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 IAA51022
	for <baum@monet.bc.edu>; Mon, 4 Jan 1999 08:34:18 -0500
From: maiser@efs.mq.edu.au
Received: (from root@localhost)
	by corot.bc.edu (8.8.7/8.8.7) with X.500 id IAA105570
	for baum@mail1.bc.edu; Mon, 4 Jan 1999 08:34:18 -0500
Received: from sunb.ocs.mq.edu.au (sunb.ocs.mq.edu.au [137.111.1.11])
	by corot.bc.edu (8.8.7/8.8.7) with ESMTP id IAA116824
	for <baum@bc.edu>; Mon, 4 Jan 1999 08:34:14 -0500
Received: from efs1.efs.mq.edu.au (efs1.efs.mq.edu.au [137.111.64.8])
	by sunb.ocs.mq.edu.au (8.9.0/8.9.0) with ESMTP id AAA02026
	for <baum@bc.edu>; Tue, 5 Jan 1999 00:34:09 +1100 (EST)
Received: from EFS1/SpoolDir by efs1.efs.mq.edu.au (Mercury 1.40);
    5 Jan 99 00:35:25 GMT+1000
Received: from SpoolDir by EFS1 (Mercury 1.40); 5 Jan 99 00:35:23 GMT+1000
To: baum@bc.edu
Date: Tue, 5 Jan 99 0:35:23 GMT+1000
Subject: Re: 
Message-ID: <9CF559503B@efs1.efs.mq.edu.au>

From: M.Haroutounian@city.ac.uk
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Network
Date: Mon, 7 Dec 1998 15:56:43 +0000
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)

Dear RATS users,

I am a PhD student working on nonlinear predictability of stock
returns. 

I am trying to estimate a simple single-layer feedforward network
regression. The process of estimation is extremely slow. 

********************************************************* 
NNLEARN(MODE=EXAMPLE,XMIN=-.30, $
YMIN=-.19,XMAX=.75,YMAX=.12,SAVE=MV,HIDDEN=6,rsquar=.80,TRACE)
# S150{1} S1200{1 2} S2200{1} S5150{1 2}   ; inputs
# y                                                                 ;output  
   
***********************************************************

I have tried to set MODE=EPOCH, vary the number of inputs,
change the number of hidden nodes: none of them works.
When I set rsquar=.50, the network does converge immediately;
however when I increase it by small amount the estimation 
process slows down dramatically.

Does anyone have suggestions how I could speed up the estimation?

Thank you,
Maria

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

From: Alain Astier <astier@ipnl.in2p3.fr>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: 
Date: Tue, 8 Dec 1998 21:51:39 +0100 (MET)
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>
Content-Type: text
X-Mailer: Mercury MTS (Bindery) v1.40

Hello everybody,

  I'm a French PhD candidate working on monetary policy transmission
process. I would like to run a structural VAR using RATS. Please anybody
who has heard about MALCOLM let me know about it. I tried to subscribe
but nobody answered. I know there is a beta version. If you have it,
if you have heard about it, please let me know.
Thanks a lot.

  F. Astier


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

From: "Estima" <estima@estima.com>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Re: 
Date: Tue, 8 Dec 1998 15:07:17 -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'm a French PhD candidate working on monetary policy transmission
> process. I would like to run a structural VAR using RATS. Please anybody
> who has heard about MALCOLM let me know about it. I tried to subscribe
> but nobody answered. I know there is a beta version. If you have it,
> if you have heard about it, please let me know.
> Thanks a lot.
> 

The MALCOLM home page is at:

http://vega.unive.it/~alex/GRETA/MALCOLM/

You should be able to order a copy there--I believe it's about $40 
(US) for a student copy (note that it is NOT shareware or freeware to 
the best of my knowledge).

Sincerely,
Tom Maycock
Estima


------------------------------------------------------------
|   Estima                    |  Sales:   (800) 822-8038   |
|   P.O. Box 1818             |  Support: (847) 864-1910   |
|   Evanston, IL 60204-1818   |  Fax:     (847) 864-6221   |
|   USA                       |  estima@estima.com         |
|                             |  http://www.estima.com     |
------------------------------------------------------------

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

From: "Jürgen Jerger" <jergerju@vwl.uni-freiburg.de>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Re: 
Date: Mon, 09 Dec 1996 15:14:48 +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: Mozilla 4.04 [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'm a French PhD candidate working on monetary policy transmission
> > process. I would like to run a structural VAR using RATS. Please anybody
> > who has heard about MALCOLM let me know about it. I tried to subscribe
> > but nobody answered. I know there is a beta version. If you have it,
> > if you have heard about it, please let me know.
> > Thanks a lot.
> >
> 
> The MALCOLM home page is at:
> 
> http://vega.unive.it/~alex/GRETA/MALCOLM/
> 
> You should be able to order a copy there--I believe it's about $40
> (US) for a student copy (note that it is NOT shareware or freeware to
> the best of my knowledge).


Well, that's the point. Like Alain, I tried to order MALCOLM exactly
from this Web-address - without any response, however.
Any information about the availablity of the program (and documentation)
would be very welcome. Regards, Juergen

 
*******************************************************************
Dr. Juergen Jerger		email: jergerju@vwl.uni-freiburg.de
Universitaet Freiburg		Tel.:  ++49-(0)761/203-2325	
Platz der Alten Synagoge	Fax.:  ++49-(0)761/203-2405	
79085 Freiburg
GERMANY
*******************************************************************

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

From: daniela marconi <daniela_marconi@yahoo.com>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Re: 
Date: Wed, 9 Dec 1998 21:32:19 +0800 (SGT)
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 Astier,
I know MALCOLM I used it for my final dissertation.
You can try to contact the Autor of MALCOLM: Rocco Mosconi
<rocco.mosconi@polimi.it>.
Bye.
D.M.   



---Alain Astier <astier@ipnl.in2p3.fr> wrote:
>
> Hello everybody,
> 
>   I'm a French PhD candidate working on monetary policy transmission
> process. I would like to run a structural VAR using RATS. Please
anybody
> who has heard about MALCOLM let me know about it. I tried to subscribe
> but nobody answered. I know there is a beta version. If you have it,
> if you have heard about it, please let me know.
> Thanks a lot.
> 
>   F. Astier
> 
> 

_________________________________________________________
DO YOU YAHOO!?
Get your free @yahoo.com address at http://mail.yahoo.com


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

From: Rocco Mosconi <mosconi@cdc8g5.cdc.polimi.it>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Re: 
Date: Wed, 09 Dec 1998 16:50:02 +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: Politecnico di Milano
X-Mailer: Mozilla 4.03 [en] (Win95; I) (via Mercury MTS (Bindery) v1.40)
MIME-Version: 1.0
Content-Type: text/plain; charset=iso-8859-1
Content-Transfer-Encoding: quoted-printable

J=FCrgen Jerger wrote:

> Well, that's the point. Like Alain, I tried to order MALCOLM exactly
> from this Web-address - without any response, however.
> Any information about the availablity of the program (and documentation=
)
> would be very welcome. Regards, Juergen


I take the opportunity to apologize to those who have recently asked me
informations about MALCOLM, Juergen first. I have been very busy
lately, but they will receive the last beta version of MALCOLM (before
the final release) in a matter of days, together with those who have
requested the program at http://vega.unive.it/~alex/GRETA/MALCOLM/
after Tom's posting to the list.
MALCOLM homepage is a bit outdated, but still working. I am rewriting
it and moving it to a new address next week. You will find the link at th=
e
old address, and all MALCOLM beta testers will be informed directly.
The final version will start shipping around January 15, as soon as the
manual (approx 230 pages) is printed. This means that the manual is not
available now, but the program is menu driven and rather self explained.
More information will be soon available in the new MALCOLM homepage.

Sincerely,

Rocco Mosconi
--
__________________________________________________
Dipartimento di Economia e Produzione
Politecnico di Milano
Piazza L. da Vinci 32, 20133 Milano
Phone: (39)-02-23992747; Fax: (39)-02-23992710
rocco.mosconi@polimi.it or rocco@mosconi.it
"The difference between theory and practice is
greater in practice than in theory." (John Wilkes)
__________________________________________________



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

From: Agust Eiriksson <Aeirik1@uic.edu>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Just testing , you can delete this message
Date: Thu, 10 Dec 1998 08:05:53 -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>
X-Mailer: QUALCOMM Windows Eudora Pro Version 4.0 (via Mercury MTS (Bindery) v1.40)
Mime-Version: 1.0
Content-Type: text/plain; charset="us-ascii"



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

From: "Guido Travaglini" <g_2002@hotmail.com>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Re: Just testing , you can delete this message
Date: Thu, 10 Dec 1998 10:02:22 PST
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
X-Mailer: Mercury MTS (Bindery) v1.40

Testing message received. Thanx and Happy Christmas. Guido Travaglini.

>From rats-l-owner@efs.mq.edu.au Thu Dec 10 06:25:13 1998
>Received: from [137.111.1.11] by hotmail.com (1.0) with SMTP id 
MHotMail30907524086035065324952305753355502410; Thu Dec 10 06:25:13 1998
>Received: from efs1.efs.mq.edu.au (efs1.efs.mq.edu.au [137.111.64.8])
>	by sunb.ocs.mq.edu.au (8.9.0/8.9.0) with ESMTP id AAA16063;
>	Fri, 11 Dec 1998 00:55:28 +1100 (EST)
>Received: from EFS1/SpoolDir by efs1.efs.mq.edu.au (Mercury 1.40);
>    11 Dec 98 00:58:27 GMT+1000
>Received: from SpoolDir by EFS1 (Mercury 1.40); 11 Dec 98 00:56:35 
GMT+1000
>From: Agust Eiriksson <Aeirik1@uic.edu>
>To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
>Subject: Just testing , you can delete this message
>Date: Thu, 10 Dec 1998 08:05:53 -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>
>X-Mailer: QUALCOMM Windows Eudora Pro Version 4.0 (via Mercury MTS 
(Bindery) v1.40)
>Mime-Version: 1.0
>Content-Type: text/plain; charset="us-ascii"
>Message-ID: <C91F894021@efs1.efs.mq.edu.au>
>
>


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

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

From: Alejandro Jara <ajara@ucla.edu>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: SWARCH estimations
Date: Sun, 13 Dec 1998 15:00:54 -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>
Organization: The Anderson School at UCLA
X-Mailer: Mozilla 3.01Gold (Win95; I) (via Mercury MTS (Bindery) v1.40)
MIME-Version: 1.0
Content-Type: text/plain; charset=euc-kr
Content-Transfer-Encoding: 7bit

I'd like to estimate volatitity switching regimes for an interest
rate data that I have. Any advise from someone who has used it before?
Thanks,
Alejandro Jara
Econ. Dept. UCLA

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

From: hideakii <hideakii@yahoo.com>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: BDS.src
Date: Tue, 15 Dec 1998 03:20:28 +0000 (GMT)
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; boundary="0-1632621729-913692028=:28832"
X-Mailer: Mercury MTS (Bindery) v1.40

--0-1632621729-913692028=:28832
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline

Dear RATS Users

I made a procedure which execute BDS test,which tests series is whether I.I.D. or not, in which null hypothesis is I.I.D.

I am not sure this is correct or not.Then, could someone check this procedure? If there is a suggestion, please let me know.

Thanx in advance

ISHIGAMI,Hideaki
Nippon Sports Science Univ.
_________________________________________________________
DO YOU YAHOO!?
Get your free @yahoo.com address at http://mail.yahoo.com

--0-1632621729-913692028=:28832
Content-Type: text/plain; name="Bds.src"
Content-Description: Bds.src
Content-Disposition: inline; filename="Bds.src"

****************************************************
/*     Brock, Dechert, & Scheinkman Test Static
	   
	   Null Hypothesis is IID

	   Brock,W.A., D.A. Hsieh, and B.Lebaron
	   _Nonlinear Dynamics,Chaos,and Instability_,
	   MIT Press,1993,Chap.2

      by Hideaki ISHIGAMI
*/
****************************************************


Procedure BDS series start end

type series series
type integer start end

local integer startl endl m nobs
local real std eps n cmt c1t K var bdst signif

option real p 1.

inquire(series=series) startl>>start endl>>end


********** Sets eps and M ********************

compute std=eps=n=0.
compute m=0

statistics(noprint) series startl endl
compute std=sqrt(%variance)
compute eps=p*std                ;* eps is threshold value for indicator function,
                                  * it should be .5*std < eps < 2*std 

compute nobs=endl-startl+1

if(nobs.le.400)
{
	dis 'Too small sample to do BDS test!'
	halt
}
else if(nobs.gt.400){
	 if(nobs.le.600)        {
						    compute m=2    ;* T/m should be greater than 200
					        }
     else if(nobs.le.800)   {
							compute m=3
							}
	 else if(nobs.le.1000)  {
							compute m=4
 							}
     else if(nobs.gt.1000)  {
							compute m=5     ;* m is no greater than 5
                            }
}
compute n=nobs-m+1


************ Computation of Correlation Integral ****************

* Computation of C_mt(eps)

compute indic=indics=dif=diff= 0.
compute r=startl
compute s=startl+1
compute j=0

while r.le.(endl-m){
			while s.le.(endl-m+1){
						while j.le.(m-1){
										compute dif =abs(series(r+j)-series(s+j))
										compute max=%if(dif.ge.diff,dif,diff)
										compute diff=dif
										compute j=j+1
										}
								compute indic=%if(max<eps,1,0)
								compute indics=indics+indic
								compute s=s+1
								compute j=0
								}
				compute r=r+1
				compute s=r+1
				}

compute cmt=indics/(n*(n-1)/2.)

* Computation of C_1t

compute norm=indic=c1t=dmt =0.
compute r=startl+1
compute s=startl

while s.le.(endl-1){
			while r.le.endl{
							compute norm= %if(abs(series(r)-series(s))<eps,1,0)
							compute indic= indic+norm
							compute r=r+1
							}
					compute s=s+1
					compute r=s+1
					}

compute c1t=indic/((nobs)*(nobs-1)/2.)


*********** Computation of Variance of D_mt*********************

* Computation of K

compute knorm=sumh=sumhh=k=0.

compute u=j=startl
while u.le.endl{
				while j.le.endl{
								compute knorm = %if(abs(series(u)-series(j))<eps,1,0)
								compute sumh  = sumh+knorm
								compute j=j+1
								}
				compute sumhh=sumhh+(sumh**2)
				compute u=u+1
				compute j=startl
				compute sumh=0.
				}

compute K=sumhh/(nobs**3.)


* Computation of Variance

compute var=z=sumz=0.

compute j=1
while j.le.m-1{
				compute z = (k**(m-j))*(c1t**(2*j))
				compute sumz=sumz+z
				compute j=j+1
				}

compute var=4*((k**m)+(2*sumz)+((m-1)**2)*(c1t**(2*m)) $
              -(m**2)*k*(c1t**(2*m-2)))


************** Computation of BDS statistic ********************

compute bdst=0.
compute bdst=sqrt(nobs)*(cmt-c1t**m)/sqrt(var)

cdf(noprint) normal bdst
compute signif=%if(%valid(%signif),%signif, 0.00000)


dis ''
dis ''
dis ''
dis @6 '************************************'
dis @12 'BDS Test for' %label(series) 
dis @8 '�\�\�\�\�\�\�\�\�\�\�\�\�\�\�\�\'
dis @11 '     P =' p
dis @11 '   eps =' eps 
dis @11 '     m =' @+6 # m
dis @11 '  C_mT =' cmt
dis @11 '   C_T =' c1t
dis @11 '     K =' k
dis @11 'sigma2 =' var
dis @11 '  BDS  =' bdst
dis @11 'signif =' signif
dis @6 '************************************'
dis ''
dis ''
dis ''


End BDS

--0-1632621729-913692028=:28832--

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

From: WOO KAI YIN <kywoo@ctimail.com>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: RE: request codes for GMM f
Date: Thu, 17 Dec 1998 00:41:49 +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

Dear RATS users,

Might I ask for codes to perform GMM estimation with possibley
non-stationary regressors and instruments which method comes from :

"Fully modified IV, GIVe and GMM estimation with possibly non-stationary
regressors and instruments", Kitamura, Phillips, J. of Econometrics,
1997, vol80 No.1, p85-123.

Thank you for your help!


Regards,

Kai-yin Woo
Dept of Economics,
Hong KOng Shue Yan College

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

From: "Estima" <estima@estima.com>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Newsletter and MacRATS Update Info
Date: Wed, 16 Dec 1998 17:12:01 -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)

Dear everyone:

We just sent off the latest issue of the RATSLetter to the printer. 
Users should begin receiving their copies in the mail in about 2 
weeks (if you've moved, send us your new address now!). The 
newsletter text will probably be posted to the Web at about the same 
time.

Included are articles on Markov Chain models, Gibbs sampling and some 
related sampling techniques, and, among other news, information on 
the upcoming release of MacRATS 4.3, scheduled to begin shipping in 
February! This will include a very speedy PowerMac version.

So, watch your mailboxes.

Thanks,
Tom Maycock
Estima



------------------------------------------------------------
|   Estima                    |  Sales:   (800) 822-8038   |
|   P.O. Box 1818             |  Support: (847) 864-1910   |
|   Evanston, IL 60204-1818   |  Fax:     (847) 864-6221   |
|   USA                       |  estima@estima.com         |
|                             |  http://www.estima.com     |
------------------------------------------------------------

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

From: jankowski@ait.fredonia.edu (Dick Jankowski)
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Monte Carlo Simulation
Date: Wed, 16 Dec 1998 20:00:27 -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 Version 1.4.4 (via Mercury MTS (Bindery) v1.40)
Mime-Version: 1.0
Content-Type: text/plain; charset="us-ascii"

        Has anyone written a program in RATS to do a Monte Carlo simulation
for small sample (n=43) cointegration rank tests?
        Thanks in advance.
        
        Dick Jankowski
        SUNY at Fredonia


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

From: Lawrence_WONG@MTI.gov.sg
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Blanchard & Quah decomposition
Date: Thu, 17 Dec 1998 19:05:55 +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>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
X-Mailer: Mercury MTS (Bindery) v1.40


Hi,
I'm currently working on a RATS code to do the Blanchard and Quah decomposition
to derive a core inflation measure, a la Quah and Vahey (1995). As in the
paper, I have a bivariate model of GDP and CPI.
I've managed to estimate the D(0) matrix & recovered the demand and supply
shocks. But I'm stuck at the next step of deriving a historical series for core
inflation

In its decomposed form,  d(CPI) = Sum [D11(L)*(supply shocks)] +
Sum[D12(L)*(demand shocks)]

I should be able to derive the core inflation series by assuming that supply
shocks = 0 in the equation above. Then, having recovered the demand shocks, and
retrieving the D12(L) elements, I should be able to get a series of
"output-neutral inflation"
But isn't the above eqn supposed to be an infinite MA process!
With a fairly short time series (only 80 observations), how is it possible to
derive a historical series of core inflation using this method?
Do I have to truncate the MA lags to a more manageable lag length?
But if I do so, will I still be able to get an accurate measure of core
inflation?

I've been trying to understand this problem for some time now - really
appreciate if anyone out there could lend a helping hand. Thanks!!

Lawrence Wong, Singapore
(Email: Lawrence_WONG@MTI.GOV.SG)


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

From: Rocco Mosconi <mosconi@cdc8g5.cdc.polimi.it>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: MALCOLM
Date: Tue, 22 Dec 1998 19:42:31 +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: Politecnico di Milano
X-Mailer: Mozilla 4.03 [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 RATS user,
a quick note to say that the new MALCOLM homepage is ready
(http://www.greta.it/malcolm).

MC & HNY,

Rocco Mosconi
--
__________________________________________________
Dipartimento di Economia e Produzione
Politecnico di Milano
Piazza L. da Vinci 32, 20133 Milano
Phone: (39)-02-23992747; Fax: (39)-02-23992710
rocco.mosconi@polimi.it or rocco@mosconi.it
"The difference between theory and practice is
greater in practice than in theory." (John Wilkes)
__________________________________________________



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

From: "Stuart M. Glosser" <glossers@uwwvax.uww.edu>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Re: MALCOLM
Date: Tue, 22 Dec 1998 13:26:54 -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
Content-Type: text/plain; charset="us-ascii"
X-Mailer: Mercury MTS (Bindery) v1.40

>Dear RATS user,
>a quick note to say that the new MALCOLM homepage is ready

Rocco,
Please explain how Malcom compares to Cats. If I  already have Cats, is
there a good reason to also have Malcom?

Sincerely,

Stuart Glosser




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

From: Mikko Syrjanen <k24360@kyyppari.hkkk.fi>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: unsubscribe
Date: Wed, 23 Dec 1998 09:29:12 +0200 (EET)
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


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

From: WOO KAI YIN <kywoo@ctimail.com>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Re: MALCOLM
Date: Thu, 24 Dec 1998 00:43:33 +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

Stuart M. Glosser wrote:
> 
> >Dear RATS user,
> >a quick note to say that the new MALCOLM homepage is ready
> 
> Rocco,
> Please explain how Malcom compares to Cats. If I  already have Cats, is
> there a good reason to also have Malcom?
> 
> Sincerely,
> 
> Stuart Glosser
Dear RATS users,

I have the same question. 

Regards,

KY Woo

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

From: Hitomi Kazumi <hitomi@criepi.denken.or.jp>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: unsubscribe
Date: Mon, 28 Dec 98 10:31:05 -0000
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: Claris Emailer-J 1.1 (via Mercury MTS (Bindery) v1.40)
Mime-Version: 1.0
Content-Type: text/plain; charset="US-ASCII"

unsubscribe

----------------------------------------------------------
Kazumi Hitomi  (hitomi@criepi.denken.or.jp)

Central Research Institute of Electric Power Industry
Socio-Economic Research Center
1-6-1 Ohtemachi, Chiyoda-ku, Tokyo 100 JAPAN
Phone +81 3 3201 6601 :  Fax +81 3 3287 2805



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

From: Rocco Mosconi <mosconi@cdc8g5.cdc.polimi.it>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Re: MALCOLM
Date: Tue, 29 Dec 1998 11:11:56 +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: Politecnico di Milano
X-Mailer: Mozilla 4.03 [en] (Win95; I) (via Mercury MTS (Bindery) v1.40)
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit

> Please explain how Malcom compares to Cats. If I  already have Cats, is
> there a good reason to also have Malcom?

This is a FAQ about MALCOLM. Advertising is (I guess) out of the rules in
the list. Hence, someone else should answer this question, after testing
both programs (not too many people, to avoid bothering the uninterested
RATS users).  I would like to see the answer too. Just a few words, since I
have been directly asked ...
I did not see the most recent version of CATS, but I would say that the
overlapping between the programs is large as far as cointegration analysis
is concerned. There are some features in MALCOLM (non cusality, some joint
restrictions on alfa and beta, forecasting, ...) which, I think, are not in
CATS, but probably the opposite statement is also correct. MALCOLM is made
up by several procedures, fully documented in the manual, which may be used
outside MALCOLM as a "cointegration library" in RATS: I do not know about
CATS on this respect.
The major difference is that, in MALCOLM, cointegration analysis is
completely integrated with Structural VAR analysis (including impulse
responses with bounds, forecast error variance decomposition ...). The
programming of this section of MALCOLM (also made up of several possibly
stand-alone subroutines) is due to Gianni Amisano and Mario Seghelini,
based on Amisano-Giannini, Topics in Structural VAR Econometrics, Springer
Verlag, 1997. Another feature of MALCOLM is that univariate unit root
analysis is also supported.
As a whole, my feeling is that it is probably useful for "cointegrators" to
have both programs, and for SVAR people to have MALCOLM.

Apologies to all those who are not interested, and Happy New Year to
everybody.

Rocco Mosconi

--
__________________________________________________
Dipartimento di Economia e Produzione
Politecnico di Milano
Piazza L. da Vinci 32, 20133 Milano
Phone: (39)-02-23992747; Fax: (39)-02-23992710
rocco.mosconi@polimi.it or rocco@mosconi.it
"The difference between theory and practice is
greater in practice than in theory." (John Wilkes)
__________________________________________________



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

From: Hiroshi KAMYAMA <kameyama@ag.kagawa-u.ac.jp>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: unsubscribe
Date: Tue, 29 Dec 1998 11:57:23 +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; boundary="---- =_NextPart_000_01BE338B.C65CE500"
X-Mailer: Mercury MTS (Bindery) v1.40


------ =_NextPart_000_01BE338B.C65CE500
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: 7bit

unsubscribe
Hiroshi KAMEYAMA
Associate Professor 
College of Agriculture
Kagawa University
2393 Ikenobe Miki-cho 
Kitagun, Kagawa
Japan 761-07
tel&fax:81+087+891+3054(direct)

------ =_NextPart_000_01BE338B.C65CE500
Content-Type: application/ms-tnef
Content-Transfer-Encoding: base64
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------ =_NextPart_000_01BE338B.C65CE500--


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

From: "Huu Minh Mai" <mai@monep.fr>
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: unsubscribe
Date: Wed, 30 Dec 1998 08:19:54 +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: Mozilla 4.05 [fr] (Win95; I) (via Mercury MTS (Bindery) v1.40)
MIME-Version: 1.0
Content-Type: text/plain; charset=iso-8859-1
Content-Transfer-Encoding: 8bit



--
Huu Minh MAI
Responsable des Recherches et Développements
Head of Research & Development
MONEP SA
39, rue Cambon
75001 Paris - France
Phone : 33 1 49 27 18 62
Fax   : 33 1 49 27 18 23
Email : mai@monep.fr



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

From: jankowski@ait.fredonia.edu (Dick Jankowski)
To: "RATS Discussion List" <RATS-L@efs.mq.edu.au>
Subject: Monte Carlo Simulations
Date: Wed, 30 Dec 1998 13:33:08 -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 Version 1.4.4 (via Mercury MTS (Bindery) v1.40)
Mime-Version: 1.0
Content-Type: text/plain; charset="us-ascii"

        I am doing some cointegration analysis but my sample size is small
(n=43).  Hence, I need to do some Monte Carlo simulations for cointegration
rank tests.  Does anyone have and know of any programs (in any language:
Gauss, Pascal, Rats etc) that perform Monte Carlo simulations for
cointegration rank tests?
        Thanks for any help in advance.

        Dick Jankowski
        SUNY at Fredonia


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