trend series.
For example:
all 10
set y = t**2
set trend = t
print
set z = y
order(decreasing) trend / z
print
Sincerely,
Tom Maycock
Estima
--
------------------------------------------------------------
| Estima | Sales: (800) 822-8038 |
| P.O. Box 1818 | (847) 864-8772 |
| Evanston, IL 60204-1818 | Support: (847) 864-1910 |
| USA | Fax: (847) 864-6221 |
| http://www.estima.com | estima@estima.com |
------------------------------------------------------------
---------- End of message ----------
From: Ferdaus Hossain <hossain@AESOP.RUTGERS.EDU>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Zivot and Andrews' unit root test
Date: Wed, 18 Aug 1999 12:08:41 -0400
Errors-to: <rats-l-owner@efs.mq.edu.au>
Reply-to: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Sender: Maiser@efs1.efs.mq.edu.au
X-listname: <RATS-L@efs1.efs.mq.edu.au>
MIME-version: 1.0
X-Mailer: Microsoft Outlook Express 5.00.2314.1300 (via Mercury MTS (Bindery) v1.40)
Content-type: text/plain; charset="iso-8859-1"
Content-transfer-encoding: 7bit
Dear Rats users:
Could someone please help me find the Rats procedure that implements the
Zivot and Andrews unit-root test (Ref: Zivot and Andrews (1992): Further
evidence on great crash, hte oil-price shock, and the unit-root hypothesis,
Journal of Business and Economic Statistics, Vol. 10 No. 3).
Thank you in advance.
Sincerely
Ferdaus Hosain
Rutgers University
email: hossain@aesop.rutgers.edu
---------- End of message ----------
From: Binelli Maurizio <mbinelli@IFAM.IT>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: FIND Function
Date: Wed, 18 Aug 1999 19:14:41 +0200
Errors-to: <rats-l-owner@efs.mq.edu.au>
Reply-to: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Sender: Maiser@efs1.efs.mq.edu.au
X-listname: <RATS-L@efs1.efs.mq.edu.au>
MIME-Version: 1.0
X-Mailer: Internet Mail Service (5.0.1460.8) (via Mercury MTS (Bindery) v1.40)
Content-Type: text/plain;
Content-Transfer-Encoding: quoted-printable
Dear Rats People,
I'm trying to optimize some hyperparameter regarding forecast
performance statistics (Theil) of my own built BVAR using the the =
function
FIND. The problem as it's possible see below, refers to the output of =
that
function: 1-it shows 9 parameters (number of variables in the system) =
2-
something very strange at the last row. Moreover, I would like to
"automatically" the result of that function.
I wuold be very grateful for any help on the topic of BVAR prior
optimization.
Thank you in advance!
Maurizio
OUTPUT:
Estimation by Simplex
Variable Coeff
*****************************************
1. REL104 0.05199
2. REL105 0.01356
3. REL107 7.78856e-004
4. REL108 5.92050e-005
5. REL109 0.00584
6. 4.78093e+180
7. 2.85747e+161
8. 2.31368e-152
9. =B6=EF^=8FD'??=F4=F2=DD=FB=BA~=A6? 8.80067e+199
---------- End of message ----------
From: "Dr. J. Dannenbaum" <dannen@hermes1.econ.uni-hamburg.de>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: MAXIMIZE and the treatment of negative values
Date: Thu, 19 Aug 1999 11:28:32 +0100
Errors-to: <rats-l-owner@efs.mq.edu.au>
Reply-to: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Sender: Maiser@efs1.efs.mq.edu.au
X-listname: <RATS-L@efs1.efs.mq.edu.au>
Organization: Universität Hamburg
X-Mailer: Microsoft Internet E-Mail/MAPI - 8.0.0.4211 (via Mercury MTS (Bindery) v1.40)
Hello,
I want to test for the hyperparameter of a Kalman filter using the maximum
likelihood function and MAXIMIZE(method = BFGS). As the hyperparameter
contains standard errors (or variances), negative values makes no sence. I
chose to maximize over standard errors, which will be squared in the frml
instruction (see below). My questions:
a) Is the BFGS procedure still valid?
b) Can I use the marginal significance for the estimated standard errors to
get information on the significance of the variance?
c) Can I simply drop the negative sign on the calculate standard errors,
given by MAXIMIZE?
Thanks
Joachim
The RATS code looks essentially like:
nonlin sigma om11 om33
compute sigma = sqrt(sigmastart)
compute om11 = sqrt(varianz(1))
compute om33 = sqrt(varianz(2))
frml logl = $
(omega = %diag(||om11*om11,om33*om33||)), $
(beta = ||gamma(1,t-1)|gamma(2,t-1)||), $
(pm = ||p(1,t-1),p(2,t-1)| $
p(3,t-1),p(4,t-1)| $
(x = ||1.0,lnysa(t)||), (gamtt = trans*beta), $
(ptt = trans*pm*tr(trans)+r*omega*tr(r)), (ytt = x*gamtt), $
(error = lnlsa(t)-ytt(1,1)), (f = sigma*sigma + x*ptt*tr(x)), $
(kg = (1.0/f(1,1))*ptt*tr(x)), (beta = gamtt + kg*error), $
(pm = ptt - kg*x*ptt), (gamma(1,t)=beta(1,1)), $
(gamma(2,t)=beta(2,1)),$
(p(1,t)=pm(1,1)),(p(2,t)=pm(1,2)),(p(3,t)=pm(1,3)),(p(4,t)=pm(2,1)), $
(-0.5) * (log(f(1,1))+error*error/f(1,1))
nlpar(sub=1000,criterion=value,cvcrit=0.00000001)
maximize(method=simplex,iterations=5,recursive) logl 1960:2 1994:4
maximize(method=bfgs,iterations=200,recursive) logl 1960:2 1994:4
------------------------------------------------------------------------
----
Dr. Joachim Dannenbaum
Institut fuer Aussenhandel und Wirtschaftsintegration
Universitaet Hamburg
Von-Melle-Park 5
20146 Hamburg
------------------------------------------------------------------------
----
---------- End of message ----------
From: Binelli Maurizio <mbinelli@IFAM.IT>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: FIND Function
Date: Wed, 18 Aug 1999 19:14:41 +0200
Errors-to: <rats-l-owner@efs.mq.edu.au>
Reply-to: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Sender: Maiser@efs1.efs.mq.edu.au
X-listname: <RATS-L@efs1.efs.mq.edu.au>
MIME-Version: 1.0
X-Mailer: Internet Mail Service (5.0.1460.8) (via Mercury MTS (Bindery) v1.40)
Content-Type: text/plain;
Content-Transfer-Encoding: quoted-printable
Dear Rats People,
I'm trying to optimize some hyperparameter regarding forecast
performance statistics (Theil) of my own built BVAR using the the =
function
FIND. The problem as it's possible see below, refers to the output of =
that
function: 1-it shows 9 parameters (number of variables in the system) =
2-
something very strange at the last row. Moreover, I would like to
"automatically" the result of that function.
I wuold be very grateful for any help on the topic of BVAR prior
optimization.
Thank you in advance!
Maurizio
OUTPUT:
Estimation by Simplex
Variable Coeff
*****************************************
1. REL104 0.05199
2. REL105 0.01356
3. REL107 7.78856e-004
4. REL108 5.92050e-005
5. REL109 0.00584
6. 4.78093e+180
7. 2.85747e+161
8. 2.31368e-152
9. =B6=EF^=8FD'??=F4=F2=DD=FB=BA~=A6? 8.80067e+199
---------- End of message ----------
From: Yong Glasure <yglasure@netscape.net>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject:
Date: 19 Aug 99 16:48:53 PDT
Errors-to: <rats-l-owner@efs.mq.edu.au>
Reply-to: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Sender: Maiser@efs1.efs.mq.edu.au
X-listname: <RATS-L@efs1.efs.mq.edu.au>
X-Mailer: USANET web-mailer (M3.2.0.53) (via Mercury MTS (Bindery) v1.40)
Mime-Version: 1.0
Content-Type: text/plain; charset=US-ASCII
Content-Transfer-Encoding: quoted-printable
Dear Colleague
When I compiled my program, I received the following message: "SR4: Tried=
to
use Series Number -30. (-series n1 n2 triples are no longer legal." Does=
anyone know how to correct this mistake?
Thanks in advance.
Yong U. Glasure =
5603 86th Street =
Lubbock, Texas 79424 =
(806) 798-3625
yglasure@netscape.net
____________________________________________________________________
Get your own FREE, personal Netscape WebMail account today at http://webm=
ail.netscape.com.
---------- End of message ----------
From: Simon van Norden <Simon.van-Norden@hec.ca>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Re: negative series numbers
Date: Thu, 19 Aug 1999 20:36:04 -0400
Errors-to: <rats-l-owner@efs.mq.edu.au>
Reply-to: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Sender: Maiser@efs1.efs.mq.edu.au
X-listname: <RATS-L@efs1.efs.mq.edu.au>
Organization: Ecole des Hautes Etudes Commerciales
X-Mailer: Mozilla 4.51 [en] (Win98; U) (via Mercury MTS (Bindery) v1.40)
MIME-Version: 1.0
Content-Type: text/plain; charset=iso-8859-1
Content-Transfer-Encoding: quoted-printable
It's probably because you're using a procedure and giving it a supplement=
ary
card that lists several lags, such as=20
# constant x1 x2{1 to 4}
The {1 to 4} causes the problem if the procedure uses the supplementary c=
ard
with an ENTER(VARYING) command.
Trying defining
SET X2L1 =3D X2(T-1)
SET X2L2 =3D X2(T-2)
etc.=20
Then use the supplementary card
# CONSTANT X1 X2L1 X2L2 X2L3 X2L4
Yong Glasure wrote:
>=20
> Dear Colleague
>=20
> When I compiled my program, I received the following message: "SR4: Tri=
ed to
> use Series Number -30. (-series n1 n2 triples are no longer legal." Do=
es
> anyone know how to correct this mistake?
>=20
> Thanks in advance.
>=20
> Yong U. Glasure
> 5603 86th Street
> Lubbock, Texas 79424
> (806) 798-3625
> yglasure@netscape.net
>=20
> ____________________________________________________________________
> Get your own FREE, personal Netscape WebMail account today at http://we=
bmail.netscape.com.
--=20
Simon van Norden, Prof. agr=E9g=E9, www.hec.ca/pages/simon.van-norden
Service de l'enseignement de la finance, =C9cole des H.E.C.
3000 Cote-Sainte-Catherine, Montreal QC, CANADA H3T 2A7
simon.van-norden@hec.ca or (514)340-6781 or fax:(514)340-5632
---------- End of message ----------
From: "Estima" <tomm@estima.com>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Re: negative series numbers
Date: Fri, 20 Aug 1999 09:57:45 -0600
Errors-to: <rats-l-owner@efs.mq.edu.au>
Reply-to: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Sender: Maiser@efs1.efs.mq.edu.au
X-listname: <RATS-L@efs1.efs.mq.edu.au>
Organization: Estima
MIME-Version: 1.0
Content-type: text/plain; charset=US-ASCII
Content-transfer-encoding: 7BIT
X-mailer: Pegasus Mail for Win32 (v3.11) (via Mercury MTS (Bindery) v1.40)
> It's probably because you're using a procedure and giving it a supplementary
> card that lists several lags, such as
>
> # constant x1 x2{1 to 4}
>
> The {1 to 4} causes the problem if the procedure uses the supplementary card
> with an ENTER(VARYING) command.
>
> Trying defining
>
> SET X2L1 = X2(T-1)
> SET X2L2 = X2(T-2)
> etc.
You can also use the supplementary card to define an equation, and
then use the %EQNCOEFFS function to get the proper series/lag numbers
off the regressor list (the problem with just trying to pull series
numbers directly from the array is that RATS uses negative integers
to code elements of the list like {, }, and "TO").
In any case, I suspect this probably isn't the cause of this
particular problem (if it was, you'd see numbers like -32767, not
-30). There are several other syntax mistakes that could potentially
produce this kind of problem:
> > When I compiled my program, I received the following message: "SR4: Tried to
> > use Series Number -30. (-series n1 n2 triples are no longer legal." Does
> > anyone know how to correct this mistake?
To offer any further help, we'd need to know exactly which
instruction produced the error message, and may in fact need to see
the rest of the program (at least the parts that lead up to the
error).
Sincerely,
Tom Maycock
Estima
--
------------------------------------------------------------
| Estima | Sales: (800) 822-8038 |
| P.O. Box 1818 | (847) 864-8772 |
| Evanston, IL 60204-1818 | Support: (847) 864-1910 |
| USA | Fax: (847) 864-6221 |
| http://www.estima.com | estima@estima.com |
------------------------------------------------------------
---------- End of message ----------
From: richard.priestley@bi.no
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Re: Andrews structural stability tests.
Date: Mon, 23 Aug 1999 10:49:57 +0200
Errors-to: <rats-l-owner@efs.mq.edu.au>
Reply-to: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Sender: Maiser@efs1.efs.mq.edu.au
X-listname: <RATS-L@efs1.efs.mq.edu.au>
Mime-Version: 1.0
Content-type: text/plain; charset=us-ascii
X-Mailer: Mercury MTS (Bindery) v1.40
I have a garch-m model where the mean is a function of a set of
instruments. I want to test for structural stability of the coefficients
wrt the instruments using Andrews, 1993, Tests for parameter instability
and structural change with unknown chnage point, Econometrica 61, 821-856,
type tests. This type of test has been used by Ghysels, 1997, On stable
factor structures in the pricing of risk...., Journal of Finance, in a GMM
framework.
Does anybody have RATS code for this type of test that may help me?
Thanks in advance
Richard Priestley
Associate Professor of Financial Economics
Department of Financial Economics
Norwegian School of Management
Elias Smiths vei 15
Sandvika
N1301
Norway
TEL: + 47 67557104
FAX: + 47 67557675
Email: richard.priestley@bi.no
---------- End of message ----------
From: "Paul Barry" <barnett@tinet.ie>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Estimation for masters thesis
Date: Tue, 24 Aug 1999 20:48:51 +0100
Errors-to: <rats-l-owner@efs.mq.edu.au>
Reply-to: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Sender: Maiser@efs1.efs.mq.edu.au
X-listname: <RATS-L@efs1.efs.mq.edu.au>
Organization:
MIME-Version: 1.0
Content-Type: multipart/alternative;
X-Mailer: Microsoft Outlook Express 5.00.2314.1300 (via Mercury MTS (Bindery) v1.40)
This is a multi-part message in MIME format.
------=_NextPart_000_0009_01BEEE72.129B4280
Content-Type: text/plain;
charset="iso-8859-1"
Content-Transfer-Encoding: quoted-printable
hello,
I have just started using rats as previously I used shazam and so I am a =
novice.
I would be very grateful for any help in the following areas.
1) applying Johansen's maximum likelihood procedure for estimating =
cointegration relationships.
2) unit root testing
3) using the vector error correction model in cointegration analysis
4) testing for the existence of 0 or more cointegrating vectors
5) determining the lag order of the model
6) applying ordinary least squares
7) applying restrictions to the ordinary least squares estimates.
thank you,
Stephen.
------=_NextPart_000_0009_01BEEE72.129B4280
Content-Type: text/html;
charset="iso-8859-1"
Content-Transfer-Encoding: quoted-printable
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">
<HTML><HEAD>
<META content=3D"text/html; charset=3Diso-8859-1" =
http-equiv=3DContent-Type>
<META content=3D"MSHTML 5.00.2614.3401" name=3DGENERATOR>
<STYLE></STYLE>
</HEAD>
<BODY bgColor=3D#ffffff>
<DIV><FONT face=3DArial size=3D2>hello,</FONT></DIV>
<DIV><FONT face=3DArial size=3D2>I have just started using rats as =
previously I used=20
shazam and so I am a novice.</FONT></DIV>
<DIV><FONT face=3DArial size=3D2>I would be very grateful for any help =
in the=20
following areas.</FONT></DIV>
<DIV><FONT face=3DArial size=3D2>1) applying Johansen's maximum =
likelihood procedure=20
for estimating cointegration relationships.</FONT></DIV>
<DIV><FONT face=3DArial size=3D2>2) unit root testing</FONT></DIV>
<DIV><FONT face=3DArial size=3D2>3) using the vector error correction =
model in=20
cointegration analysis</FONT></DIV>
<DIV><FONT face=3DArial size=3D2>4) testing for the existence of 0 or =
more=20
cointegrating vectors</FONT></DIV>
<DIV><FONT face=3DArial size=3D2>5) determining the lag order of the=20
model</FONT></DIV>
<DIV><FONT face=3DArial size=3D2>6) applying ordinary least =
squares</FONT></DIV>
<DIV><FONT face=3DArial size=3D2>7) applying restrictions to the =
ordinary least=20
squares estimates.</FONT></DIV>
<DIV> </DIV>
<DIV><FONT face=3DArial size=3D2>thank you,</FONT></DIV>
<DIV><FONT face=3DArial size=3D2>Stephen.</FONT></DIV></BODY></HTML>
------=_NextPart_000_0009_01BEEE72.129B4280--
---------- End of message ----------
From: "Gregory, Richard" <RGregory@VEDP.state.va.us>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: RE: Estimation for masters thesis
Date: Tue, 24 Aug 1999 16:05:04 -0400
Errors-to: <rats-l-owner@efs.mq.edu.au>
Reply-to: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Sender: Maiser@efs1.efs.mq.edu.au
X-listname: <RATS-L@efs1.efs.mq.edu.au>
MIME-Version: 1.0
X-Mailer: Internet Mail Service (5.5.2448.0) (via Mercury MTS (Bindery) v1.40)
Content-Type: text/plain;
You should be able to find many of these at www.estima.com
-----Original Message-----
From: Paul Barry [mailto:barnett@tinet.ie]
Sent: Tuesday, August 24, 1999 3:49 PM
To: RATS Discussion List
Subject: Estimation for masters thesis
This is a multi-part message in MIME format.
------=_NextPart_000_0009_01BEEE72.129B4280
Content-Type: text/plain;
charset="iso-8859-1"
Content-Transfer-Encoding: quoted-printable
hello,
I have just started using rats as previously I used shazam and so I am a =
novice.
I would be very grateful for any help in the following areas.
1) applying Johansen's maximum likelihood procedure for estimating =
cointegration relationships.
2) unit root testing
3) using the vector error correction model in cointegration analysis
4) testing for the existence of 0 or more cointegrating vectors
5) determining the lag order of the model
6) applying ordinary least squares
7) applying restrictions to the ordinary least squares estimates.
thank you,
Stephen.
------=_NextPart_000_0009_01BEEE72.129B4280
Content-Type: text/html;
charset="iso-8859-1"
Content-Transfer-Encoding: quoted-printable
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">
<HTML><HEAD>
<META content=3D"text/html; charset=3Diso-8859-1" =
http-equiv=3DContent-Type>
<META content=3D"MSHTML 5.00.2614.3401" name=3DGENERATOR>
<STYLE></STYLE>
</HEAD>
<BODY bgColor=3D#ffffff>
<DIV><FONT face=3DArial size=3D2>hello,</FONT></DIV>
<DIV><FONT face=3DArial size=3D2>I have just started using rats as =
previously I used=20
shazam and so I am a novice.</FONT></DIV>
<DIV><FONT face=3DArial size=3D2>I would be very grateful for any help =
in the=20
following areas.</FONT></DIV>
<DIV><FONT face=3DArial size=3D2>1) applying Johansen's maximum =
likelihood procedure=20
for estimating cointegration relationships.</FONT></DIV>
<DIV><FONT face=3DArial size=3D2>2) unit root testing</FONT></DIV>
<DIV><FONT face=3DArial size=3D2>3) using the vector error correction =
model in=20
cointegration analysis</FONT></DIV>
<DIV><FONT face=3DArial size=3D2>4) testing for the existence of 0 or =
more=20
cointegrating vectors</FONT></DIV>
<DIV><FONT face=3DArial size=3D2>5) determining the lag order of the=20
model</FONT></DIV>
<DIV><FONT face=3DArial size=3D2>6) applying ordinary least =
squares</FONT></DIV>
<DIV><FONT face=3DArial size=3D2>7) applying restrictions to the =
ordinary least=20
squares estimates.</FONT></DIV>
<DIV> </DIV>
<DIV><FONT face=3DArial size=3D2>thank you,</FONT></DIV>
<DIV><FONT face=3DArial size=3D2>Stephen.</FONT></DIV></BODY></HTML>
------=_NextPart_000_0009_01BEEE72.129B4280--
---------- End of message ----------
From: Ferdaus Hossain <hossain@AESOP.RUTGERS.EDU>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Re: Estimation for masters thesis
Date: Tue, 24 Aug 1999 16:26:22 -0400
Errors-to: <rats-l-owner@efs.mq.edu.au>
Reply-to: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Sender: Maiser@efs1.efs.mq.edu.au
X-listname: <RATS-L@efs1.efs.mq.edu.au>
MIME-version: 1.0
X-Mailer: Microsoft Outlook Express 5.00.2314.1300 (via Mercury MTS (Bindery) v1.40)
Content-type: text/plain; charset="iso-8859-1"
Content-transfer-encoding: 7bit
For cointegration analysis, you really should have CATS which is an addon
for RATS. CATS is specifically written for CI analysis. However, you may
be able to get by RATS. Check their website for the procedures dealing with
you your specific needs.
Good Luck
Ferdaus
---------- End of message ----------
From: "Estima" <tomm@estima.com>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Re: Estimation for masters thesis
Date: Tue, 24 Aug 1999 15:42:29 -0600
Errors-to: <rats-l-owner@efs.mq.edu.au>
Reply-to: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Sender: Maiser@efs1.efs.mq.edu.au
X-listname: <RATS-L@efs1.efs.mq.edu.au>
Organization: Estima
MIME-Version: 1.0
Content-type: text/plain; charset=US-ASCII
Content-transfer-encoding: 7BIT
X-mailer: Pegasus Mail for Win32 (v3.11) (via Mercury MTS (Bindery) v1.40)
> I would be very grateful for any help in the following areas.
> 1) applying Johansen's maximum likelihood procedure for estimating =
> cointegration relationships.
As suggested, serious cointegration analysis is best done using the
CATS add-on to RATS.
> 2) unit root testing
Simple DFUNIT and PPUNIT procedures are included with RATS and
discussed (briefly) in the RATS manual. The RATS web page provides
many other more advanced and/or specialized unit root tests. See
URADF.SRC for a good general procedure.
> 5) determining the lag order of the model
> 6) applying ordinary least squares
> 7) applying restrictions to the ordinary least squares estimates.
This is all covered in the RATS users manual. The RATS Handbook for
Econometric Time Series also covers most of this, and has proven
quite helpful for many beginning users. You can order from us at
Estima, or pretty much any other bookseller.
Sincerely,
Tom Maycock
Estima
--
------------------------------------------------------------
| Estima | Sales: (800) 822-8038 |
| P.O. Box 1818 | (847) 864-8772 |
| Evanston, IL 60204-1818 | Support: (847) 864-1910 |
| USA | Fax: (847) 864-6221 |
| http://www.estima.com | estima@estima.com |
------------------------------------------------------------
---------- End of message ----------
From: Woo Kai-Yin <kywoo@i-cable.com>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: RE:request for program
Date: Sat, 28 Aug 1999 11:33:20 +0800
Errors-to: <rats-l-owner@efs.mq.edu.au>
Reply-to: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Sender: Maiser@efs1.efs.mq.edu.au
X-listname: <RATS-L@efs1.efs.mq.edu.au>
X-Mailer: Mozilla 3.01C-IMS (Win95; I) (via Mercury MTS (Bindery) v1.40)
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
Dear RATS users,
I wish to perform estimation of cointegrating vectors using GMM by use
of Prof.Quintos, Analysis of Cointegrating vectors using GMM appraoch,
J. of Econometrics, vol.85, No.1, 1998.
May I request for the RATS program to implement the estimation and
statistical inference by use of her approach, please?
I would be grateful if you could give me a hand.
Many thanks.
regards,
KY Woo
Senior Lecturer,
Dept of Economics,
Hong Kong Shue Yan College.
Hong Kong.
---------- End of message ----------
From: Price SG <S.G.Price@city.ac.uk>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: stability in VECM
Date: Tue, 31 Aug 1999 11:27:48 +0100 (BST)
Errors-to: <rats-l-owner@efs.mq.edu.au>
Reply-to: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Sender: Maiser@efs1.efs.mq.edu.au
X-listname: <RATS-L@efs1.efs.mq.edu.au>
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; charset=US-ASCII
X-Mailer: Mercury MTS (Bindery) v1.40
In single equation ECMs the stability condition on the loading is
obviously pretty simple. But in VECM the condition for
stability/convergence to the long-run equilibria are more complex. In
particular, I imagine we might occasionally encounter models where the
estimated loading(s) in an ECM equation in the VECM has the "wrong" ie
positive sign (when the level corresponding to the lhs variable is
normalised with a positive coefficient), but the system is still stable.
Does anyone know any papers that discuss this?
---------- End of message ----------
From: "Jian Yang" <jian-yang@tamu.edu>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Re: stability in VECM
Date: Tue, 31 Aug 1999 08:59:52 -0500
Errors-to: <rats-l-owner@efs.mq.edu.au>
Reply-to: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Sender: Maiser@efs1.efs.mq.edu.au
X-listname: <RATS-L@efs1.efs.mq.edu.au>
X-Mailer: Novell GroupWise 5.5.2 (via Mercury MTS (Bindery) v1.40)
Mime-Version: 1.0
Content-Type: text/plain; charset=US-ASCII
Content-Transfer-Encoding: quoted-printable
I can only give a piece of advice which is not really a helpful one. I =
remeber that a paper by Granger collected in "Long-run economic relationshi=
ps" gave the convergene condition in a bivaraite ECM context. I just tried =
to find out where it exactly was, but did not succeed. But I know it is =
there because I was bothered with a similar question before. Unfortunately,=
I was lazy to put it in my paper. =20
Jian Yang
>>> Price SG <S.G.Price@city.ac.uk> 08/31/99 05:27AM >>>
In single equation ECMs the stability condition on the loading is
obviously pretty simple. But in VECM the condition for
stability/convergence to the long-run equilibria are more complex. In
particular, I imagine we might occasionally encounter models where the
estimated loading(s) in an ECM equation in the VECM has the "wrong" ie
positive sign (when the level corresponding to the lhs variable is
normalised with a positive coefficient), but the system is still stable.=20=
Does anyone know any papers that discuss this?
---------- End of message ----------