From: James Peery Cover <jcover@bama.ua.edu>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Re: Nelson-Plosser dataset-OOPS
Date: Mon, 31 May 1999 09:55:25 -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>
Organization: University of Alabama
X-Mailer: Mozilla 4.05 [en] (Win95; I) (via Mercury MTS (Bindery) v1.40)
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit

OOPS! I forgot that they used annual data, which FRED does not have.
sorry.

Guido Travaglini wrote:
> 
> Anybody in this list knows wherefrom can I download the complete US
> dataset of the Nelson and Plosser article 'Trends and Random Walks in
> Macro. Time Series', JME 1982  ? Thanx, Guido, UNIROME, Italy.
> 
> ______________________________________________________
> Get Your Private, Free Email at http://www.hotmail.com

-- 
James Peery Cover
Department of Economics and Finance
Culverhouse College of Commerce
University of Alabama
P. O. Box 870224
Tuscaloosa, AL 35487-0224

---------- End of message ----------

From: James Peery Cover <jcover@bama.ua.edu>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Re: Nelson-Plosser dataset
Date: Mon, 31 May 1999 09:54:32 -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>
Organization: University of Alabama
X-Mailer: Mozilla 4.05 [en] (Win95; I) (via Mercury MTS (Bindery) v1.40)
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit

Although you would not get the actual data tht Nelson and Plosser used,
you can get a lot U.S. macroeconomics data from the web site of the
federal reserve bank of st. louis (a section called FRED).
I believe it is www.stls.frb.org/FRED.

Guido Travaglini wrote:
> 
> Anybody in this list knows wherefrom can I download the complete US
> dataset of the Nelson and Plosser article 'Trends and Random Walks in
> Macro. Time Series', JME 1982  ? Thanx, Guido, UNIROME, Italy.
> 
> ______________________________________________________
> Get Your Private, Free Email at http://www.hotmail.com

-- 
James Peery Cover
Department of Economics and Finance
Culverhouse College of Commerce
University of Alabama
P. O. Box 870224
Tuscaloosa, AL 35487-0224

---------- End of message ----------

From: Christopher F Baum <baum@bc.edu>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Re: Nelson-Plosser dataset-OOPS
Date: Mon, 31 May 1999 11:33:06 -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) [1.4.3, 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

But the Economic Report of the President, which is available online, does...

http://www.access.gpo.gov/su_docs/budget99/maindown.html

Kit Baum
Boston College Economics

--On Mon, May 31, 1999 9:55 -0500 James Peery Cover <jcover@bama.ua.edu>
wrote:

> OOPS! I forgot that they used annual data, which FRED does not have.
> sorry.
> 
> Guido Travaglini wrote:
>> 
>> Anybody in this list knows wherefrom can I download the complete US
>> dataset of the Nelson and Plosser article 'Trends and Random Walks in
>> Macro. Time Series', JME 1982  ? Thanx, Guido, UNIROME, Italy.
>> 
>> ______________________________________________________
>> Get Your Private, Free Email at http://www.hotmail.com
> 
> -- 
> James Peery Cover
> Department of Economics and Finance
> Culverhouse College of Commerce
> University of Alabama
> P. O. Box 870224
> Tuscaloosa, AL 35487-0224





---------- End of message ----------

From: "VIJAYA SARATHI N." <SARATHI@FPMLAN.iimahd.ernet.in>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: 
Date: Wed, 2 Jun 1999 15:29:44 GMT+0530
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:  IIM, Ahmedabad
X-mailer: Pegasus Mail v3.31 (via Mercury MTS (Bindery) v1.40)

Dear colleagues,

Is there a RATS code for implementing the EM algorithm for  imputing 
missing values in multivariate normal data, of the kind detailed in 
the Riskmetrics document of JP MORGAN ?

Please direct me to the right sources.

Thanks in advance for your help.

regards,

Sarathi
IIM-India.


---------- End of message ----------

From: anjun zhou <a-zhou@students.uiuc.edu>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Estimate Complicated Models
Date: Mon, 7 Jun 1999 11:24:12 -0500 (CDT)
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 Users,

I was trying to imbed a flexible model into uni-variate GARCH conditional
variance equation such as 

	c0*(f**c1)*((f-.06)**c2)*exp(c3)

where all the c's are coefficients that need to be estimated, and the f
is the series of data. I modified the garch.src so that the above
expression is added to the GARCHVAR equation and the c's are defined and
initiated as real numbers. But I got an error message as the following:

	## SX22. Expected Type INTEGER, Got REAL Instead
	>>>>c1,c2,c3

I need to get the estimates as real numbers. Please let me know how I can
make it work. Thanks a lot!

Anjun Zhou
Dept. of Finance
Univ of Illinois(UIUC)	


---------- End of message ----------

From: "Estima" <estima@estima.com>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Re: Estimate Complicated Models
Date: Mon, 7 Jun 1999 13:04:13 -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; charset=US-ASCII
Content-transfer-encoding: 7BIT
X-mailer: Pegasus Mail for Win32 (v2.54) (via Mercury MTS (Bindery) v1.40)

> I was trying to imbed a flexible model into uni-variate GARCH conditional
> variance equation such as 
> 
> 	c0*(f**c1)*((f-.06)**c2)*exp(c3)
> 
> where all the c's are coefficients that need to be estimated, and the f
> is the series of data. I modified the garch.src so that the above
> expression is added to the GARCHVAR equation and the c's are defined and
> initiated as real numbers. But I got an error message as the following:
> 
> 	## SX22. Expected Type INTEGER, Got REAL Instead
> 	>>>>c1,c2,c3
> 

I'd have to see the instruction that actually produced the error 
message to even guess at what might be wrong. If you don't know for 
sure which instruction is causing the problem, go back and run 
the program in batch mode or else execute your program one line at a 
time in interactive mode (i.e. put the cursor on the first line, hit 
<enter>, and keep hitting <enter> to execute successive lines until 
you get 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: Ying-Man Chung <y_mchung@yahoo.com>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: RE: explosive series simulation
Date: Mon, 7 Jun 1999 19:39:47 -0700 (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>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
X-Mailer: Mercury MTS (Bindery) v1.40

Dear RATS users,

May I request for commands to implement simulation of the explosive
process, please?

Yt= 1.05 * Yt-1 + zt where zt is N(0,1).

I appreciate for your help. Thank you.


With best wishes,

Sarah
HKSYC

_________________________________________________________
Do You Yahoo!?
Get your free @yahoo.com address at http://mail.yahoo.com


---------- End of message ----------

From: Galindo Andrade Arturo <agalinan@banrep.gov.co>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: RE: explosive series simulation
Date: Tue, 8 Jun 1999 08:46:14 -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>
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

Hi Sarah, this is what you might want to do:

set err=3D%ran(1.0)
set y 1 1 =3D 0.0
set y 2 100 =3D 1.05*y{1} + err

Good luck

Arturo Galindo
Banco de la Rep=FAblica
Bogot=E1, Colombia



> -----Mensaje original-----
> De: Ying-Man Chung [mailto:y_mchung@yahoo.com]
> Enviado el: lunes 7 de junio de 1999 21:40
> Para: RATS Discussion List
> Asunto: RE: explosive series simulation
>=20
>=20
> Dear RATS users,
>=20
> May I request for commands to implement simulation of the explosive
> process, please?
>=20
> Yt=3D 1.05 * Yt-1 + zt where zt is N(0,1).
>=20
> I appreciate for your help. Thank you.
>=20
>=20
> With best wishes,
>=20
> Sarah
> HKSYC
>=20
> _________________________________________________________
> Do You Yahoo!?
> Get your free @yahoo.com address at http://mail.yahoo.com
>=20

---------- End of message ----------

From: "Vasquez Escobar Diego M." <dvasques@banrep.gov.co>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: RE: explosive series simulation
Date: Tue, 8 Jun 1999 11:01:25 -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>
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

This is a more formal set of instructions to simulate an ARMA process =
as you
requested for:

[Here you'll find three examples for each case (AR(1),MA(1),ARMA(1,1))]

**********************************************************************
allo 100
seed 0
********************
* AR(1) SIMULATION *
********************
set y =3D 0.0
equation simeq y
# y{1}              =20
seed                =20
associate(variance=3Dsqrt(1)) simeq =20
# 1.05               =20
simulate 1 100 2    =20
# simeq y           =20
print / y
graph 1
# y
*************************************
* MA(1) SIMULATION WITHOUT CONSTANT *
*************************************
set a =3D %ran(1)
set y =3D 0.0
equation(noconstant,ma=3D1) simeq y 0 1
associate(resids=3Da) simeq =20
# 1.05               =20
simulate 1 100 2    =20
# simeq y           =20
print / y
graph 1
# y
*****************************************
* ARMA(1,1) SIMULATION WITHOUT CONSTANT *
*****************************************
set y =3D 0.0
equation(noconstant,ar=3D1,ma=3D1) simeq y 1 1
associate(resids=3Da) simeq =20
# 1.05 1.05              =20
simulate 1 100 2    =20
# simeq y           =20
print / y
graph 1
# y
**********************************************************************

Hope this helps. Best regards,

Diego M. V=E1squez
Luis F. Mej=EDa
BANCO DE LA REP=DABLICA - COLOMBIA

---------- End of message ----------

From: Ying-Man Chung <y_mchung@yahoo.com>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: RE: explosive series simulation
Date: Tue, 8 Jun 1999 09:27:46 -0700 (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>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
X-Mailer: Mercury MTS (Bindery) v1.40



--- Galindo Andrade Arturo <agalinan@banrep.gov.co> wrote:
> Hi Sarah, this is what you might want to do:
> 
> set err=%ran(1.0)
> set y 1 1 = 0.0
> set y 2 100 = 1.05*y{1} + err
> 
> Good luck
> 
> Arturo Galindo
> Banco de la República
> Bogotá, Colombia
> 
> 
> 
> > -----Mensaje original-----
> > De: Ying-Man Chung [mailto:y_mchung@yahoo.com]
> > Enviado el: lunes 7 de junio de 1999 21:40
> > Para: RATS Discussion List
> > Asunto: RE: explosive series simulation
> > 
> > 
> > Dear RATS users,
> > 
> > May I request for commands to implement simulation
> of the explosive
> > process, please?
> > 
> > Yt= 1.05 * Yt-1 + zt where zt is N(0,1).
> > 
> > I appreciate for your help. Thank you.
> > 
> > 
> > With best wishes,
> > 
> > Sarah
> > HKSYC
> > 
>Dear Galindo,

Thank you.

regards,

Sarah  >
> _________________________________________________________
> > Do You Yahoo!?
> > Get your free @yahoo.com address at
> http://mail.yahoo.com
> > 
> 

_________________________________________________________
Do You Yahoo!?
Get your free @yahoo.com address at http://mail.yahoo.com


---------- End of message ----------

From: Ying-Man Chung <y_mchung@yahoo.com>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: RE: explosive series simulation
Date: Tue, 8 Jun 1999 09:31:04 -0700 (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>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
X-Mailer: Mercury MTS (Bindery) v1.40



--- "Vasquez Escobar Diego M." <dvasques@banrep.gov.co> wrote:
> This is a more formal set of instructions to
> simulate an ARMA process as you
> requested for:
> 
> [Here you'll find three examples for each case
> (AR(1),MA(1),ARMA(1,1))]
> 
>
**********************************************************************
> allo 100
> seed 0
> ********************
> * AR(1) SIMULATION *
> ********************
> set y = 0.0
> equation simeq y
> # y{1}               
> seed                 
> associate(variance=sqrt(1)) simeq  
> # 1.05                
> simulate 1 100 2     
> # simeq y            
> print / y
> graph 1
> # y
> *************************************
> * MA(1) SIMULATION WITHOUT CONSTANT *
> *************************************
> set a = %ran(1)
> set y = 0.0
> equation(noconstant,ma=1) simeq y 0 1
> associate(resids=a) simeq  
> # 1.05                
> simulate 1 100 2     
> # simeq y            
> print / y
> graph 1
> # y
> *****************************************
> * ARMA(1,1) SIMULATION WITHOUT CONSTANT *
> *****************************************
> set y = 0.0
> equation(noconstant,ar=1,ma=1) simeq y 1 1
> associate(resids=a) simeq  
> # 1.05 1.05               
> simulate 1 100 2     
> # simeq y            
> print / y
> graph 1
> # y
>
**********************************************************************
> 
> Hope this helps. Best regards,
> 
> Diego M. Vásquez
> Luis F. Mejía
> BANCO DE LA REPÚBLICA - COLOMBIA
> 
Dear Diego,

Thank you

regards,

Sarah
_________________________________________________________
Do You Yahoo!?
Get your free @yahoo.com address at http://mail.yahoo.com


---------- End of message ----------

From: "Yong U. Glasure" <yglasure@wbu1.wbu.edu>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: VARs
Date: Thu, 10 Jun 1999 10:28:57 -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: Windows Eudora Light Version 1.5.2 (via Mercury MTS (Bindery) v1.40)
Mime-Version: 1.0
Content-Type: text/plain; charset="us-ascii"

Dear Colleagues,

I am interested in estimating VARs with the different lag length of each
variable.  If you happen to have a sample program, could you kindly share
with me.

Thank you.


Yong U. Glasure
Division of Business
Wayland Baptist University
2002 W. Loop 289, Suite 200
Lubbock, Texas 79407
Voice:  806-785-9285
Fax:  806-794-4227
E-mail:  yglasure@wbu1.wbu.edu


---------- End of message ----------

From: Woo Kai Yin <kywoo@ctimail.com>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Re: VARs
Date: Fri, 11 Jun 1999 00:50:49 +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 3.0 (Win95; I) (via Mercury MTS (Bindery) v1.40)
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit

Yong U. Glasure wrote:
> 
> Dear Colleagues,
> 
> I am interested in estimating VARs with the different lag length of each
> variable.  If you happen to have a sample program, could you kindly share
> with me.
> 
> Thank you.
> 
> Yong U. Glasure
> Division of Business
> Wayland Baptist University
> 2002 W. Loop 289, Suite 20D0
> Lubbock, Texas 79407
> Voice:  806-785-9285
> Fax:  806-794-4227
> E-mail:  yglasure@wbu1.wbu.edu

Dear Glasure,

Downloard var.src from the homepages of the Estima.

Regards,

kevin

---------- End of message ----------

From: Krassimir Petrov <krassimir_petrov@hotmail.com>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Re: VARs
Date: Thu, 10 Jun 1999 09:53:54 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>
Mime-Version: 1.0
Content-Type: text/plain; format=flowed
X-Mailer: Mercury MTS (Bindery) v1.40

>Dear Colleagues,
>
>I am interested in estimating VARs with the different lag length of each
>variable.  If you happen to have a sample program, could you kindly share
>with me.


A good start will be N. Morin's VAR.SRC. Start with it and see how you could 
modify the code to your needs. That is at least how I resolved my specific 
problems (incorporating Litterman's priors etc.).

Regards.


_______________________________________________________________
Get Free Email and Do More On The Web. Visit http://www.msn.com

---------- End of message ----------

From: "Estima" <estima@estima.com>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Re: VARs
Date: Thu, 10 Jun 1999 12:41:39 -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; charset=US-ASCII
Content-transfer-encoding: 7BIT
X-mailer: Pegasus Mail for Win32 (v2.54) (via Mercury MTS (Bindery) v1.40)

> >
> >I am interested in estimating VARs with the different lag length of each
> >variable.  If you happen to have a sample program, could you kindly share
> >with me.
> 
> 
> A good start will be N. Morin's VAR.SRC. Start with it and see how you could 
> modify the code to your needs. That is at least how I resolved my specific 
> problems (incorporating Litterman's priors etc.).
> 

I wouldn't really recommend VAR.SRC as a starting point if you simply 
want to do relitvely straightforard VAR analyses with different lag 
structures. Even if you ultimately wanted to end up modifying VAR.SRC 
to suit your needs, you'll still need to know the basics of setting 
up a near-VAR model. 

We do discuss near-VAR's on pp. 8-2 and 8-3 of the manual, and that's 
where you should start. The only real difference is that you need to 
use EQUATION or LINREG commands to define the individual equations 
(i.e. rather than using the VARIABLES, LAGS, and DETERMINISTIC 
commands). You can then group the equations into a SYSTEM using 
SYSTEM and END(SYSTEM), which will allow you to estimate the model 
using the ESTIMATE command.

For the most part, any of the standard VAR techniques (forecasting,
variance decomposition, impulse responses, etc.) can be without to 
the near-VAR without any modifications. One exception is the 
MONTEVAR.PRG routine, which requires all equations to have the same 
rhs variables.

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: Travis D Nesmith <travis.d.nesmith@frb.gov>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Re: VARs
Date: Thu, 10 Jun 1999 14:27:44 -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
Content-type: text/plain; charset=us-ascii
X-Mailer: Mercury MTS (Bindery) v1.40



A VAR with different lag lengths is a special case of an asymmetric VAR.  You
might want to look at a paper by John Keating on the subject.
The paper can be downloaded from http://falcon.cc.ukans.edu/~econ/
You will have to select working papers and then 1998 to get to the paper.

Tom already covered how to implement an AVAR in RATS, but I thought this
reference would be useful.  Also John probably has RATS code that he would
probably share.

Travis



---------- End of message ----------

From: Enrico De Giorgi <edegiorgi@ticino.edu>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Literature
Date: Thu, 10 Jun 1999 22:24:09 +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>
X-Mailer: Mozilla 4.03 [de]C-NECCK  (Win95; I) (via Mercury MTS (Bindery) v1.40)
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit

Dear All:

I'm trying to create a web site, which contains a list of books in
econometric and mathematical finance.
Can you help me with some suggestions.

Tank you
Regards,

Enrico Degiorgi


---------- End of message ----------

From: Krassimir Petrov <krassimir_petrov@hotmail.com>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Re: Literature
Date: Fri, 11 Jun 1999 00:02:46 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>
Mime-Version: 1.0
Content-Type: text/plain; format=flowed
X-Mailer: Mercury MTS (Bindery) v1.40

>Dear All:
>
>I'm trying to create a web site, which contains a list of books in
>econometric and mathematical finance.
>Can you help me with some suggestions.
>Enrico Degiorgi

Contact Chris at <pirinsky.2@osu.edu>. He can really jumpstart your project. 
His forte is math finance and can supply you with an extensive list of books 
from "Numerical Methods for Stochastic Differential Equations" to Duffie's 
"Dynamic Asset Pricing Theory".

I'd gladly fill in with books on probability and stochastics in case you 
want to cover some background.

My suggestion at this point is to further classify what you are looking for 
by providing a more detailed list in the spirit of:
probability, statistics, stochastics, numerical methods, asset pricing, 
derivatives (futures, options), etc. Also provide what you are looking for 
[author, name, level of difficulty, etc.].

When you get the site running and the address firm, you may send me your 
HTTP so that the Web Master for the Journal of Finance [he is my roommate, 
we are PhD students at the Ohio State University] will make a link to your 
Site.

I hope this helps.



Krassimir Petrov



_______________________________________________________________
Get Free Email and Do More On The Web. Visit http://www.msn.com

---------- End of message ----------

From: "Frieder Knüpling" <knueplin@ruf.uni-freiburg.de>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Thickness of Lines
Date: Mon, 14 Jun 1999 17:25:33 +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>
X-Mailer: Mozilla 4.06 [en] (Win98; 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,

how can I produce GRAPHs or SCATTER plots with thicker lines than usual?
I want to publish my PhD-thesis containig various RATS graphs, and I am
having problems with the publisher because of the thin lines. Of course,
I can double-click the graphs in Word97 and modify them there; but when
I do this with graphs containig several time series, at the very moment
all lines but one vanish - once and for ever.

Your help is greatly appreciated.

Yours, Frieder

--
Frieder Knuepling
Albert-Ludwigs-Universitaet Freiburg
Institut fuer Allgemeine Wirtschaftsforschung
Abteilung Statistik und Oekonometrie
Belfortstr. 24
D-79098 Freiburg
Tel +49 761 / 203 - 2341
Fax +49 761 / 203 - 2340



---------- End of message ----------

From: Mark Tomsett <M.P.Tomsett@durham.ac.uk>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Re: Thickness of Lines
Date: Mon, 14 Jun 1999 17:15:32 +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>
X-Mailer: QUALCOMM Windows Eudora Light Version 3.0.6 (32) (via Mercury MTS (Bindery) v1.40)
Mime-Version: 1.0
Content-Type: text/plain; charset="us-ascii"

You've got a tricky one there. It's fairly easy to change the line patterns
(just refer to the manual), but there is little guidance regarding
thickness of lines. To be honest it's easier to produce graphs in almost
any other package. 

Sorry to be of little help. Take comfort in the fact that you're not the
only one having problems with graphs in a PhD generated by Rats.


At 17:25 14/06/99 +0200, you wrote:
>Dear RATS users,
>
>how can I produce GRAPHs or SCATTER plots with thicker lines than usual?
>I want to publish my PhD-thesis containig various RATS graphs, and I am
>having problems with the publisher because of the thin lines. Of course,
>I can double-click the graphs in Word97 and modify them there; but when
>I do this with graphs containig several time series, at the very moment
>all lines but one vanish - once and for ever.
>
>Your help is greatly appreciated.
>
>Yours, Frieder
>
>--
>Frieder Knuepling
>Albert-Ludwigs-Universitaet Freiburg
>Institut fuer Allgemeine Wirtschaftsforschung
>Abteilung Statistik und Oekonometrie
>Belfortstr. 24
>D-79098 Freiburg
>Tel +49 761 / 203 - 2341
>Fax +49 761 / 203 - 2340
>
>
>
>
*************************************************************************
Mark Tomsett
Department of Economics and Finance
University of Durham
23-26 Old Elvet
DH1 3HY
Tel: 0191-374-7268
*************************************************************************

---------- End of message ----------

From: "Estima" <estima@estima.com>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Re: Thickness of Lines
Date: Mon, 14 Jun 1999 15:34:14 -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; charset=US-ASCII
Content-transfer-encoding: 7BIT
X-mailer: Pegasus Mail for Win32 (v2.54) (via Mercury MTS (Bindery) v1.40)

> 
> how can I produce GRAPHs or SCATTER plots with thicker lines than usual?
> I want to publish my PhD-thesis containig various RATS graphs, and I am
> having problems with the publisher because of the thin lines. Of course,
> I can double-click the graphs in Word97 and modify them there; but when
> I do this with graphs containig several time series, at the very moment
> all lines but one vanish - once and for ever.
> 

Will the publisher accept graphs in PostScript format, or, if you're 
supplying the hard copy, does your printer include PostScript 
support? If so, I think it's a fairly simple matter to change the 
PROLOG.PST header file to adjust the line thicknesses. If interested, 
let me know and I'll check into it.

On a related note, we are deep into the development process on 
Version 5. If there are additions or improvements you'd like to see 
in the graphics capabilities, now's the time to let us know.

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: "Stephen A. DeLurgio" <sad@forecast.umkc.edu>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Re: RATS Improvements for Version 5
Date: Mon, 14 Jun 1999 17:10:40 -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>
Organization: University of Missouri
X-Mailer: Mozilla 4.02 [en] (Win95; I) (via Mercury MTS (Bindery) v1.40)
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit

Dear Tom:

I would very much like to use RATS in lower level classes (statistics classes
and other planning classes).  One of the reasons RATS is not used (i.e., hard
for me to justify to others) is because simple histograms and other
exploratory data analysis procedures are not built into RATS.  I am aware of
user writen procedures, but I wonder if you have ever thought of adding some
very basic exploratory commands?  These would greatly enhance my ability to
use RATS in other classes.

Thanks,

Regards,

Steve DeLurgio

Estima wrote:

> >
> > how can I produce GRAPHs or SCATTER plots with thicker lines than usual?
> > I want to publish my PhD-thesis containig various RATS graphs, and I am
> > having problems with the publisher because of the thin lines. Of course,
> > I can double-click the graphs in Word97 and modify them there; but when
> > I do this with graphs containig several time series, at the very moment
> > all lines but one vanish - once and for ever.
> >
>
> Will the publisher accept graphs in PostScript format, or, if you're
> supplying the hard copy, does your printer include PostScript
> support? If so, I think it's a fairly simple matter to change the
> PROLOG.PST header file to adjust the line thicknesses. If interested,
> let me know and I'll check into it.
>
> On a related note, we are deep into the development process on
> Version 5. If there are additions or improvements you'd like to see
> in the graphics capabilities, now's the time to let us know.
>
> 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: Ashley Lyman <alyman@uidaho.edu>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Re: Thickness of Lines
Date: Mon, 14 Jun 1999 15:35:41 -0700 (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>
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; charset=US-ASCII
X-Mailer: Mercury MTS (Bindery) v1.40

Tom,
	Since you mention you are deep into the development process on
Version 5,  is there any chance that you might consider improving
capabilities in Rats for examining problems of ill conditioning and data
weaknesses.  Reference: Belsley, 1991. Conditioning Diagnostics:
Collinearity and Weak Data in Regression. Wiley: New York.  Other packages
such as SAS and Shazam have such procedures and, with the use of various
types of aggregated data in Economics where model specification questions
arise, it would be very nice to make use of procedures in Rats rather than
have to maintain other packages for these reasons.

Thanks,

Ashley Lyman
Economics Department
University of Idaho


On Mon, 14 Jun 1999, Estima wrote:

> > 
> > how can I produce GRAPHs or SCATTER plots with thicker lines than usual?
> > I want to publish my PhD-thesis containig various RATS graphs, and I am
> > having problems with the publisher because of the thin lines. Of course,
> > I can double-click the graphs in Word97 and modify them there; but when
> > I do this with graphs containig several time series, at the very moment
> > all lines but one vanish - once and for ever.
> > 
> 
> Will the publisher accept graphs in PostScript format, or, if you're 
> supplying the hard copy, does your printer include PostScript 
> support? If so, I think it's a fairly simple matter to change the 
> PROLOG.PST header file to adjust the line thicknesses. If interested, 
> let me know and I'll check into it.
> 
> On a related note, we are deep into the development process on 
> Version 5. If there are additions or improvements you'd like to see 
> in the graphics capabilities, now's the time to let us know.
> 
> 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: Rob Trevor <robt@efs.mq.edu.au>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Version 5
Date: Tue, 15 Jun 1999 10:31:06 +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 Tom

Since you asked for ideas for v5, here's a reminder of one from several
years back:

* access to the 'internals' of the maximise instruction

It would be great if we could directly access the (numerical) first
derivative of the objective function and the approximation of the second,
when generated by the choice of optimisation method. (Obviously, simplex
doesn't generate derivatives.)

It would be even better if there was a new instruction that allowed one to
take numerical first (and second, although I'm well aware of the numerical
problems that this can generate) of a particluar FRML.

Either, or both, of these would allow much more flexibility in doing
certain types of robust variance-covariance matrix calculations, esp in
GARCH-type models.

Progress seems to have been made on automatic differentiation engines in
the last few years. Analytical first derivatives could even be achievable
using publically available code.

My real wish list also includes:

* ability for a rats format dataset to include LABEL type series (ie
something with alpha entries in the series)

* ability for rats to use business day data without dropping the date
information -- ie when data were of this new type rats would know to skip
NA's in time series instructions as if the data were read in as irregular,
yet you could still associate data entries with dates (I'd even be happy
with a solution which required the user to supply a series which flagged
non-business days - much like a SMPL series in some instructions now)

* ability to define own FUNCTION in rats, rather than just a procedure
which is much like defining an instruction

* ability to call compiled external C functions and/or subroutines, even if
this meant that these externals needed to be written with special headers
etc to make them compatible with RATS

* 'matrix' FRML's - ie FRML F(T) is a vector of current FRML's (this would
make my well used work around for multivariate GARCH models obsolete)

Cheers

Rob

---------- End of message ----------

From: Travis D Nesmith <travis.d.nesmith@frb.gov>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Version 5
Date: Tue, 15 Jun 1999 08:21:28 -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
Content-type: text/plain; charset=us-ascii
X-Mailer: Mercury MTS (Bindery) v1.40



Dear Estima,

I would also like to have the ability to call DLLs written in other languages,
especially Fortran and C.

Thanks.

Travis



---------- End of message ----------

From: "Wai Lee" <lee_wai@jpmorgan.com>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Re: Version 5
Date: Tue, 15 Jun 1999 14:09:23 -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
Content-type: text/plain; charset=us-ascii
X-Mailer: Mercury MTS (Bindery) v1.40

I would love to see particularly the following two suggested by Rob in
version 5.  The first one will be really helpful for those of us who want
to see what's going on.  Thanks.


* access to the 'internals' of the maximise instruction

It would be great if we could directly access the (numerical) first
derivative of the objective function and the approximation of the second,
when generated by the choice of optimisation method. (Obviously, simplex
doesn't generate derivatives.)

It would be even better if there was a new instruction that allowed one to
take numerical first (and second, although I'm well aware of the numerical
problems that this can generate) of a particluar FRML.


* 'matrix' FRML's - ie FRML F(T) is a vector of current FRML's (this would
make my well used work around for multivariate GARCH models obsolete)



This communication is for informational purposes only.  It is not intended as
an offer or solicitation for the purchase or sale of any financial instrument
or as an official confirmation of any transaction, unless specifically agreed
otherwise. All market prices, data and other information are not warranted as
to completeness or accuracy and is subject to change without notice. Any
comments or statements made herein do not necessarily reflect those of
J.P. Morgan & Co. Incorporated, its subsidiaries and affiliates.


---------- End of message ----------

From: "Estima" <estima@estima.com>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Re: Version 5
Date: Wed, 16 Jun 1999 10:43:40 -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; charset=US-ASCII
Content-transfer-encoding: 7BIT
X-mailer: Pegasus Mail for Win32 (v2.54) (via Mercury MTS (Bindery) v1.40)

Everyone:

Thanks for the many Version 5 suggestions (some sent to the RATS-L
list, some directly to Estima). I'm happy to say that many of the
suggestions were for improvements we have already implemented or
have been considering, but several others were new to us. Stay tuned 
to the RATS list and the web site--I hope to post some preliminary 
info on Version 5 in the coming weeks.

Sincerely,
Tom Maycock
Estima

PS. Please don't ask me when Version 5 will be ready. I don't know 
yet. Thanks.



 
--
------------------------------------------------------------
|   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: Heiko Gerbel <gerbel@uni-freiburg.de>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: 
Date: Wed, 16 Jun 1999 18:28:02 +0200 (MET DST)
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

How to compute a cyclometric function, e. g. arctan(x), i. e. the inverse
of the
trigonometric function tangent of x, tan(x), described in Appendix B:
Functions of the RATS user's manual?

Heiko Gerbel,  <gerbel@ruf.uni-freiburg.de>


---------- End of message ----------

From: "Estima" <estima@estima.com>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Re: Thickness of Lines
Date: Wed, 16 Jun 1999 11:41:04 -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; charset=US-ASCII
Content-transfer-encoding: 7BIT
X-mailer: Pegasus Mail for Win32 (v2.54) (via Mercury MTS (Bindery) v1.40)

For those who are interested in the line-thickness issue, it's
_very_ easy to change the line thickness if you can export your
graph to PS format. Here's the basics of what I described to Mr.
Knuepling.

First, note that you can make the change in either of two ways:

* You can change the definition of THICK in the PROLOG.PST file
(found in your WinRATS directory). This is a PostScript file is
prepended to every graph you export in PostScript format from RATS.
Thus, whatever setting for THICK you use in PROLOG.PST will
automatically apply to any graphs you subsequently export to PS
format from RATS (you can, of course, go back and change THICK
again).

* You can also change the THICK setting for each graph individually,
_after_ it has been exported.

I would recommend that you start by exporting one graph to PostScript
format, and try playing around with a setting for THICK that you
like. Once you settle on a value for the thickness, you can change
PROLOG.PST accordingly, and then export the rest of the
graphs--they'll all have the thickness setting specified in
PROLOG.PST.

Here's how you make the change:

1) Open the PostScript file (PROLOG.PST or a graph you've saved in PS
format) in any text editor (such as RATS, Notepad, or the DOS utility
EDIT).

2) Look for these three lines (they start at about line 79 in the
file--you can search for "THICK" if you want):

  % Define the possible line widths
  /THIN  {0.125 setlinewidth } def
  /THICK {0.500 setlinewidth } def

3) To increase the thickness of the graph lines (i.e. the plots of the
series values), just increase the "0.500" value to some larger number,
such as 0.75, 1.0, 2.0, etc. For example:

  /THICK {1.250 setlinewidth } def


4) Save and close the file.

5) If you changed PROLOG.PST, use RATS to open your RGF file and do
Save As... to export the graph to PostScript format (either Portrait
or Landscape orientation, as desired). If you edited your graph file
directly, skip this step.

6) Print the graph. The easiest way to do this is to go into DOS and
do a command like:

copy mygraph.eps lpt1:

where LPT1: is your printer port.

Alternatively, you could import the PS graph into a page layout 
program and print it from within the program.

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: Jeannine Bailliu <JBailliu@bank-banque-canada.ca>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Testing for unit roots in a panel data set
Date: Wed, 16 Jun 1999 14:05:14 -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: Mozilla 4.05 [en] (X11; U; SunOS 5.6 sun4u) (via Mercury MTS (Bindery) v1.40)
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit

Hello,

I have a panel data set comprised of quarterly data for a sample of
emerging market countries over time and I want to test for the
stationarity of the various data series. There is a way to test for the
presence of unit roots using the entire panel rather than testing the
series by individual country.  Has anyone written a procedure that does
this in RATS?

Jeannine Bailliu
International Department
Bank of Canada


---------- End of message ----------

From: Guido Travaglini <g_2002@hotmail.com>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Eigenvectors
Date: Wed, 16 Jun 1999 11:14:15 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>
Mime-Version: 1.0
Content-Type: text/plain; format=flowed
X-Mailer: Mercury MTS (Bindery) v1.40

After finding the eigenvalues and the eigenvectors of a given matrix A
with the EIGEN command, I want to display the (absolute) values and the row 
placement in decreasing order of the elements of each column of the 
eigenvectors matrix (which I call E). However I succeed only at finding the 
maximum element of each column and its row placement, but not the others. I 
used the following code:
dec vec absv(%ncmom)           ;*%ncmom is the size of A
do k=1,%ncmom
  do i=1,%ncmom
  ewise absv(i) = abs(E(i,k))
  com maxz = %maxvalue(absv)
  if absv(i).eq.maxz
  dis(store=ss) i
  end do i
  dis ss maxz
end do k
The result assigns to each maxz its placement in its own column (e.g.
maxz in the third column can be found in the first row).
Anybody could help me solve this problem? Many thanx, Guido.


______________________________________________________
Get Your Private, Free Email at http://www.hotmail.com

---------- End of message ----------

From: Simon.Van-Norden@hec.ca
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Re: Testing for unit roots in a panel data set
Date: Wed, 16 Jun 1999 14:24:04 -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

Jeannine;

Hi!

There are many such tests. There is also an important recent literature (=
mostly
applied to tests for PPP) on size distortion in such tests; under some co=
mmonly
occurring circumstances they can reject the presence of unit roots *way* =
too
often under the null.  You should check out the work by Peter Pedroni at
University of Indiana and Paul O'Connell (former Grad student at harvard =
- I
think he went to Michigan?)

Regards,


SvN

Jeannine Bailliu wrote:
>=20
> Hello,
>=20
> I have a panel data set comprised of quarterly data for a sample of
> emerging market countries over time and I want to test for the
> stationarity of the various data series. There is a way to test for the
> presence of unit roots using the entire panel rather than testing the
> series by individual country.  Has anyone written a procedure that does
> this in RATS?
>=20
> Jeannine Bailliu
> International Department
> Bank of Canada

--=20
Simon van Norden			Professeur invit=E9
E-mail:  simon.van-norden@hec.ca   or    svn@alum.mit.edu=20
Home Page:       http://www.hec.ca/pages/simon.van-norden
(514)340-6781 or fax (514)340-5632 or  cell (514)993-0466
Service de l'enseignement de la finance, =C9cole des H.E.C.
3000 Cote-Sainte-Catherine, Montreal QC, CANADA   H3T 2A7

---------- End of message ----------

From: "Masih, Rumi" <Rumi.Masih@gs.com>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: RE: Testing for unit roots in a panel data set
Date: Wed, 16 Jun 1999 14:24:55 -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 may like to ask Peter Pedroni at Indiana


His email is at:

ppedroni@indiana.edu <mailto:ppedroni@indiana.edu> 

Peter has written code for the Im-Pesaran-Shin test and also for various
panel estimators.

Regards

RUMI


Rumi Masih
Emerging Markets Economic Research
Goldman Sachs & Co.
85 Broad Street (28th Floor)
New York  NY  10004, U.S.A.
Phone: 212-902-4410
Fax: 212-346-4402
E-Mail: rumi.masih@gs.com



	-----Original Message-----
	From:	Jeannine Bailliu [SMTP:JBailliu@bank-banque-canada.ca]
	Sent:	Wednesday, June 16, 1999 2:05 PM
	To:	RATS Discussion List
	Subject:	Testing for unit roots in a panel data set

	Hello,

	I have a panel data set comprised of quarterly data for a sample of
	emerging market countries over time and I want to test for the
	stationarity of the various data series. There is a way to test for
the
	presence of unit roots using the entire panel rather than testing
the
	series by individual country.  Has anyone written a procedure that
does
	this in RATS?

	Jeannine Bailliu
	International Department
	Bank of Canada

---------- End of message ----------

From: "David Leblang" <dleblang@unt.edu>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: GARCH.SRC
Date: Wed, 16 Jun 1999 13:42:48 CST6CDT
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: UNT College of Arts and Sciences
MIME-Version: 1.0
Content-type: text/plain; charset=US-ASCII
Content-transfer-encoding: 7BIT
X-mailer: Pegasus Mail for Win32 (v2.54) (via Mercury MTS (Bindery) v1.40)

Hi,

I am using the GARCH.SRC menu driven procedure and am trying to 
figure out how to include an MA(1) term in the mean equation.  Does 
anyone know how this can be done?

Thanks,

David Leblang
University of North Texas

---------- End of message ----------

From: Aghdas Mirzaie <mirzaie@csd.uwm.edu>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Re: GARCH.SRC
Date: Wed, 16 Jun 1999 13:57:05 -0500 (CDT)
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

Unsubscirbe

Aghdas Mirzaie - Economics Department			
University of Wisconsin-Milwaukee, Office: Bolton 854, 	
Tel: 229-6536 or 229-4811	
University of Wisconsin-Waukesha, Office: N123,		
Tel: 521-5535


---------- End of message ----------

From: Christopher F Baum <baum@bc.edu>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Re: Testing for unit roots in a panel data set
Date: Wed, 16 Jun 1999 15:14:49 -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) [1.4.3, 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

Peter Pedroni of Indiana University has written such software for RATS to
implement the econometric procedures he has dveeloped for panel unit root
tests. Contact him at ppedroni@indiana.edu.

Kit Baum

--On Wed, Jun 16, 1999 14:05 -0400 Jeannine Bailliu
<JBailliu@bank-banque-canada.ca> wrote:

> Hello,
> 
> I have a panel data set comprised of quarterly data for a sample of
> emerging market countries over time and I want to test for the
> stationarity of the various data series. There is a way to test for the
> presence of unit roots using the entire panel rather than testing the
> series by individual country.  Has anyone written a procedure that does
> this in RATS?
> 
> Jeannine Bailliu
> International Department
> Bank of Canada
> 





---------- End of message ----------

From: "Estima" <estima@estima.com>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Re: Eigenvectors
Date: Wed, 16 Jun 1999 16:18:57 -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; charset=US-ASCII
Content-transfer-encoding: 7BIT
X-mailer: Pegasus Mail for Win32 (v2.54) (via Mercury MTS (Bindery) v1.40)

> After finding the eigenvalues and the eigenvectors of a given matrix A
> with the EIGEN command, I want to display the (absolute) values and the row 
> placement in decreasing order of the elements of each column of the 
> eigenvectors matrix (which I call E). However I succeed only at finding the 
> maximum element of each column and its row placement, but not the others. I 
> used the following code:
> dec vec absv(%ncmom)           ;*%ncmom is the size of A
> do k=1,%ncmom
>   do i=1,%ncmom
>   ewise absv(i) = abs(E(i,k))
>   com maxz = %maxvalue(absv)
>   if absv(i).eq.maxz
>   dis(store=ss) i
>   end do i
>   dis ss maxz
> end do k

Guido:

I haven't had time to take a close look at this, but I do see one
obvious problem: You don't want to use I or J as loop indices for
any block that includes an EWISE instruction--the EWISE is going to
reset the value of I, which will probably cause problems for the
rest of your loop. For example, try using something like "ii":

do k=1,%ncmom
 do ii=1,%ncmom
  etc.


If you still have problems, let us konw.

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: "Estima" <estima@estima.com>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Re: 
Date: Wed, 16 Jun 1999 16:18:57 -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; charset=US-ASCII
Content-transfer-encoding: 7BIT
X-mailer: Pegasus Mail for Win32 (v2.54) (via Mercury MTS (Bindery) v1.40)


> How to compute a cyclometric function, e. g. arctan(x), i. e. the inverse
> of the
> trigonometric function tangent of x, tan(x), described in Appendix B:
> Functions of the RATS user's manual?
> 

If COS(X) = Y, you can get X (i.e. the ARCCOS) by:

 x = arctan( sqrt(1 - y**2) / y )

Where ARCTAN(X) is given by:

ARCTAN = $real( %arg( %cmplx(1,X) ) )

Version 5 will include arctan, arcsin, etc. as built in functions.

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: "R.Perman" <r.perman@strath.ac.uk>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Re: Testing for unit roots in a panel data set
Date: Thu, 17 Jun 1999 10:42:13 +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: QUALCOMM Windows Eudora Light Version 3.0.3 (32) (via Mercury MTS (Bindery) v1.40)
Mime-Version: 1.0
Content-Type: text/plain; charset="us-ascii"

Jeannine

Peter Pedroni has written some RATS code for this. Contact him at

ppedroni@indiana.edu

There are also some tests in the Levin and Lin tradition available as
add-ins to be found on the Estima home page.

Roger Perman



---------- End of message ----------

From: "Giles Heywood" <Giles.Heywood@gartmore.com>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: MALCOLM, CATS
Date: Thu, 17 Jun 1999 11:04:57 +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
Content-type: text/plain; charset=iso-8859-1
Content-transfer-encoding: quoted-printable
X-Mailer: Mercury MTS (Bindery) v1.40

I would welcome any feedback from users on the features, useability,
documentation of the version of MALCOLM which was released in December,=

especially in comparison with CATS (I am aware of the website for MALCO=
LM).
Any comments on the merits of MALCOLM compared to other packages such a=
s
EVIEWS or PC-GIVE/FIML, in the context of cointegration analysis, would=

also be most helpful.

TIA

Giles Heywood



_______________________________________________________________________=
____
                                         _____


=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=
=3D

Gartmore Investment Management plc is an appointed representative of
Gartmore Investment Ltd (GIL) which is regulated by IMRO and the Person=
al
Investment Authority.  GIL represents only the NatWest and Gartmore
Marketing Group for life assurance, Pensions, unit trusts, other regula=
ted
collective investment schemes and investment services.

CONFIDENTIALITY NOTICE

This message is sent in confidence for the addressee only.  The content=
s
are not to be disclosed to anyone other than the addressee.  Unauthoris=
ed
recipients must preserve this confidentiality and should please advise =
the
sender of any error in transmission.

i=A8?
=



---------- End of message ----------

From: WHEELER@wmich.edu
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Re: Version 5
Date: Tue, 22 Jun 1999 15:01:18 -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
X-Mailer: Mercury MTS (Bindery) v1.40

Tom,

In the next version of RATS, I would like to see asymptotic standard errors
for IRFs.  The formula for these can be found on page 339 of Hamilton (1994).

Mark Wheeler

---------- End of message ----------

From: Thamana Lekprichakul <thamana@hawaii.edu>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Accessing median
Date: Thu, 24 Jun 1999 21:55:19 -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,

Please pardon me for asking very elementary question as I am a new RATS
users. Could someone please help me with retrieving median of a matrix of
series. I wish to write a batch command to do outliers analysis. 

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: Myrvin Anthony <m.l.anthony@strath.ac.uk>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Unsubsribe
Date: Fri, 25 Jun 1999 17:38:53 +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)

Unsubscribe.

Myrvin Anthony


---------- End of message ----------

From: anjun zhou <a-zhou@students.uiuc.edu>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Unsubsribe 
Date: Fri, 25 Jun 1999 11:50:20 -0500 (CDT)
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


Unsubscribe.

Anjun Zhou


---------- End of message ----------

From: Robert Howard <polrhh@panther.gsu.edu>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Re: Unsubsribe
Date: Fri, 25 Jun 1999 13:46:45 -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: Mozilla 4.05 [en] (Win95; I) (via Mercury MTS (Bindery) v1.40)
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit




> unsubscribe




---------- End of message ----------

From: Thamana Lekprichakul <thamana@hawaii.edu>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: RATS version 5
Date: Sun, 27 Jun 1999 11:59:38 -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

Hi,

As a beginner, I find RATS manual difficult to follow (based my comment on
version 4.20). Adding more features and making RTAS more flexible are more
than welcome. However, it would be nice also to have a good manual. From
my limited experience with other statistical software, Stata does a very
good job in making its manual. It provides techical information, tips,
and application example.

/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: =?iso-8859-9?Q?Prof=2EDr=2E=D6nder=20=D6ZKAZAN=C7?= 	<onder@anadolu.edu.tr>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Unsubscribe
Date: Mon, 28 Jun 1999 15:30:07 +0300
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: ANADOLU UNIVERSITY
X-Mailer: Mozilla 4.5 (Macintosh; I; PPC) (via Mercury MTS (Bindery) v1.40)
MIME-Version: 1.0
Content-Type: text/plain; charset=iso-8859-9; x-mac-type="54455854"; x-mac-creator="4D4F5353"
Content-Transfer-Encoding: 7bit

Unsubscribe.

Onder Ozkazanc


---------- End of message ----------