From ???@??? Thu Dec 02 08:48:04 1999 Received: from localhost (localhost [127.0.0.1]) by amethyst.efs.mq.edu.au (8.9.1/8.9.1) with ESMTP id GAA15438 for ; Thu, 2 Dec 1999 06:00:05 +1100 Message-Id: <199912011900.GAA15438@amethyst.efs.mq.edu.au> Received: from efs1.efs.mq.edu.au by localhost with POP3 (fetchmail-5.0.0) for robt@localhost (single-drop); Thu, 02 Dec 1999 06:00:05 +1100 (EETDT) Received: from SpoolDir by EFS1 (Mercury 1.40); 2 Dec 99 05:57:25 GMT+1000 From: Galindo Andrade Arturo To: "RATS Discussion List" Subject: SWARCH Date: Wed, 1 Dec 1999 13:57:45 -0500 Errors-to: Reply-to: "RATS Discussion List" Sender: Maiser@efs1.efs.mq.edu.au X-listname: MIME-Version: 1.0 X-Mailer: Internet Mail Service (5.5.2448.0) (via Mercury MTS (Bindery) v1.40) Content-Type: text/plain; > Dear friends. > > Has anyone had success in the estimation of a SWARCH model in RATS? > I'm doing the following, but its not working: > > DECLARE SERIES U1 > DECLARE SERIES U2 > DECLARE SERIES h1 > DECLARE SERIES h2 > nonlin p12 p21 a01 a02 d01 d11 d02 d12 > frml reg1 = x - a01 > frml reg2 = x - a02 > frml sig1 = d01 + d11*U1{1}**2 > frml sig2 = d02 + d12*U2{1}**2 > set pstar = 0.5 > frml markov = $ > (U1(T)=reg1(T)),(U2(T)=reg2(T)),(H1(T)=sig1(T)),(H2(T)=sig2(T)), > f1=%density(U1{0}/H1(T))/H1(T),$ > f2=%density(U2{0}/H2(T))/H2(T),$ > rp1=f1*(p21*(1-pstar{1})+(1-p12)*pstar{1}) ,$ > rp2=f2*((1-p21)*(1-pstar{1}) + p12*pstar{1}) ,$ > pstar=rp1/(rp1+rp2),log(rp1+rp2) > linreg(noprint) x / U1; # constant > set U2 = U1 / 2 > set h1 = %seesq > set h2 = h1 / 2 > maximize markov 1994:02:08 * > I get the following error message > ## MAT13. Store into Out-of-Range Matrix or Series Element > I have tried several initial values but I'm still getting the same message > I would really appreciate it, if someone out there can give me a hand. > > In advance thanks, > > Arturo Galindo > > From ???@??? Mon Dec 06 21:40:44 1999 Received: from localhost (localhost [127.0.0.1]) by amethyst.efs.mq.edu.au (8.9.1/8.9.1) with ESMTP id VAA14630 for ; Mon, 6 Dec 1999 21:40:04 +1100 Message-Id: <199912061040.VAA14630@amethyst.efs.mq.edu.au> Received: from efs1.efs.mq.edu.au by localhost with POP3 (fetchmail-5.0.0) for robt@localhost (single-drop); Mon, 06 Dec 1999 21:40:04 +1100 (EETDT) Received: from SpoolDir by EFS1 (Mercury 1.40); 6 Dec 99 21:38:25 GMT+1000 From: "Guido Travaglini" To: "RATS Discussion List" Subject: LABELS & LOOPS Date: Mon, 06 Dec 1999 02:38:53 PST Errors-to: Reply-to: "RATS Discussion List" Sender: Maiser@efs1.efs.mq.edu.au X-listname: Mime-Version: 1.0 Content-Type: text/plain; format=flowed X-Mailer: Mercury MTS (Bindery) v1.40 To RATS DISCUSSION LIST MEMBERS: Some steps in the LABELS command of the manual are unclear to me, especially when it comes to naming new series generated within a loop. I have: all 0 2464 open data d:\winrats/data/nya9099.dat data(for=free,org=obs) / COMP IND TRANS UTIL FIN scratch 100 / ** The above series are automatically numbered 1 to 5 by RATS. ** Now I want to log transform the original series: do i = 1,5 log i / i+10 end do i ** ... and to first difference the new series: do i = 1,5 diff i+10 / i+20 end do i * Question is: how can I name the new numbered series 11 to 15 and 21 to 25 by appending an extension to the name of the original series, e.g LOGCOMP for the log transformation of COMP and DLCOMP for its logged first difference? I would be grateful for any help, thanx in advance, Guido. ______________________________________________________ Get Your Private, Free Email at http://www.hotmail.com From ???@??? Tue Dec 07 09:59:42 1999 Received: from localhost (localhost [127.0.0.1]) by amethyst.efs.mq.edu.au (8.9.1/8.9.1) with ESMTP id JAA14360 for ; Tue, 7 Dec 1999 09:55:04 +1100 Message-Id: <199912062255.JAA14360@amethyst.efs.mq.edu.au> Received: from efs1.efs.mq.edu.au by localhost with POP3 (fetchmail-5.0.0) for robt@localhost (single-drop); Tue, 07 Dec 1999 09:55:04 +1100 (EETDT) Received: from SpoolDir by EFS1 (Mercury 1.40); 7 Dec 99 09:51:03 GMT+1000 From: "Vasquez Escobar Diego M." To: "RATS Discussion List" Subject: Question Date: Mon, 6 Dec 1999 17:51:20 -0500 Errors-to: Reply-to: "RATS Discussion List" Sender: Maiser@efs1.efs.mq.edu.au X-listname: MIME-Version: 1.0 X-Mailer: Internet Mail Service (5.5.2650.21) (via Mercury MTS (Bindery) v1.40) Content-Type: text/plain; Dear Rats users: I need to generate a sequence of matrixes in the following way. I have N subsamples of data, for each sub sample I need to generate the matrix XX_N = (X_N'X_N)**-1. So at the end I will have N matrixes of this kind. Is there a way to do this in a loop so that at the end I have XX(1),XX(2)....XX(N) in a similar way that I could do, when I have vectors of series? I have in mind something like: do j = 1,N linreg(noprint,smpl=dummies(j)) y ; # constant x compute xx(N) = %xx end do j but of course the line 'compute xx(N) = %xx' does not work with rats because xx are matrixes. Can someone please help me? Thanks, Diego Vasquez From ???@??? Wed Dec 08 10:13:45 1999 Received: from localhost (localhost [127.0.0.1]) by amethyst.efs.mq.edu.au (8.9.1/8.9.1) with ESMTP id WAA14202 for ; Tue, 7 Dec 1999 22:50:04 +1100 Message-Id: <199912071150.WAA14202@amethyst.efs.mq.edu.au> Received: from efs1.efs.mq.edu.au by localhost with POP3 (fetchmail-5.0.0) for robt@localhost (single-drop); Tue, 07 Dec 1999 22:50:04 +1100 (EETDT) Received: from SpoolDir by EFS1 (Mercury 1.40); 7 Dec 99 22:47:06 GMT+1000 From: "Wong, King" To: "RATS Discussion List" Subject: compatibility problems with win98 Date: Tue, 7 Dec 1999 11:49:40 -0000 Errors-to: Reply-to: "RATS Discussion List" Sender: Maiser@efs1.efs.mq.edu.au X-listname: MIME-Version: 1.0 X-Mailer: Internet Mail Service (5.5.1960.3) (via Mercury MTS (Bindery) v1.40) Content-Type: text/plain winrats 4.31 with win 98 brings up fatal errors when run in DOS box, and out of memory errors. Anyone experience similar problems? Cheers King From ???@??? Wed Dec 08 10:15:51 1999 Received: from localhost (localhost [127.0.0.1]) by amethyst.efs.mq.edu.au (8.9.1/8.9.1) with ESMTP id EAA06632 for ; Wed, 8 Dec 1999 04:00:04 +1100 Message-Id: <199912071700.EAA06632@amethyst.efs.mq.edu.au> Received: from efs1.efs.mq.edu.au by localhost with POP3 (fetchmail-5.0.0) for robt@localhost (single-drop); Wed, 08 Dec 1999 04:00:04 +1100 (EETDT) Received: from SpoolDir by EFS1 (Mercury 1.40); 8 Dec 99 03:39:03 GMT+1000 From: "Estima" To: "RATS Discussion List" Subject: Re: Question Date: Tue, 7 Dec 1999 10:12:23 -0600 Errors-to: Reply-to: "RATS Discussion List" Sender: Maiser@efs1.efs.mq.edu.au X-listname: Organization: Estima MIME-Version: 1.0 Content-type: text/plain; charset=US-ASCII Content-transfer-encoding: 7BIT X-mailer: Pegasus Mail for Win32 (v3.11) (via Mercury MTS (Bindery) v1.40) > > I have in mind something like: > > do j = 1,N > linreg(noprint,smpl=dummies(j)) y ; # constant x > compute xx(N) = %xx > end do j > > but of course the line 'compute xx(N) = %xx' does not work with rats because > xx are matrixes. > It will if you first define XX as a VECTOR of RECTANGULAR arrays. Also, I think you meant to use "j", rather than "N" as the subscript reference on COMPUTE. For example: declare vector[rectangular] xx(N) do j = 1,N linreg(noprint,smpl=dummies(j)) y ; # constant x compute xx(j) = %xx end do j You can refer to a particular matrix as "xx(1)", "xx(2)", etc. 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 | ------------------------------------------------------------ From ???@??? Fri Dec 10 04:05:42 1999 Received: from localhost (localhost [127.0.0.1]) by amethyst.efs.mq.edu.au (8.9.1/8.9.1) with ESMTP id EAA14730 for ; Fri, 10 Dec 1999 04:00:04 +1100 Message-Id: <199912091700.EAA14730@amethyst.efs.mq.edu.au> Received: from efs1.efs.mq.edu.au by localhost with POP3 (fetchmail-5.0.0) for robt@localhost (single-drop); Fri, 10 Dec 1999 04:00:04 +1100 (EETDT) Received: from SpoolDir by EFS1 (Mercury 1.40); 10 Dec 99 03:56:14 GMT+1000 From: Galindo Andrade Arturo To: "RATS Discussion List" Subject: Handling regressors Date: Thu, 9 Dec 1999 11:56:29 -0500 Errors-to: Reply-to: "RATS Discussion List" Sender: Maiser@efs1.efs.mq.edu.au X-listname: MIME-Version: 1.0 X-Mailer: Internet Mail Service (5.5.2650.21) (via Mercury MTS (Bindery) v1.40) Content-Type: text/plain; Dear Rats users: When I have a vector of series call them x of dimension 3, that is x(1), x(2),x(3) I can regress y on all of them at the same time using linreg y ; # x this way I will obtain output of the form Dependent Variable y - Estimation by Least Squares Panel(55) of Monthly Data From 1//1995:02 To 28//1999:08 Usable Observations 1176 Degrees of Freedom 1173 Total Observations 1540 Skipped/Missing 364 Centered R**2 0.485420 R Bar **2 0.484543 Uncentered R**2 0.779068 T x R**2 916.184 Mean of Dependent Variable 0.2453858875 Std Error of Dependent Variable 0.2129364098 Standard Error of Estimate 0.1528784539 Sum of Squared Residuals 27.415146826 Regression F(2,1173) 553.2646 Significance Level of F 0.00000000 Durbin-Watson Statistic 0.418154 Variable Coeff Std Error T-Stat Signif **************************************************************************** *** 1. x() 0.234504093 0.010354930 22.64661 0.00000000 2. x() 0.491151924 0.020304034 24.18987 0.00000000 3. x() -1.385837847 0.097787139 -14.17198 0.00000000 How can I do something similar if instead of having my dependent variables in a vector of series I have them defined as a rect[series] say z with i rows and j columns. For example I would like to regress y on the all the j variables that are on the first row of column z . That is y on x(1,1) to x(1,j) Thanks, Arturo Galindo From ???@??? Fri Dec 10 04:35:48 1999 Received: from localhost (localhost [127.0.0.1]) by amethyst.efs.mq.edu.au (8.9.1/8.9.1) with ESMTP id EAA08410 for ; Fri, 10 Dec 1999 04:30:06 +1100 Message-Id: <199912091730.EAA08410@amethyst.efs.mq.edu.au> Received: from efs1.efs.mq.edu.au by localhost with POP3 (fetchmail-5.0.0) for robt@localhost (single-drop); Fri, 10 Dec 1999 04:30:06 +1100 (EETDT) Received: from SpoolDir by EFS1 (Mercury 1.40); 10 Dec 99 04:25:36 GMT+1000 From: Simon.Van-Norden@hec.ca To: "RATS Discussion List" Subject: Re: Handling regressors Date: Thu, 09 Dec 1999 12:28:31 -0500 Errors-to: Reply-to: "RATS Discussion List" Sender: Maiser@efs1.efs.mq.edu.au X-listname: Organization: Ecole des Hautes Etudes Commerciales X-Mailer: Mozilla 4.61 [en] (Win98; U) (via Mercury MTS (Bindery) v1.40) MIME-Version: 1.0 Content-Type: text/plain Content-Transfer-Encoding: 8bit Check out the OVERLAY command. This allows you to create a new VECTOR who elements share the same space in memory as consecutive entries of another vector or matrix. Galindo Andrade Arturo wrote: > > Dear Rats users: > > When I have a vector of series call them x of dimension 3, that is x(1), > x(2),x(3) > I can regress y on all of them at the same time using > > linreg y ; # x > this way I will obtain output of the form > > Dependent Variable y - Estimation by Least Squares > Panel(55) of Monthly Data From 1//1995:02 To 28//1999:08 > Usable Observations 1176 Degrees of Freedom 1173 > Total Observations 1540 Skipped/Missing 364 > Centered R**2 0.485420 R Bar **2 0.484543 > Uncentered R**2 0.779068 T x R**2 916.184 > Mean of Dependent Variable 0.2453858875 > Std Error of Dependent Variable 0.2129364098 > Standard Error of Estimate 0.1528784539 > Sum of Squared Residuals 27.415146826 > Regression F(2,1173) 553.2646 > Significance Level of F 0.00000000 > Durbin-Watson Statistic 0.418154 > > Variable Coeff Std Error T-Stat Signif > **************************************************************************** > *** > 1. x() 0.234504093 0.010354930 22.64661 0.00000000 > 2. x() 0.491151924 0.020304034 24.18987 0.00000000 > 3. x() -1.385837847 0.097787139 -14.17198 0.00000000 > > How can I do something similar if instead of having my dependent variables > in a vector of series I have them defined as a rect[series] say z with i > rows and j columns. > For example I would like to regress y on the all the j variables that are on > the first row of column z . > > That is y on x(1,1) to x(1,j) > > Thanks, > > Arturo Galindo -- Simon van Norden, Prof. agrŽgŽ, www.hec.ca/pages/simon.van-norden Service de l'enseignement de la finance, ƒcole des H.E.C. 3000 Cote-Sainte-Catherine, Montreal QC, CANADA H3T 2A7 simon.van-norden@hec.ca or (514)340-6781 or fax:(514)340-5632 From ???@??? Fri Dec 10 06:25:24 1999 Received: from localhost (localhost [127.0.0.1]) by amethyst.efs.mq.edu.au (8.9.1/8.9.1) with ESMTP id GAA14258 for ; Fri, 10 Dec 1999 06:20:04 +1100 Message-Id: <199912091920.GAA14258@amethyst.efs.mq.edu.au> Received: from efs1.efs.mq.edu.au by localhost with POP3 (fetchmail-5.0.0) for robt@localhost (single-drop); Fri, 10 Dec 1999 06:20:04 +1100 (EETDT) Received: from SpoolDir by EFS1 (Mercury 1.40); 10 Dec 99 06:16:53 GMT+1000 From: "Estima" To: "RATS Discussion List" Subject: Re: Handling regressors Date: Thu, 9 Dec 1999 13:20:09 -0600 Errors-to: Reply-to: "RATS Discussion List" Sender: Maiser@efs1.efs.mq.edu.au X-listname: Organization: Estima MIME-Version: 1.0 Content-type: text/plain; charset=US-ASCII Content-transfer-encoding: 7BIT X-mailer: Pegasus Mail for Win32 (v3.11) (via Mercury MTS (Bindery) v1.40) On 9 Dec 99, at 12:28, Simon.Van-Norden@hec.ca wrote: > Check out the OVERLAY command. > This allows you to create a new VECTOR who elements share the same space in > memory as consecutive entries of another vector or matrix. I haven't actually tried it, but I don't think that's going to work for arrays of series very well. > > > > How can I do something similar if instead of having my dependent variables > > in a vector of series I have them defined as a rect[series] say z with i > > rows and j columns. > > For example I would like to regress y on the all the j variables that are on > > the first row of column z . > > > > That is y on x(1,1) to x(1,j) These are effectively stored columnwise, in the sense that the first i series numbers will correspond to the series in column 1, the next i series numbers will correspond to the series numbers in column 2, and so. So, if you stored your series in column order instead of row order, as suggested above, you could simply do: linreg y # x(1,1) to x(i,1) Otherwise, you could use ENTER in a loop to build up your regressor list. For example, suppose you have set up a rectangular array of series called "S", and you want to use all columns in a particular row as your regressor list. You could do: dec vect[integer] reglist(0) compute row = 1 (specify the desired row here) do col=1,%cols(s) enter(varying) reglist # reglist s(1,col) end do col linreg y # reglist 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 | ------------------------------------------------------------ From ???@??? Fri Dec 10 09:04:57 1999 Received: from localhost (localhost [127.0.0.1]) by amethyst.efs.mq.edu.au (8.9.1/8.9.1) with ESMTP id JAA14126 for ; Fri, 10 Dec 1999 09:00:05 +1100 Message-Id: <199912092200.JAA14126@amethyst.efs.mq.edu.au> Received: from efs1.efs.mq.edu.au by localhost with POP3 (fetchmail-5.0.0) for robt@localhost (single-drop); Fri, 10 Dec 1999 09:00:05 +1100 (EETDT) Received: from SpoolDir by EFS1 (Mercury 1.40); 10 Dec 99 08:56:54 GMT+1000 From: "Maher Chatti" To: "RATS Discussion List" Subject: Scale Date: Thu, 9 Dec 1999 22:53:47 +0100 Errors-to: Reply-to: "RATS Discussion List" Sender: Maiser@efs1.efs.mq.edu.au X-listname: MIME-Version: 1.0 X-Mailer: Microsoft Outlook Express 4.72.3110.5 (via Mercury MTS (Bindery) v1.40) Content-Type: multipart/alternative; ------=_NextPart_000_000D_01BF4298.408CE160 Content-Type: text/plain Dear RATS Users I need to run an old program where a matrix Pi is defined as follows: comp pi1 = scale(-1)*tr(eye+gamma2). But Rats 4.20 cannot recognize the identifier Scale and the manual dont talk about it. Is it an old instruction?. I would be most grateful if anyone can tell me what Scale(-1) represent and how it was replaced by the recent versions of RATS. Thanks in advance. Maher CHATTI E-mail: maher.chatti@gnet.tn ------extPart_000_000D_01BF4298.408CE160 Content-Type: text/html; charsetso-8859-1" Content-Transfer-Encoding: quoted-printable
Dear RATS Users
 
I need to run an old program where a matrix Pi is defined as follows:
 
comp pi1 = scale(-1)*tr(eye+gamma2).
 
But Rats 4.20 cannot recognize the identifier Scale and the manual dont talk about it. Is it an old instruction?. 
 
I would be most grateful if anyone can tell me what Scale(-1) represent and how it was replaced by the recent versions of RATS.
 
Thanks in advance.

Maher CHATTI
------extPart_000_000D_01BF4298.408CE160-- From ???@??? Tue Dec 14 08:01:57 1999 Received: from localhost (localhost [127.0.0.1]) by amethyst.efs.mq.edu.au (8.9.1/8.9.1) with ESMTP id GAA03934 for ; Tue, 14 Dec 1999 06:10:04 +1100 Message-Id: <199912131910.GAA03934@amethyst.efs.mq.edu.au> Received: from efs1.efs.mq.edu.au by localhost with POP3 (fetchmail-5.0.0) for robt@localhost (single-drop); Tue, 14 Dec 1999 06:10:05 +1100 (EETDT) Received: from SpoolDir by EFS1 (Mercury 1.40); 14 Dec 99 06:07:33 GMT+1000 From: Tomo To: "RATS Discussion List" Subject: Fully Modified techniques Date: Mon, 13 Dec 1999 13:08:14 -0600 Errors-to: Reply-to: "RATS Discussion List" Sender: Maiser@efs1.efs.mq.edu.au X-listname: MIME-version: 1.0 Content-type: text/plain; charset=us-ascii Content-transfer-encoding: 7BIT X-Mailer: Mercury MTS (Bindery) v1.40 Dear RATS & CATS users, Hello. I mostly use RATS and CATS for time series analyses. I want to use Fully Modified (FM) techniques such FM-OLS, FM-LAN and FM-VAR created by Peter C. B. Phillips of Cowles Foundation at Yale University. As far as I know, there have been at least three papers that use these techniques in International Finance (only Risk Premium). In those papers, the authors used COINT 2.0 with GAUSS. I asked ESTIMA, but they were not aware of FM techniques. Does that mean RATS users don't use those techniques? At this moment, there exist no source programs posted on ESTIMA's webpage for these techniques. Does anyone use these techniques with RATS? Regards, Tomo U of Oklahoma REFERENCES: P. C. B. Phillips, 1995a, Fully modified least squares and vector autoregression, Econometrica, Vol. 5 (September), pp. 1023-1078. P. C. B. Phillips, 1995b, Robust nonstationary regression, Econometric Theory, Vol. 11, pp. 912-51. P. C. B. Phillips, J. M. McFarland, 1997, Forward exchange market unbiasedness: the case of the Australian dollar since 1984, Journal of International Money and Finance, Vol. 16, pp. 885-907. P. C. B. Phillips, J. M. McFarland and P. C. McMahon, 1996, Robust tests of forward exchange market efficiency with empirical evidence from the 1920s, Journal of Applied Econometrics, Vol. 11, pp. 1-22. From ???@??? Tue Dec 14 08:02:06 1999 Received: from localhost (localhost [127.0.0.1]) by amethyst.efs.mq.edu.au (8.9.1/8.9.1) with ESMTP id HAA12296 for ; Tue, 14 Dec 1999 07:55:04 +1100 Message-Id: <199912132055.HAA12296@amethyst.efs.mq.edu.au> Received: from efs1.efs.mq.edu.au by localhost with POP3 (fetchmail-5.0.0) for robt@localhost (single-drop); Tue, 14 Dec 1999 07:55:04 +1100 (EETDT) Received: from SpoolDir by EFS1 (Mercury 1.40); 14 Dec 99 07:52:25 GMT+1000 From: "Christopher F. Baum" To: "RATS Discussion List" Subject: Re: Fully Modified techniques Date: Mon, 13 Dec 1999 15:53:11 -0500 Errors-to: Reply-to: "RATS Discussion List" Sender: Maiser@efs1.efs.mq.edu.au X-listname: X-Mailer: Mulberry (MacOS) [1.4.4, s/n P020-300786-009] (via Mercury MTS (Bindery) v1.40) MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Peter Pedroni from Indiana U. has used the FM techniques extensively in his panel unit root tests, which are implemented in RATS. Kit Baum Boston College Economics --On Mon, Dec 13, 1999 13:08 -0600 Tomo wrote: > Dear RATS & CATS users, > > Hello. I mostly use RATS and CATS for time series analyses. I want to > use Fully Modified (FM) techniques such FM-OLS, FM-LAN and FM-VAR created > by Peter C. B. Phillips of Cowles Foundation at Yale University. As far > as I know, there have been at least three papers that use these > techniques in International Finance (only Risk Premium). In those > papers, the authors used COINT 2.0 with GAUSS. I asked ESTIMA, but they > were not aware of FM techniques. Does that mean RATS users don't use > those techniques? At this moment, there exist no source programs posted > on ESTIMA's webpage for these techniques. Does anyone use these > techniques with RATS? > > Regards, > > Tomo > U of Oklahoma > > > REFERENCES: > > P. C. B. Phillips, 1995a, Fully modified least squares and vector > autoregression, Econometrica, Vol. 5 (September), pp. 1023-1078. > > P. C. B. Phillips, 1995b, Robust nonstationary regression, Econometric > Theory, Vol. 11, pp. 912-51. > > P. C. B. Phillips, J. M. McFarland, 1997, Forward exchange market > unbiasedness: the case of the Australian dollar since 1984, Journal of > International Money and Finance, Vol. 16, pp. 885-907. > > P. C. B. Phillips, J. M. McFarland and P. C. McMahon, 1996, Robust tests > of forward exchange market efficiency with empirical evidence from the > 1920s, Journal of Applied Econometrics, Vol. 11, pp. 1-22. > > ----------------------------------------------------------------- Kit Baum baum@bc.edu http://fmwww.bc.edu/ec-v/baum.fac.html From ???@??? Tue Dec 14 08:39:12 1999 Received: from localhost (localhost [127.0.0.1]) by amethyst.efs.mq.edu.au (8.9.1/8.9.1) with ESMTP id IAA14190 for ; Tue, 14 Dec 1999 08:35:04 +1100 Message-Id: <199912132135.IAA14190@amethyst.efs.mq.edu.au> Received: from efs1.efs.mq.edu.au by localhost with POP3 (fetchmail-5.0.0) for robt@localhost (single-drop); Tue, 14 Dec 1999 08:35:04 +1100 (EETDT) Received: from SpoolDir by EFS1 (Mercury 1.40); 14 Dec 99 08:32:32 GMT+1000 From: Thamana Lekprichakul To: "RATS Discussion List" Subject: How to turn off display echo? Date: Mon, 13 Dec 1999 11:32:59 -1000 Errors-to: Reply-to: "RATS Discussion List" Sender: Maiser@efs1.efs.mq.edu.au X-listname: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII X-Mailer: Mercury MTS (Bindery) v1.40 Dear RATS users Please excuse me for asking very elementary question. I want to display calculated results and stack them up nicely so that I can import into spreadsheet program in one time. However, in batch mode, RATS keeps echo my display command, which makes my output looked messy. the followings are part of my display commands: Disp @19 'Upper Endpoint' @52 'Lower Endpoint' Disp 'Normal Approximation' @19 ####.#### nauci @52 ####.#### nalci Disp 'Normal Approx. (Qn)' @19 ####.#### nauciq @52 ####.#### nalciq and here is my messy output: Upper Endpoint Lower Endpoint Disp 'Normal Approximation' @19 ####.#### nauci @52 ####.#### nalci Normal Approximatio 0.9414 0.8964 Disp 'Normal Approx. (Qn)' @19 ####.#### nauciq @52 ####.#### nalciq Normal Approx. (Qn) 0.9416 0.8962 I already browsed through the manual but could not find any thing about it. Many thanks in advance for your kind assistance. /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. * ======================================================================== From ???@??? Tue Dec 14 09:31:08 1999 Received: from localhost (localhost [127.0.0.1]) by amethyst.efs.mq.edu.au (8.9.1/8.9.1) with ESMTP id JAA06406 for ; Tue, 14 Dec 1999 09:25:04 +1100 Message-Id: <199912132225.JAA06406@amethyst.efs.mq.edu.au> Received: from efs1.efs.mq.edu.au by localhost with POP3 (fetchmail-5.0.0) for robt@localhost (single-drop); Tue, 14 Dec 1999 09:25:04 +1100 (EETDT) Received: from SpoolDir by EFS1 (Mercury 1.40); 14 Dec 99 09:23:01 GMT+1000 From: Thamana Lekprichakul To: "RATS Discussion List" Subject: How to turn off display echo? Date: Mon, 13 Dec 1999 12:23:39 -1000 Errors-to: Reply-to: "RATS Discussion List" Sender: Maiser@efs1.efs.mq.edu.au X-listname: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII X-Mailer: Mercury MTS (Bindery) v1.40 Dear RATS users Please excuse me for asking very elementary question. I want to display calculated results and stack them up nicely so that I can import into spreadsheet program in one time. However, in batch mode, RATS keeps echo my display command, which makes my output looked messy. the followings are part of my display commands: Disp @19 'Upper Endpoint' @52 'Lower Endpoint' Disp 'Normal Approximation' @19 ####.#### nauci @52 ####.#### nalci Disp 'Normal Approx. (Qn)' @19 ####.#### nauciq @52 ####.#### nalciq and here is my messy output: Upper Endpoint Lower Endpoint Disp 'Normal Approximation' @19 ####.#### nauci @52 ####.#### nalci Normal Approximatio 0.9414 0.8964 Disp 'Normal Approx. (Qn)' @19 ####.#### nauciq @52 ####.#### nalciq Normal Approx. (Qn) 0.9416 0.8962 I already browsed through the manual but could not find any thing about it. Many thanks in advance for your kind assistance. /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. * ======================================================================== From ???@??? Wed Dec 15 08:20:35 1999 Received: from localhost (localhost [127.0.0.1]) by amethyst.efs.mq.edu.au (8.9.1/8.9.1) with ESMTP id MAA15006 for ; Tue, 14 Dec 1999 12:50:03 +1100 Message-Id: <199912140150.MAA15006@amethyst.efs.mq.edu.au> Received: from efs1.efs.mq.edu.au by localhost with POP3 (fetchmail-5.0.0) for robt@localhost (single-drop); Tue, 14 Dec 1999 12:50:04 +1100 (EETDT) Received: from SpoolDir by EFS1 (Mercury 1.40); 14 Dec 99 12:44:06 GMT+1000 From: "Thamana Lekprichakul" To: "RATS Discussion List" Subject: How to turn off display echo? Date: Mon, 13 Dec 1999 15:49:13 -1000 Errors-to: Reply-to: "RATS Discussion List" Sender: Maiser@efs1.efs.mq.edu.au X-listname: MIME-Version: 1.0 Content-Type: text/plain; Content-Transfer-Encoding: 7bit X-Mailer: Microsoft Outlook Express 4.72.3155.0 (via Mercury MTS (Bindery) v1.40) Content-Transfer-Encoding: 7bit Dear RATS users Please excuse me for asking very elementary question. I want to display calculated results and stack them up nicely so that I can import them into spreadsheet program in one step. However, in batch mode, RATS keeps echo my display command, which makes my output looked messy. the followings are part of my display commands: Disp @19 'Upper Endpoint' @52 'Lower Endpoint' Disp 'Normal Approximation' @19 ####.#### nauci @52 ####.#### nalci Disp 'Normal Approx. (Qn)' @19 ####.#### nauciq @52 ####.#### nalciq and here is my messy output: Upper Endpoint Lower Endpoint Disp 'Normal Approximation' @19 ####.#### nauci @52 ####.#### nalci Normal Approximatio 0.9414 0.8964 Disp 'Normal Approx. (Qn)' @19 ####.#### nauciq @52 ####.#### nalciq Normal Approx. (Qn) 0.9416 0.8962 This is what I want to get: Upper Endpoint Lower Endpoint Normal Approximation 0.9414 0.8964 Normal Approx. (Qn) 0.9416 0.8962 I already browsed through the manual but could not find any thing about it. Many thanks in advance for your kind assistance. /Thamana Dept. of Economics U. of Hawaii at Manoa From ???@??? Wed Dec 15 08:22:42 1999 Received: from localhost (localhost [127.0.0.1]) by amethyst.efs.mq.edu.au (8.9.1/8.9.1) with ESMTP id GAA14860 for ; Wed, 15 Dec 1999 06:45:04 +1100 Message-Id: <199912141945.GAA14860@amethyst.efs.mq.edu.au> Received: from efs1.efs.mq.edu.au by localhost with POP3 (fetchmail-5.0.0) for robt@localhost (single-drop); Wed, 15 Dec 1999 06:45:04 +1100 (EETDT) Received: from SpoolDir by EFS1 (Mercury 1.40); 15 Dec 99 06:43:19 GMT+1000 From: "Estima" To: "RATS Discussion List" Subject: Re: How to turn off display echo? Date: Tue, 14 Dec 1999 13:48:47 -0600 Errors-to: Reply-to: "RATS Discussion List" Sender: Maiser@efs1.efs.mq.edu.au X-listname: Organization: Estima MIME-Version: 1.0 Content-type: text/plain; charset=US-ASCII Content-transfer-encoding: 7BIT X-mailer: Pegasus Mail for Win32 (v3.11) (via Mercury MTS (Bindery) v1.40) > > and here is my messy output: > > Upper Endpoint Lower Endpoint > Disp 'Normal Approximation' @19 ####.#### nauci @52 ####.#### nalci > Normal Approximatio 0.9414 0.8964 > Disp 'Normal Approx. (Qn)' @19 ####.#### nauciq @52 ####.#### nalciq > Normal Approx. (Qn) 0.9416 0.8962 > > I already browsed through the manual but could not find any thing about > it. Many thanks in advance for your kind assistance. Use the command: environment noecho at the top of your program to supress echoing of the input lines. 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 | ------------------------------------------------------------ From ???@??? Wed Dec 15 08:23:47 1999 Received: from localhost (localhost [127.0.0.1]) by amethyst.efs.mq.edu.au (8.9.1/8.9.1) with ESMTP id HAA12984 for ; Wed, 15 Dec 1999 07:55:05 +1100 Message-Id: <199912142055.HAA12984@amethyst.efs.mq.edu.au> Received: from efs1.efs.mq.edu.au by localhost with POP3 (fetchmail-5.0.0) for robt@localhost (single-drop); Wed, 15 Dec 1999 07:55:05 +1100 (EETDT) Received: from SpoolDir by EFS1 (Mercury 1.40); 15 Dec 99 07:50:16 GMT+1000 From: "Thamana Lekprichakul" To: "RATS Discussion List" Subject: Thank you Date: Tue, 14 Dec 1999 10:49:55 -1000 Errors-to: Reply-to: "RATS Discussion List" Sender: Maiser@efs1.efs.mq.edu.au X-listname: MIME-Version: 1.0 Content-Type: text/plain; Content-Transfer-Encoding: 7bit X-Mailer: Microsoft Outlook Express 4.72.3155.0 (via Mercury MTS (Bindery) v1.40) Content-Transfer-Encoding: 7bit Dear RATS List, My sincere thanks to those who respond to my inquiry about turning off display echo. I'd like also to apologize to the list for posting repeated messages. It was purely accidental. /Thamana From ???@??? Thu Dec 16 20:06:26 1999 Received: from localhost (localhost [127.0.0.1]) by amethyst.efs.mq.edu.au (8.9.1/8.9.1) with ESMTP id UAA12288 for ; Thu, 16 Dec 1999 20:00:04 +1100 Message-Id: <199912160900.UAA12288@amethyst.efs.mq.edu.au> Received: from efs1.efs.mq.edu.au by localhost with POP3 (fetchmail-5.0.0) for robt@localhost (single-drop); Thu, 16 Dec 1999 20:00:04 +1100 (EETDT) Received: from SpoolDir by EFS1 (Mercury 1.40); 16 Dec 99 19:58:23 GMT+1000 From: "Guido Travaglini" To: "RATS Discussion List" Subject: MATRIX INVERSION Date: Thu, 16 Dec 1999 00:58:46 PST Errors-to: Reply-to: "RATS Discussion List" Sender: Maiser@efs1.efs.mq.edu.au X-listname: Mime-Version: 1.0 Content-Type: text/plain; format=flowed X-Mailer: Mercury MTS (Bindery) v1.40 In dealing with matrix inversion, I've encountered the following: com [symm] invv = inv(v) ## MAT14. Non-invertible Matrix. Using Generalized Inverse for SYMMETRIC. where v is a covariance matrix and its elements are not necessarily large numbers. How can I suppress the error message, under the assumption that RATS performs double digit precision? Thanx in advance for any clarification, Guido. ______________________________________________________ Get Your Private, Free Email at http://www.hotmail.com From ???@??? Sat Dec 18 09:18:28 1999 Received: from localhost (localhost [127.0.0.1]) by amethyst.efs.mq.edu.au (8.9.1/8.9.1) with ESMTP id CAA14384 for ; Sat, 18 Dec 1999 02:30:04 +1100 Message-Id: <199912171530.CAA14384@amethyst.efs.mq.edu.au> Received: from efs1.efs.mq.edu.au by localhost with POP3 (fetchmail-5.0.0) for robt@localhost (single-drop); Sat, 18 Dec 1999 02:30:04 +1100 (EETDT) Received: from SpoolDir by EFS1 (Mercury 1.40); 18 Dec 99 02:08:00 GMT+1000 From: "Estima" To: "RATS Discussion List" Subject: Re: MATRIX INVERSION Date: Thu, 16 Dec 1999 16:01:24 -0600 Errors-to: Reply-to: "RATS Discussion List" Sender: Maiser@efs1.efs.mq.edu.au X-listname: Organization: Estima MIME-Version: 1.0 Content-type: text/plain; charset=US-ASCII Content-transfer-encoding: 7BIT X-mailer: Pegasus Mail for Win32 (v3.11) (via Mercury MTS (Bindery) v1.40) > In dealing with matrix inversion, I've encountered the following: > com [symm] invv = inv(v) > ## MAT14. Non-invertible Matrix. Using Generalized Inverse for SYMMETRIC. > where v is a covariance matrix and its elements are not necessarily large > numbers. How can I suppress the error message, under the > assumption that RATS performs double digit precision? Thanx in > advance for any clarification, Guido. Guido: I'm not quite sure I understand what you are asking (particularly the part of the precision of the computation), but will try to provide some information. First, if you _really_ want to, you can use: environment traperrors to turn on supression of error messages. Note that this won't prevent a fatal error from terminating the program, but it will supress the message (MAT14 can occur as an error that halts the program, or as a warning message, as in a MAXIMIZE estimation, that does not halt the program). In any case, I wouldn't recommend ever using TRAPERRORS unless you really know what you are doing (for one thing, you'll never see other error messages that you might not be expecting). More to the point, are you sure you want to suppress this message? It is after all indicating that RATS is unable to compute a valid inverse matrix using normal means, which is usually indicative of a serious problem. As the message indicates, the program will compute a result by applying a generalized inverse routine _if_ the argument is a symmetric matrix, but that is NOT the same thing as producing a normal inverse matrix. 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 | ------------------------------------------------------------ From ???@??? Mon Dec 27 09:21:17 1999 Received: from SpoolDir by EFS01 (Mercury 1.40); 27 Dec 99 09:32:16 GMT+1000 From: "Alfonso Arpaia" To: "RATS Discussion List" Subject: SVAR and structural representation Date: Sun, 26 Dec 1999 23:34:36 +0100 Errors-to: Reply-to: "RATS Discussion List" Sender: Maiser@efs01.efs.mq.edu.au X-listname: MIME-Version: 1.0 Content-Type: multipart/alternative; X-Mailer: Microsoft Outlook Express 4.72.2106.4 (via Mercury MTS (Bindery) v1.40) ------=_NextPart_000_038F_01BF4FF9.C565D720 Content-Type: text/plain Dear Collegues To get a measure of core inflation , I'm trying to calculate a structural decomposition of inflation with an identification a la Quahand vahey . I'm using Malcolm. I can get the structural impulse response functions (the graphs), but how I can get the the structural decomposition? Thank you Alfonso Arpaia ____________________ email: aarpaia@pelagus.it ------extPart_000_038F_01BF4FF9.C565D720 Content-Type: text/html; charsetso-8859-1" Content-Transfer-Encoding: quoted-printable
Dear Collegues
 
To get a measure of core inflation , I'm trying to calculate a structural decomposition of inflation with an identification a la Quahand vahey . I'm using Malcolm. I can get the  structural impulse response functions (the graphs), but how I can get the the structural decomposition?
Thank you
Alfonso Arpaia
____________________
email: aarpaia@pelagus.it
------extPart_000_038F_01BF4FF9.C565D720-- From ???@??? Fri Dec 31 12:40:30 1999 Received: from SpoolDir by EFS01 (Mercury 1.40); 30 Dec 99 17:46:39 GMT+1000 From: Ying-Man Chung To: "RATS Discussion List" Subject: RE:kalman filtering Date: Tue, 28 Dec 1999 07:42:12 -0800 (PST) Errors-to: Reply-to: "RATS Discussion List" Sender: Maiser@efs01.efs.mq.edu.au X-listname: MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mercury MTS (Bindery) v1.40 Dear RATS users, Is it possible to set the coefficients of the transition equation to be time-varying? Or in other words, the coefficients of the transition equation are also state variables? If possible, can we imlement it by RATS? I will be grateful to anybody for help. Sincerely, Sarah HKSYC __________________________________________________ Do You Yahoo!? Talk to your friends online with Yahoo! Messenger. http://messenger.yahoo.com From ???@??? Fri Dec 31 12:43:49 1999 Received: from SpoolDir by EFS01 (Mercury 1.40); 30 Dec 99 17:46:50 GMT+1000 From: Carlo Di Giorgio To: "RATS Discussion List" Subject: common cycles Date: Tue, 28 Dec 1999 17:03:21 +0100 Errors-to: Reply-to: "RATS Discussion List" Sender: Maiser@efs01.efs.mq.edu.au X-listname: X-Mailer: QUALCOMM Windows Eudora Pro Version 4.2.2 (via Mercury MTS (Bindery) v1.40) Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii"; format=flowed Dear Rats users, I'm looking for a rats procedure for the serial correlation common features test or common cycles test and estimation. At this moment, there exist no source programs posted on Estima's webpage for this technique. Does anyone use this technique with RATS? Thanks Carlo Di Giorgio References: Engle, R.F.-S. Kozicki (1993), "Testing for common features", Journal of Business and Economic Statistics, 11, pp. 369-80 Vahid, F.-R.F. Engle (1993), "Common Trends and Common Cycles", Journal of Applied Econometrics, vol. 8, pp. 341-360