From ???@??? Sat Apr 01 14:39:22 2000 Received: from localhost (localhost [127.0.0.1]) by amethyst.efs.mq.edu.au (8.9.1/8.9.1) with ESMTP id OAA07764 for ; Sat, 1 Apr 2000 14:35:16 +1000 Message-Id: <200004010435.OAA07764@amethyst.efs.mq.edu.au> Received: from efs01.efs.mq.edu.au by localhost with POP3 (fetchmail-5.0.0) for robt@localhost (single-drop); Sat, 01 Apr 2000 14:35:17 +1000 (EET) Received: from SpoolDir by EFS01 (Mercury 1.40); 1 Apr 100 14:34:40 GMT+1000 From: "Christopher F. Baum" To: "RATS Discussion List" Subject: archives Date: Fri, 31 Mar 2000 15:01:43 -0500 Errors-to: Reply-to: "RATS Discussion List" Sender: Maiser@efs01.efs.mq.edu.au X-listname: X-Mailer: Mulberry (MacOS) [1.4.5, 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 Anyone know why the commands to get the archives of this list no longer work? I have always sent an email to maiser@efs.mq.edu.au with a message like 'send rats9912.arc' and gotten a response. Now I just get a bounce from that site saying that this is not a valid email address. Seemed to happen around New Year's, coincidentally... Thanks Kit ----------------------------------------------------------------- Kit Baum baum@bc.edu http://fmwww.bc.edu/ec-v/baum.fac.html From ???@??? Sat Apr 01 14:39:16 2000 Received: from localhost (localhost [127.0.0.1]) by amethyst.efs.mq.edu.au (8.9.1/8.9.1) with ESMTP id OAA07758 for ; Sat, 1 Apr 2000 14:35:16 +1000 Message-Id: <200004010435.OAA07758@amethyst.efs.mq.edu.au> Received: from efs01.efs.mq.edu.au by localhost with POP3 (fetchmail-5.0.0) for robt@localhost (single-drop); Sat, 01 Apr 2000 14:35:16 +1000 (EET) Received: from SpoolDir by EFS01 (Mercury 1.40); 1 Apr 100 14:34:39 GMT+1000 From: Xi Li To: "RATS Discussion List" Subject: RE: Date: Fri, 31 Mar 2000 16:31:48 -0600 Errors-to: Reply-to: "RATS Discussion List" Sender: Maiser@efs01.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; Rob, Thank you for your help. So you mean the se of abs(a) should be the se of estimated a, and se of sqrt(a)*sqrt(a) is the squre of se of estimated a? Thanks and hope you have a nice weekend. Xi -----Original Message----- From: Rob Trevor [mailto:robt@mafc.mq.edu.au] Sent: Wednesday, March 29, 2000 7:13 PM To: RATS Discussion List Subject: Re: There was a discussion you will find in the archives re different ways of forcing a parameter to be non-negative. From memory: abs(a) or sqrt(a)*sqrt(a) or sqrt(a*a) will work and give correct asymptotic se's - some a bit better than others. (I've never had trouble with sqrt(a)*sqrt(a).) From memory the more recent garch procedure on the Estima web site incorporates non-negativity constraints. (The one written by Normin Morin.) If it doesn't, it should be easy to add. (If you want to ensure that the parameters sum to less than 1, just define one of the parameters as the residual and force that to be non-negative.) Cheers Rob At 2:48 PM -0600 26/3/00, Xi Li wrote: >Dear Rob, > >Sorry to send you the second message. I found that you have written >multivariate GARCH procedure in Estima's procedure page. I wonder if your >version of procedure include the positivity constraints on coefficients in >variance processes? > >Thanks a lot and hope you have a nice day. > >Best regards, > >Xi From ???@??? Sat Apr 01 14:38:08 2000 Received: from localhost (localhost [127.0.0.1]) by amethyst.efs.mq.edu.au (8.9.1/8.9.1) with ESMTP id OAA15548 for ; Sat, 1 Apr 2000 14:30:05 +1000 Message-Id: <200004010430.OAA15548@amethyst.efs.mq.edu.au> Received: from efs01.efs.mq.edu.au by localhost with POP3 (fetchmail-5.0.0) for robt@localhost (single-drop); Sat, 01 Apr 2000 14:30:05 +1000 (EET) Received: from SpoolDir by EFS01 (Mercury 1.40); 1 Apr 100 14:29:47 GMT+1000 From: Jason Morris To: "RATS Discussion List" Subject: ICSS Algorithm Date: Fri, 31 Mar 2000 23:08:01 -0500 (EST) 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 Content-Transfer-Encoding: 7bit X-Mailer: mail.com (via Mercury MTS (Bindery) v1.40) Hi, I'm a final year M.Sc student. I'm trying to model Sock exchange data on emerging stock markets, using GARCH. I need to model sudden changes in variance into the GARCH model. I would be grateful if anyone could tell me how to implement(program) the Iterative Cumulative Sums of Squares algorithm (by Inclan and Tiao, 1994), used to detect the number of sudden changes in variance and the time point and magnitude of each detected sudden change in a time series, in RATS. Thanks much ----------------------------------------------- FREE! The World's Best Email Address @email.com Reserve your name now at http://www.email.com From ???@??? Sat Apr 01 14:38:29 2000 Received: from localhost (localhost [127.0.0.1]) by amethyst.efs.mq.edu.au (8.9.1/8.9.1) with ESMTP id OAA14836 for ; Sat, 1 Apr 2000 14:35:04 +1000 Message-Id: <200004010435.OAA14836@amethyst.efs.mq.edu.au> Received: from efs01.efs.mq.edu.au by localhost with POP3 (fetchmail-5.0.0) for robt@localhost (single-drop); Sat, 01 Apr 2000 14:35:05 +1000 (EET) Received: from SpoolDir by EFS01 (Mercury 1.40); 1 Apr 100 14:30:38 GMT+1000 From: Jason Morris To: "RATS Discussion List" Subject: GARCH and sudden changes in variance Date: Fri, 31 Mar 2000 23:19:43 -0500 (EST) Errors-to: Reply-to: "RATS Discussion List" Sender: Maiser@efs01.efs.mq.edu.au X-listname: Mime-Version: 1.0 Content-Type: text/plain Content-Transfer-Encoding: 7bit X-Mailer: mail.com (via Mercury MTS (Bindery) v1.40) Hi, How does one implement dummy variabels in a GARCH(1,1) model? For example, if Yt = Ut + et et|It ~N(0,ht) ht = w +d1D1 + d2D2 + ....+ dnDn+ ae^2t-1 +bht-1 where Yt is stock returns that follow an AR(1) process, et is the normally distributed error term with varinace mean zero, variance ht, and ht is GARCH, where D1,...Dn are dummy variables taking a value of one fromeach point of sudden change of variance onwards and zero elsewhere, how is this implemented? Your help much appreciated. ----------------------------------------------- FREE! The World's Best Email Address @email.com Reserve your name now at http://www.email.com From ???@??? Sat Apr 01 16:58:02 2000 Received: from localhost (localhost [127.0.0.1]) by amethyst.efs.mq.edu.au (8.9.1/8.9.1) with ESMTP id QAA12948 for ; Sat, 1 Apr 2000 16:50:04 +1000 Message-Id: <200004010650.QAA12948@amethyst.efs.mq.edu.au> Received: from efs01.efs.mq.edu.au by localhost with POP3 (fetchmail-5.0.0) for robt@localhost (single-drop); Sat, 01 Apr 2000 16:50:04 +1000 (EET) Received: from SpoolDir by EFS01 (Mercury 1.40); 1 Apr 100 16:47:37 GMT+1000 From: Rob Trevor To: "RATS Discussion List" Subject: Re: archives Date: Sat, 1 Apr 2000 16:41:40 +1000 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" ; format="flowed" X-Mailer: Mercury MTS (Bindery) v1.40 Timing would be right...they changed the server on me around then. I will check up on the archive function. Rob At 3:01 PM -0500 31/3/00, Christopher F. Baum wrote: >Anyone know why the commands to get the archives of this list no longer >work? >I have always sent an email to maiser@efs.mq.edu.au with a message like >'send rats9912.arc' and gotten a response. Now I just get a bounce from >that site saying that this is not a valid email address. Seemed to happen >around New Year's, coincidentally... > >Thanks >Kit >----------------------------------------------------------------- >Kit Baum baum@bc.edu http://fmwww.bc.edu/ec-v/baum.fac.html From ???@??? Sat Apr 01 16:58:02 2000 Received: from localhost (localhost [127.0.0.1]) by amethyst.efs.mq.edu.au (8.9.1/8.9.1) with ESMTP id QAA12952 for ; Sat, 1 Apr 2000 16:50:05 +1000 Message-Id: <200004010650.QAA12952@amethyst.efs.mq.edu.au> Received: from efs01.efs.mq.edu.au by localhost with POP3 (fetchmail-5.0.0) for robt@localhost (single-drop); Sat, 01 Apr 2000 16:50:05 +1000 (EET) Received: from SpoolDir by EFS01 (Mercury 1.40); 1 Apr 100 16:47:38 GMT+1000 From: Rob Trevor To: "RATS Discussion List" Subject: RE: Date: Sat, 1 Apr 2000 16:44:20 +1000 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" ; format="flowed" X-Mailer: Mercury MTS (Bindery) v1.40 At 4:31 PM -0600 31/3/00, Xi Li wrote: >... >Thank you for your help. So you mean the se of abs(a) should be the se of >estimated a, and se of sqrt(a)*sqrt(a) is the squre of se of estimated a? >... ^^^^^^ I certainly hope not! Rob >-----Original Message----- >From: Rob Trevor [mailto:robt@mafc.mq.edu.au] >Sent: Wednesday, March 29, 2000 7:13 PM >To: RATS Discussion List >Subject: Re: > > >There was a discussion you will find in the archives re different >ways of forcing a parameter to be non-negative. From memory: > > abs(a) or sqrt(a)*sqrt(a) or sqrt(a*a) > >will work and give correct asymptotic se's - some a bit better than >others. (I've never had trouble with sqrt(a)*sqrt(a).) > > From memory the more recent garch procedure on the Estima web site >incorporates non-negativity constraints. (The one written by Normin >Morin.) If it doesn't, it should be easy to add. (If you want to >ensure that the parameters sum to less than 1, just define one of the >parameters as the residual and force that to be non-negative.) > >Cheers > >Rob > > >At 2:48 PM -0600 26/3/00, Xi Li wrote: >>Dear Rob, >> >>Sorry to send you the second message. I found that you have written >>multivariate GARCH procedure in Estima's procedure page. I wonder if your >>version of procedure include the positivity constraints on coefficients in >>variance processes? >> >>Thanks a lot and hope you have a nice day. >> >>Best regards, >> >>Xi From ???@??? Sat Apr 01 16:58:04 2000 Received: from localhost (localhost [127.0.0.1]) by amethyst.efs.mq.edu.au (8.9.1/8.9.1) with ESMTP id QAA12960 for ; Sat, 1 Apr 2000 16:50:05 +1000 Message-Id: <200004010650.QAA12960@amethyst.efs.mq.edu.au> Received: from efs01.efs.mq.edu.au by localhost with POP3 (fetchmail-5.0.0) for robt@localhost (single-drop); Sat, 01 Apr 2000 16:50:05 +1000 (EET) Received: from SpoolDir by EFS01 (Mercury 1.40); 1 Apr 100 16:47:49 GMT+1000 From: Rob Trevor To: "RATS Discussion List" Subject: Re: GARCH and sudden changes in variance Date: Sat, 1 Apr 2000 16:47:30 +1000 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" ; format="flowed" X-Mailer: Mercury MTS (Bindery) v1.40 At 11:19 PM -0500 31/3/00, Jason Morris wrote: >... >How does one implement dummy variabels in a GARCH(1,1) model? >... >ht = w +d1D1 + d2D2 + ....+ dnDn+ ae^2t-1 +bht-1 >... >where D1,...Dn are dummy variables taking a value of one fromeach point of >sudden change of variance onwards and zero elsewhere, how is this >implemented? >... Exactly as you've written it PROVIDED you want the impact to be as permanent as all the other shocks. Otherwise you need to take out the lag effect (via bht-1) next period. Rob Trevor From ???@??? Sat Apr 01 19:07:22 2000 Received: from localhost (localhost [127.0.0.1]) by amethyst.efs.mq.edu.au (8.9.1/8.9.1) with ESMTP id TAA11144 for ; Sat, 1 Apr 2000 19:00:05 +1000 Message-Id: <200004010900.TAA11144@amethyst.efs.mq.edu.au> Received: from efs01.efs.mq.edu.au by localhost with POP3 (fetchmail-5.0.0) for robt@localhost (single-drop); Sat, 01 Apr 2000 19:00:05 +1000 (EET) Received: from SpoolDir by EFS01 (Mercury 1.40); 1 Apr 100 18:56:34 GMT+1000 From: "A.Mufit ArBerk" To: "RATS Discussion List" Subject: EGARCHM(1,1) Date: Sat, 01 Apr 2000 09:56:24 BST Errors-to: Reply-to: "RATS Discussion List" Sender: Maiser@efs01.efs.mq.edu.au X-listname: Mime-Version: 1.0 Content-Type: text/plain; format=flowed X-Mailer: Mercury MTS (Bindery) v1.40 Hi, I am trying to write egarch(1,1) but I receive a message as SX27 Illegal Combination of data types for operation. Firstly, what could be this error message and finally, has oneyone already have or written this program? I would be grateful if anyone could tell me how can I reach this sourch code. Many Thanks. ArBerk ______________________________________________________ Get Your Private, Free Email at http://www.hotmail.com From ???@??? Sat Apr 01 21:56:54 2000 Received: from localhost (localhost [127.0.0.1]) by amethyst.efs.mq.edu.au (8.9.1/8.9.1) with ESMTP id VAA12858 for ; Sat, 1 Apr 2000 21:55:04 +1000 Message-Id: <200004011155.VAA12858@amethyst.efs.mq.edu.au> Received: from efs01.efs.mq.edu.au by localhost with POP3 (fetchmail-5.0.0) for robt@localhost (single-drop); Sat, 01 Apr 2000 21:55:04 +1000 (EET) Received: from SpoolDir by EFS01 (Mercury 1.40); 1 Apr 100 21:51:55 GMT+1000 From: Christopher F Baum To: "RATS Discussion List" Subject: Re: EGARCHM(1,1) Date: Sat, 01 Apr 2000 06:52:18 -0500 Errors-to: Reply-to: "RATS Discussion List" Sender: Maiser@efs01.efs.mq.edu.au X-listname: X-Mailer: Mulberry (MacOS) [1.4.5, 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 It is provided as an option in Norman Morin's excellent GARCH procedure at Estima's website. Taking that procedure as a point of departure is the easiest way to get this done right. Kit Baum --On Sat, Apr 1, 2000 9:56 +0000 "A.Mufit ArBerk" wrote: > > Hi, > I am trying to write egarch(1,1) but I receive a message as SX27 Illegal > Combination of data types for operation. > > Firstly, what could be this error message and finally, has oneyone > already have or written this program? > > I would be grateful if anyone could tell me how can I reach this sourch > code. > > Many Thanks. > > ArBerk > ______________________________________________________ > Get Your Private, Free Email at http://www.hotmail.com > From ???@??? Tue Apr 04 08:28:42 2000 Received: from localhost (localhost [127.0.0.1]) by amethyst.efs.mq.edu.au (8.9.1/8.9.1) with ESMTP id EAA14366 for ; Tue, 4 Apr 2000 04:30:08 +1000 Message-Id: <200004031830.EAA14366@amethyst.efs.mq.edu.au> Received: from efs01.efs.mq.edu.au by localhost with POP3 (fetchmail-5.0.0) for robt@localhost (single-drop); Tue, 04 Apr 2000 04:30:08 +1000 (EET) Received: from SpoolDir by EFS01 (Mercury 1.40); 4 Apr 100 04:24:46 GMT+1000 From: JohnVelis@intesasgr.it To: "RATS Discussion List" Subject: Switching Regimes Date: Mon, 3 Apr 2000 20:24:58 +0200 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 Hi all, has anyone on the list ever managed to program a regime switching model with time varying transition probabilities in which the regime switiching probabilities are functions of exogenous varibales. (The model was suggetsied by Diebold, Lee and Winbach,1994 and examples of applications could be found in Weinbach, Fed BOG, 1998; and Engel and Hakkio, 1996). I know, that van Norden has a version of his code available on his homepage, base don his paper with Vigfusson (1998), but it is in GAUSS as are those available from Kim, related to his text book with Nelson. I woudl really like to see if there is a RATS version out there somewhere. Thanks -John Velis From ???@??? Wed Apr 05 08:38:44 2000 Received: from localhost (localhost [127.0.0.1]) by amethyst.efs.mq.edu.au (8.9.1/8.9.1) with ESMTP id XAA14520 for ; Tue, 4 Apr 2000 23:30:04 +1000 Message-Id: <200004041330.XAA14520@amethyst.efs.mq.edu.au> Received: from efs01.efs.mq.edu.au by localhost with POP3 (fetchmail-5.0.0) for robt@localhost (single-drop); Tue, 04 Apr 2000 23:30:04 +1000 (EET) Received: from SpoolDir by EFS01 (Mercury 1.40); 4 Apr 100 23:07:05 GMT+1000 From: Ian W Marsh To: "RATS Discussion List" Subject: RE: Switching Regimes Date: Tue, 4 Apr 2000 14:05:47 +0100 Errors-to: Reply-to: "RATS Discussion List" Sender: Maiser@efs01.efs.mq.edu.au X-listname: MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="---- =_NextPart_000_01BF9E3E.E1441680" X-Mailer: Mercury MTS (Bindery) v1.40 Dear Mr Velis, I have made an attempt to write a switching model with time-varying transitions probs. I based my RATS code on the Gauss program by Steven Gray who wrote a paper in the Journal of Financial Economics in 1996 (I think). I have attached the program and the necessary data file. It is a while since I looked at it but I think it will work. It is not particularly well annotated so if you cannot follow what I did please get in touch. Good luck! Ian Marsh City University Business School, London From ???@??? Wed Apr 05 08:40:47 2000 Received: from localhost (localhost [127.0.0.1]) by amethyst.efs.mq.edu.au (8.9.1/8.9.1) with ESMTP id BAA15676 for ; Wed, 5 Apr 2000 01:30:04 +1000 Message-Id: <200004041530.BAA15676@amethyst.efs.mq.edu.au> Received: from efs01.efs.mq.edu.au by localhost with POP3 (fetchmail-5.0.0) for robt@localhost (single-drop); Wed, 05 Apr 2000 01:30:04 +1000 (EET) Received: from SpoolDir by EFS01 (Mercury 1.40); 5 Apr 100 01:24:17 GMT+1000 From: Simon.Van-Norden@hec.ca To: "RATS Discussion List" Subject: Re: Switching Regimes Date: Tue, 04 Apr 2000 09:35:11 -0400 Errors-to: Reply-to: "RATS Discussion List" Sender: Maiser@efs01.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; charset=iso-8859-1 Content-Transfer-Encoding: 8bit John: I've never seen RATS code for that. However, the modification for time-varying transition probabilities is not hard. As I recall, this would basically involve modifying the calculation of the filter (and smoother) probabilities in the program available on the Estima web site. SvN JohnVelis@intesasgr.it wrote: > > Hi all, > has anyone on the list ever managed to program a regime switching model > with time varying transition probabilities in which the regime switiching > probabilities are functions of exogenous varibales. (The model was > suggetsied by Diebold, Lee and Winbach,1994 and examples of applications > could be found in Weinbach, Fed BOG, 1998; and Engel and Hakkio, 1996). > > I know, that van Norden has a version of his code available on his > homepage, base don his paper with Vigfusson (1998), but it is in GAUSS as > are those available from Kim, related to his text book with Nelson. I > woudl really like to see if there is a RATS version out there somewhere. > > Thanks > > -John Velis -- Simon van Norden, Prof. agrégé, www.hec.ca/pages/simon.van-norden Service de l'enseignement de la finance, École 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 ???@??? Wed Apr 05 11:17:50 2000 Received: from localhost (localhost [127.0.0.1]) by amethyst.efs.mq.edu.au (8.9.1/8.9.1) with ESMTP id LAA15116 for ; Wed, 5 Apr 2000 11:15:04 +1000 Message-Id: <200004050115.LAA15116@amethyst.efs.mq.edu.au> Received: from efs01.efs.mq.edu.au by localhost with POP3 (fetchmail-5.0.0) for robt@localhost (single-drop); Wed, 05 Apr 2000 11:15:04 +1000 (EET) Received: from SpoolDir by EFS01 (Mercury 1.40); 5 Apr 100 11:12:03 GMT+1000 From: Marc Bremer To: "RATS Discussion List" Subject: Is there a procedure that calculates the Brown, Durbin and Evans Date: Wed, 5 Apr 2000 10:12:24 +0900 Errors-to: Reply-to: "RATS Discussion List" Sender: Maiser@efs01.efs.mq.edu.au X-listname: MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="---- =_NextPart_000_01BF9EE7.70D05A40" X-Mailer: Mercury MTS (Bindery) v1.40 Is there a RATS procedure or instruction that calculates the Brown, Durbin, Evans [Journal of the Royal Statistical Society, 1975] cumulative sum of squared residuals statistic (CUMSUMSQ)? Thanks! Marc Bremer Nanzan University bremerm@ic.nanzan-u.ac.jp From ???@??? Wed Apr 05 18:16:44 2000 Received: from localhost (localhost [127.0.0.1]) by amethyst.efs.mq.edu.au (8.9.1/8.9.1) with ESMTP id SAA14330 for ; Wed, 5 Apr 2000 18:10:04 +1000 Message-Id: <200004050810.SAA14330@amethyst.efs.mq.edu.au> Received: from efs01.efs.mq.edu.au by localhost with POP3 (fetchmail-5.0.0) for robt@localhost (single-drop); Wed, 05 Apr 2000 18:10:04 +1000 (EET) Received: from SpoolDir by EFS01 (Mercury 1.40); 5 Apr 100 18:06:24 GMT+1000 From: Owe Jessen To: "RATS Discussion List" Subject: RE: Switching Regimes Date: Wed, 5 Apr 2000 10:04:21 +0200 Errors-to: Reply-to: "RATS Discussion List" Sender: Maiser@efs01.efs.mq.edu.au X-listname: X-mailer: Pegasus Mail for Win32 (v3.12b) (via Mercury MTS (Bindery) v1.40) MIME-version: 1.0 Content-type: text/plain; charset="ISO-8859-1" Content-Transfer-Encoding: 8bit On 4 Apr 00, at 14:05, Ian W Marsh wrote: Dear Sir, it may not be obvious to someone working at a university, but there are still people out there, who might consider an 447kbyte attachement a bit too large. Owe Jessen -- -------------------------------------------------- Owe Jessen Olshausenstr. 64a 24118 Kiel Persönliche Homepage http://matrix.crosswinds.net/~owejessen/ Homepage des Institut für Wirtschaftspolitik: http://www.bwl.uni-kiel.de/Ordnung+Wettbewerbspolitik/index.html From ???@??? Wed Apr 05 19:16:34 2000 Received: from localhost (localhost [127.0.0.1]) by amethyst.efs.mq.edu.au (8.9.1/8.9.1) with ESMTP id TAA18334 for ; Wed, 5 Apr 2000 19:15:04 +1000 Message-Id: <200004050915.TAA18334@amethyst.efs.mq.edu.au> Received: from efs01.efs.mq.edu.au by localhost with POP3 (fetchmail-5.0.0) for robt@localhost (single-drop); Wed, 05 Apr 2000 19:15:04 +1000 (EET) Received: from SpoolDir by EFS01 (Mercury 1.40); 5 Apr 100 19:10:43 GMT+1000 From: Ian W Marsh To: "RATS Discussion List" Subject: RE: Switching Regimes Date: Wed, 5 Apr 2000 10:10:44 +0100 Errors-to: Reply-to: "RATS Discussion List" Sender: Maiser@efs01.efs.mq.edu.au X-listname: MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="---- =_NextPart_000_01BF9EE7.3506DF20" X-Mailer: Mercury MTS (Bindery) v1.40 Hello everyone, Yes, apologies to all for sending a large attachment. In the midst of a bad day at the office I mistakenly replied to the whole list rather than the one applicant. Still, as several others have asked for the code at least some people are happy. Ian From ???@??? Wed Apr 05 21:46:40 2000 Received: from localhost (localhost [127.0.0.1]) by amethyst.efs.mq.edu.au (8.9.1/8.9.1) with ESMTP id VAA15654 for ; Wed, 5 Apr 2000 21:45:04 +1000 Message-Id: <200004051145.VAA15654@amethyst.efs.mq.edu.au> Received: from efs01.efs.mq.edu.au by localhost with POP3 (fetchmail-5.0.0) for robt@localhost (single-drop); Wed, 05 Apr 2000 21:45:05 +1000 (EET) Received: from SpoolDir by EFS01 (Mercury 1.40); 5 Apr 100 21:44:06 GMT+1000 From: JohnVelis@intesasgr.it To: "RATS Discussion List" Subject: Oggetto: RE: Switching Regimes Date: Wed, 5 Apr 2000 13:44:04 +0200 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 Greetings. Thanks very much for the note and the code, as well as your offer to be of assistance. I hope to get around to looking at it this week; I'll let you know if I have any comments or quetsions. Best, -jov From ???@??? Wed Apr 05 21:52:36 2000 Received: from localhost (localhost [127.0.0.1]) by amethyst.efs.mq.edu.au (8.9.1/8.9.1) with ESMTP id VAA14646 for ; Wed, 5 Apr 2000 21:50:04 +1000 Message-Id: <200004051150.VAA14646@amethyst.efs.mq.edu.au> Received: from efs01.efs.mq.edu.au by localhost with POP3 (fetchmail-5.0.0) for robt@localhost (single-drop); Wed, 05 Apr 2000 21:50:04 +1000 (EET) Received: from SpoolDir by EFS01 (Mercury 1.40); 5 Apr 100 21:47:07 GMT+1000 From: JohnVelis@intesasgr.it To: "RATS Discussion List" Subject: Oggetto: Re: Switching Regimes Date: Wed, 5 Apr 2000 13:47:15 +0200 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=iso-8859-1 Content-Transfer-Encoding: 8bit X-Mailer: Mercury MTS (Bindery) v1.40 Hi Simon, thanks a lot for the tip. I knew that you had done a lot of switching work while you were at BOC, but I couldn't find you there recently when I went to the home page. Until I re-joined the RATS discussion list, I didn't know where you had ended up. I have downlòoaded your stuff from HEC, as well. If you don't mind, once I have a chance to sit downand look at various codes and decide whcih one(s) is most easily modified for my purposes (and abilities -- GAUSS is not my bag!) I might get in touch with you. I hopet that's o.k. Thanks again, Best, -jov From ???@??? Wed Apr 05 21:52:37 2000 Received: from localhost (localhost [127.0.0.1]) by amethyst.efs.mq.edu.au (8.9.1/8.9.1) with ESMTP id VAA20028 for ; Wed, 5 Apr 2000 21:50:05 +1000 Message-Id: <200004051150.VAA20028@amethyst.efs.mq.edu.au> Received: from efs01.efs.mq.edu.au by localhost with POP3 (fetchmail-5.0.0) for robt@localhost (single-drop); Wed, 05 Apr 2000 21:50:05 +1000 (EET) Received: from SpoolDir by EFS01 (Mercury 1.40); 5 Apr 100 21:47:55 GMT+1000 From: JohnVelis@intesasgr.it To: "RATS Discussion List" Subject: Oggetto: RE: Switching Regimes Date: Wed, 5 Apr 2000 13:48:12 +0200 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 Ohy by the way, where did you find Gray's original code? I tried to get it off his site at Duke, but there was nothing there. Thanks again! best wishes, -jov From ???@??? Wed Apr 05 22:14:29 2000 Received: from localhost (localhost [127.0.0.1]) by amethyst.efs.mq.edu.au (8.9.1/8.9.1) with ESMTP id WAA16806 for ; Wed, 5 Apr 2000 22:10:04 +1000 Message-Id: <200004051210.WAA16806@amethyst.efs.mq.edu.au> Received: from efs01.efs.mq.edu.au by localhost with POP3 (fetchmail-5.0.0) for robt@localhost (single-drop); Wed, 05 Apr 2000 22:10:04 +1000 (EET) Received: from SpoolDir by EFS01 (Mercury 1.40); 5 Apr 100 22:05:18 GMT+1000 From: JohnVelis@intesasgr.it To: "RATS Discussion List" Subject: Sorry! Date: Wed, 5 Apr 2000 14:05:16 +0200 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 Friends, sorry that I sent my replies to all of you on the discussion list. I inadvertendly had my email defaults set to 'reply to all'. My appologies. Sincerley, John Velis From ???@??? Thu Apr 06 08:04:53 2000 Received: from localhost (localhost [127.0.0.1]) by amethyst.efs.mq.edu.au (8.9.1/8.9.1) with ESMTP id AAA15758 for ; Thu, 6 Apr 2000 00:00:04 +1000 Message-Id: <200004051400.AAA15758@amethyst.efs.mq.edu.au> Received: from efs01.efs.mq.edu.au by localhost with POP3 (fetchmail-5.0.0) for robt@localhost (single-drop); Thu, 06 Apr 2000 00:00:04 +1000 (EET) Received: from SpoolDir by EFS01 (Mercury 1.40); 5 Apr 100 23:39:06 GMT+1000 From: "John Ireland" To: "RATS Discussion List" Subject: Re: Oggetto: RE: Switching Regimes Date: Wed, 5 Apr 2000 14:42:20 +0100 Errors-to: Reply-to: "RATS Discussion List" Sender: Maiser@efs01.efs.mq.edu.au X-listname: Organization: University of Strathclyde MIME-Version: 1.0 Content-Type: text/plain; Content-Transfer-Encoding: 7bit X-Mailer: Microsoft Outlook Express 5.00.2615.200 (via Mercury MTS (Bindery) v1.40) ----- Original Message ----- From: To: RATS Discussion List Sent: Wednesday, April 05, 2000 12:48 PM Subject: Oggetto: RE: Switching Regimes Ohy by the way, where did you find Gray's original code? I tried to get it off his site at Duke, but there was nothing there. Thanks again! best wishes, -jov From ???@??? Thu Apr 06 08:06:08 2000 Received: from localhost (localhost [127.0.0.1]) by amethyst.efs.mq.edu.au (8.9.1/8.9.1) with ESMTP id HAA08318 for ; Thu, 6 Apr 2000 07:50:04 +1000 Message-Id: <200004052150.HAA08318@amethyst.efs.mq.edu.au> Received: from efs01.efs.mq.edu.au by localhost with POP3 (fetchmail-5.0.0) for robt@localhost (single-drop); Thu, 06 Apr 2000 07:50:04 +1000 (EET) Received: from SpoolDir by EFS01 (Mercury 1.40); 6 Apr 100 01:02:22 GMT+1000 From: Simon.Van-Norden@hec.ca To: "RATS Discussion List" Subject: Re: Is there a procedure that calculates the Brown, Durbin and Ev Date: Wed, 05 Apr 2000 10:30:32 -0400 Errors-to: Reply-to: "RATS Discussion List" Sender: Maiser@efs01.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; charset=iso-8859-1 Content-Transfer-Encoding: 8bit Marc; There's a suite of RATS programs available on my web site. One of these, resdiag, computes the CUSUM and CUSUMSQ statistics, among many others. The program *might* also be available in some of the RATS archives on the net. Regards, SvN Marc Bremer wrote: > > Is there a RATS procedure or instruction that calculates the Brown, > Durbin, Evans [Journal of the Royal Statistical Society, 1975] > cumulative sum of squared residuals statistic (CUMSUMSQ)? > > Thanks! > > Marc Bremer > Nanzan University > bremerm@ic.nanzan-u.ac.jp > > -------------------------------------------------------------------------------- > > Part 1.2 Type: application/ms-tnef > Encoding: base64 -- Simon van Norden, Prof. agrégé, www.hec.ca/pages/simon.van-norden Service de l'enseignement de la finance, École 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 ???@??? Thu Apr 06 08:05:13 2000 Received: from localhost (localhost [127.0.0.1]) by amethyst.efs.mq.edu.au (8.9.1/8.9.1) with ESMTP id AAA19388 for ; Thu, 6 Apr 2000 00:30:04 +1000 Message-Id: <200004051430.AAA19388@amethyst.efs.mq.edu.au> Received: from efs01.efs.mq.edu.au by localhost with POP3 (fetchmail-5.0.0) for robt@localhost (single-drop); Thu, 06 Apr 2000 00:30:04 +1000 (EET) Received: from SpoolDir by EFS01 (Mercury 1.40); 6 Apr 100 00:09:09 GMT+1000 From: "Stephan Kohns" To: "RATS Discussion List" Subject: Normal Completion. Halt at DO Date: Wed, 5 Apr 2000 16:09:27 +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 5.00.2919.6600 (via Mercury MTS (Bindery) v1.40) ------=_NextPart_000_00A9_01BF9F19.51396D20 Content-Type: text/plain; charset="iso-8859-1" Dear RATS users, I have a program that includes a large loop and several smaller loops nested within. The program works smoothly (or seems to do so), but after the final iteration I get the message Normal Completion. Halt at DO The next command after the end of the loop is "write arbstat", where arbstat is a rectangular of reals. When executing this command, I get the following error message: ## SX11. Identifier ARBSTAT is Not Recognizable. Incorrect Option Field or Parameter Order? >>>>write arbstat<<<< The strange thing is that when I copy this command into the loop, I get no error message, and the command is executed properly. Do you have any ideas what is happening here? Thank you very much for your help, Stephan ------extPart_000_00A9_01BF9F19.51396D20 Content-Type: text/html; charsetso-8859-1" Content-Transfer-Encoding: quoted-printable
Dear RATS users,
 I have a program that includes a large loop and several smaller loops nested within. The program works smoothly (or seems to do so), but after the final iteration I get the message
 
Normal Completion. Halt at DO
 The next command after the end of the loop is "write arbstat", where arbstat is a rectangular of reals. When executing this command, I get the following error message:
 
## SX11. Identifier ARBSTAT is Not Recognizable. Incorrect Option Field or Parameter Order?
>>>>write arbstat<<<<
 
The strange thing is that when I copy this command into the loop, I get no error message, and the command is executed properly.
 
 Do you have any ideas what is happening here? Thank you very much for your help,
 
 Stephan
------extPart_000_00A9_01BF9F19.51396D20-- From ???@??? Thu Apr 06 08:06:42 2000 Received: from localhost (localhost [127.0.0.1]) by amethyst.efs.mq.edu.au (8.9.1/8.9.1) with ESMTP id HAA11176 for ; Thu, 6 Apr 2000 07:50:09 +1000 Message-Id: <200004052150.HAA11176@amethyst.efs.mq.edu.au> Received: from efs01.efs.mq.edu.au by localhost with POP3 (fetchmail-5.0.0) for robt@localhost (single-drop); Thu, 06 Apr 2000 07:50:09 +1000 (EET) Received: from SpoolDir by EFS01 (Mercury 1.40); 6 Apr 100 01:23:30 GMT+1000 From: "Estima" To: "RATS Discussion List" Subject: Re: Normal Completion. Halt at DO Date: Wed, 5 Apr 2000 10:22:00 -0500 Errors-to: Reply-to: "RATS Discussion List" Sender: Maiser@efs01.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) Stephan: First, if at all possible, please turn off MIME formatting on your e- mail--makes life easier. Regarding the question: On 5 Apr 00, at 16:09, Stephan Kohns wrote: > This is a multi-part message in MIME format. > > ------=_NextPart_000_00A9_01BF9F19.51396D20 > Content-Type: text/plain; > charset="iso-8859-1" > Content-Transfer-Encoding: quoted-printable > > Dear RATS users, > I have a program that includes a large loop and several smaller loops = > nested within. The program works smoothly (or seems to do so), but after = > the final iteration I get the message > > Normal Completion. Halt at DO > > The next command after the end of the loop is "write arbstat", where = > arbstat is a rectangular of reals. When executing this command, I get = > the following error message: The message "Normal Completion. Halt at DO" indicates that your END instruction is actually ending your program, not just a loop. If you didn't have the word "DO" after your END command, that END would actually shut down RATS. Instead, the DO acts as a "halt command"-- this tells RATS to clear out the memory, but not quit (see the description of END in Chapter 14 for details). As a result, the variable name "ARBSTAT" has been cleared from memory before the WRITE command is executed--that's why you get a "not recognized" error. The most likely explanation is that you've simply got an extra END command. Check to make sure that you only have one END instruction for each loop. Also, check to make sure that you are NOT using END for any IF, UNTIL, or WHILE instructions located inside a loop (again, see descriptions of IF in Chapter 14 for details). 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 Apr 10 23:32:56 2000 Received: from localhost (localhost [127.0.0.1]) by amethyst.efs.mq.edu.au (8.9.1/8.9.1) with ESMTP id XAA18260 for ; Mon, 10 Apr 2000 23:30:04 +1000 Message-Id: <200004101330.XAA18260@amethyst.efs.mq.edu.au> Received: from efs01.efs.mq.edu.au by localhost with POP3 (fetchmail-5.0.0) for robt@localhost (single-drop); Mon, 10 Apr 2000 23:30:04 +1000 (EET) Received: from SpoolDir by EFS01 (Mercury 1.40); 10 Apr 100 23:03:32 GMT+1000 From: Jason Morris To: "RATS Discussion List" Subject: Simple Algorithm Date: Mon, 10 Apr 2000 09:03:53 -0400 (EDT) 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 Content-Transfer-Encoding: 7bit X-Mailer: mail.com (via Mercury MTS (Bindery) v1.40) Hi! How do you get the individual values of a series and how do you sum it? I am trying to code the ICSS algorithm by Inclan and Tiao 1999, JFQA) Ck = Sum(ressq) from t=1 to k, where k=1,2,3,..., T with T being the number of observations, ressq being the residuals squared ie C1 = ressq1 C2 = ressq1+ressq2 C3 = ressq1+ressq2+ressq3 ........... Ck = ressq1+ressq2+ressq3+.....+ressqk OR C1 = ressq1 C2 = C1+ressq2 C3 = C2+ressq3..... How do I do this in RATS? Further I wish to calculate the Dk statistic, which depends on each Ck, example Dk = Ck/Ct - k/T where Ct is the avg of the ressq series ie D1 = C1/Ct - 1/T D2 = C2/Ct - 2/T D3 = C3/Ct - 3/T How do I do all this in Rats? the manual did not help. How do I form a loop to do this? I just can't figure out how to get the individual Ck's so that I can form a loop. Could you please help? ----------------------------------------------- FREE! The World's Best Email Address @email.com Reserve your name now at http://www.email.com From ???@??? Tue Apr 11 01:37:46 2000 Received: from localhost (localhost [127.0.0.1]) by amethyst.efs.mq.edu.au (8.9.1/8.9.1) with ESMTP id BAA19190 for ; Tue, 11 Apr 2000 01:30:04 +1000 Message-Id: <200004101530.BAA19190@amethyst.efs.mq.edu.au> Received: from efs01.efs.mq.edu.au by localhost with POP3 (fetchmail-5.0.0) for robt@localhost (single-drop); Tue, 11 Apr 2000 01:30:04 +1000 (EET) Received: from SpoolDir by EFS01 (Mercury 1.40); 11 Apr 100 01:12:58 GMT+1000 From: "Konstantinos Tsatsaronis" To: "RATS Discussion List" Subject: Re: Simple Algorithm Date: Mon, 10 Apr 2000 17:11:42 +0200 Errors-to: Reply-to: "RATS Discussion List" Sender: Maiser@efs01.efs.mq.edu.au X-listname: X-Mailer: Novell GroupWise 5.5.3 (via Mercury MTS (Bindery) v1.40) Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 8bit There is a command called ACCUMULATE which will do exactly what you want provided that you have created a series RESSQ (set RESSQ = **2) For the loop, if your accumulated squared residuals series is called C, then you do: SET DK = %na STAT(noprint) ressq DO time = 1,%nobs COMPUTE DK(time) = (C(time)/%mean)- time/%nobs END DO time Good luck, Kostas Tsatsaronis Monetary and Economic Department Bank for International Settlements Centralbahnplatz 2 CH-4002, Basel , Switzerland tel: +41 61 280 8082 fax: +41 61 280 9100 >>> jasonwm@email.com 04/10/00 03:03pm >>> Hi! How do you get the individual values of a series and how do you sum it? I am trying to code the ICSS algorithm by Inclan and Tiao 1999, JFQA) Ck = Sum(ressq) from t=1 to k, where k=1,2,3,..., T with T being the number of observations, ressq being the residuals squared How do I do this in RATS? Further I wish to calculate the Dk statistic, which depends on each Ck, example Dk = Ck/Ct - k/T where Ct is the avg of the ressq series ie D1 = C1/Ct - 1/T D2 = C2/Ct - 2/T D3 = C3/Ct - 3/T How do I do all this in Rats? the manual did not help. How do I form a loop to do this? I just can't figure out how to get the individual Ck's so that I can form a loop. Could you please help? ----------------------------------------------- FREE! The World's Best Email Address @email.com Reserve your name now at http://www.email.com DISCLAIMER: Any e-mail messages from the Bank for International Settlements are sent in good faith, but shall not be binding nor construed as constituting any obligation on the part of the Bank. CONFIDENTIALITY NOTICE: This e-mail contains confidential information, which is intended only for the use of the recipient(s) named above. If you have received this communication in error, please notify the sender immediately via e-mail and return the entire message. Thank you for your assistance. From ???@??? Tue Apr 11 03:32:23 2000 Received: from localhost (localhost [127.0.0.1]) by amethyst.efs.mq.edu.au (8.9.1/8.9.1) with ESMTP id DAA18300 for ; Tue, 11 Apr 2000 03:30:05 +1000 Message-Id: <200004101730.DAA18300@amethyst.efs.mq.edu.au> Received: from efs01.efs.mq.edu.au by localhost with POP3 (fetchmail-5.0.0) for robt@localhost (single-drop); Tue, 11 Apr 2000 03:30:05 +1000 (EET) Received: from SpoolDir by EFS01 (Mercury 1.40); 11 Apr 100 03:22:41 GMT+1000 From: Jason Morris To: "RATS Discussion List" Subject: BOXjenk conditional forecasts Date: Mon, 10 Apr 2000 13:21:39 -0400 (EDT) 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 Content-Transfer-Encoding: 7bit X-Mailer: mail.com (via Mercury MTS (Bindery) v1.40) Hi!, i'm trying to find the conditional forecast of a series using the BOXJENK methodology. For example, I need to generate 408 conditional forecasts for series ep using BOXJENK. I tried modelling this using the code below, but it doesn't work, what do I do? I have 408 entries in my series and need to generate 408 conditional forecasts. DO I = 1,448 ** BOXJENK(noprint,AR=1) ep 1 39=39+i FORECAST 1 1 39+i COMPUTE ep(39+i)=fore1 END DOFOR I What Do I do?? ----------------------------------------------- FREE! The World's Best Email Address @email.com Reserve your name now at http://www.email.com From ???@??? Sun Apr 16 01:40:48 2000 Received: from localhost (localhost [127.0.0.1]) by amethyst.efs.mq.edu.au (8.9.1/8.9.1) with ESMTP id BAA11608 for ; Sun, 16 Apr 2000 01:30:04 +1000 Message-Id: <200004151530.BAA11608@amethyst.efs.mq.edu.au> Received: from efs01.efs.mq.edu.au by localhost with POP3 (fetchmail-5.0.0) for robt@localhost (single-drop); Sun, 16 Apr 2000 01:30:04 +1000 (EET) Received: from SpoolDir by EFS01 (Mercury 1.40); 16 Apr 100 01:21:12 GMT+1000 From: Jason Morris To: "RATS Discussion List" Subject: ICSS Algorithm Date: Sat, 15 Apr 2000 11:21:30 -0400 (EDT) Errors-to: Reply-to: "RATS Discussion List" Sender: Maiser@efs01.efs.mq.edu.au X-listname: Mime-Version: 1.0 Content-Type: text/plain Content-Transfer-Encoding: 7bit X-Mailer: mail.com (via Mercury MTS (Bindery) v1.40) Hi! This is part of the code for the ICSS algorithm used by Aggarwal, Inclan and Leal(JFQA, 1999), to detect sudden changes in variance. It was first introduced by Inclan and Tiao in 1994. Does anyone know what the Ct stands for? Dk = Ck/Ct - k/T Ck is just the sum of the residuals squared from 1 to T, where T is the %NOBS, and k=1,2,...,T At first I thought it was the average of the Ck sereis but it isn't. Your help will be much apreciated. It would be even better isf anyone knows their e-mail and could send it to me so I could contact them. Thanks much. ----------------------------------------------- FREE! The World's Best Email Address @email.com Reserve your name now at http://www.email.com From ???@??? Thu Apr 20 08:04:58 2000 Received: from localhost (localhost [127.0.0.1]) by amethyst.efs.mq.edu.au (8.9.1/8.9.1) with ESMTP id IAA10858 for ; Thu, 20 Apr 2000 08:00:04 +1000 Message-Id: <200004192200.IAA10858@amethyst.efs.mq.edu.au> Received: from efs01.efs.mq.edu.au by localhost with POP3 (fetchmail-5.0.0) for robt@localhost (single-drop); Thu, 20 Apr 2000 08:00:04 +1000 (EET) Received: from SpoolDir by EFS01 (Mercury 1.40); 20 Apr 100 07:58:22 GMT+1000 From: Hazem Daouk To: "RATS Discussion List" Subject: Panel and autocorrelation Date: Wed, 19 Apr 2000 16:58:43 -0500 (EST) 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, I am estimating a panel regression with fixed effects. I am correcting for cohort specific heteroskedasticity by using the SPREAD option: panel cr / pcr 1 entry 1.0 indiv -1.0 panel it / pit 1 entry 1.0 indiv -1.0 linreg(smpl=sm5,noprint) cr / u1 # it panel(spread=panels1) u1 linreg(smpl=sm5,spread=panels1,dfc=136) pcr # pit I would like to correct for cohort specific autocorrelation (in addition to cohort heteroskedasticity). How can I modify my program to do that? Any help/advice would be appreciated. Hazem Daouk Finance Department Kelley School of Business Indiana University Bloomington, IN 47405 U.S.A. Voice: (1)(812)857-6662 Fax: (1)(812)855-5875 EMail: hdaouk@indiana.edu From ???@??? Fri Apr 21 00:31:33 2000 Received: from localhost (localhost [127.0.0.1]) by amethyst.efs.mq.edu.au (8.9.1/8.9.1) with ESMTP id AAA20186 for ; Fri, 21 Apr 2000 00:30:04 +1000 Message-Id: <200004201430.AAA20186@amethyst.efs.mq.edu.au> Received: from efs01.efs.mq.edu.au by localhost with POP3 (fetchmail-5.0.0) for robt@localhost (single-drop); Fri, 21 Apr 2000 00:30:04 +1000 (EET) Received: from SpoolDir by EFS01 (Mercury 1.40); 21 Apr 100 00:11:56 GMT+1000 From: "Bob Shain" To: "RATS Discussion List" Subject: RE: Panel and autocorrelation Date: Thu, 20 Apr 2000 10:12:22 -0400 Errors-to: Reply-to: "RATS Discussion List" Sender: Maiser@efs01.efs.mq.edu.au X-listname: MIME-Version: 1.0 Content-Type: text/plain; Content-Transfer-Encoding: 7bit X-Mailer: Microsoft Outlook 8.5, Build 4.71.2173.0 (via Mercury MTS (Bindery) v1.40) Have you talked to Peter Pedroni at your school? -----Original Message----- From: Maiser@EFS01.efs.mq.edu.au [mailto:Maiser@EFS01.efs.mq.edu.au]On Behalf Of Hazem Daouk Sent: Wednesday, April 19, 2000 5:59 PM To: RATS Discussion List Subject: Panel and autocorrelation Dear RATS users, I am estimating a panel regression with fixed effects. I am correcting for cohort specific heteroskedasticity by using the SPREAD option: panel cr / pcr 1 entry 1.0 indiv -1.0 panel it / pit 1 entry 1.0 indiv -1.0 linreg(smpl=sm5,noprint) cr / u1 # it panel(spread=panels1) u1 linreg(smpl=sm5,spread=panels1,dfc=136) pcr # pit I would like to correct for cohort specific autocorrelation (in addition to cohort heteroskedasticity). How can I modify my program to do that? Any help/advice would be appreciated. Hazem Daouk Finance Department Kelley School of Business Indiana University Bloomington, IN 47405 U.S.A. Voice: (1)(812)857-6662 Fax: (1)(812)855-5875 EMail: hdaouk@indiana.edu From ???@??? Sun Apr 23 08:23:27 2000 Received: from localhost (localhost [127.0.0.1]) by amethyst.efs.mq.edu.au (8.9.1/8.9.1) with ESMTP id TAA11710 for ; Fri, 21 Apr 2000 19:20:04 +1000 Message-Id: <200004210920.TAA11710@amethyst.efs.mq.edu.au> Received: from efs01.efs.mq.edu.au by localhost with POP3 (fetchmail-5.0.0) for robt@localhost (single-drop); Fri, 21 Apr 2000 19:20:04 +1000 (EET) Received: from SpoolDir by EFS01 (Mercury 1.40); 21 Apr 100 19:15:31 GMT+1000 From: "kshitija donde" To: "RATS Discussion List" Subject: HELP regarding Kalman Filter Date: Fri, 21 Apr 2000 14:45:09 IST Errors-to: Reply-to: "RATS Discussion List" Sender: Maiser@efs01.efs.mq.edu.au X-listname: Mime-Version: 1.0 Content-Type: text/plain; format=flowed X-Mailer: Mercury MTS (Bindery) v1.40 Dear Users, I am trying to estimate Potential output in the Indian context. I have done my estimations using the Kalman Filter- 'Unobservable Components Model'. Y(t) measures the Actual Output. X(t) measures the permanent output. the measurement equation is: Y(t)= X(t) + e(t) the transition equation is: X(t)= r + X(t-1) + u(t) Thus Measured Output is a sum of Permanent Output and Cyclical Output, which can be considered as a measure of the Output gap. According to the transition equation, the Permanent Output follows a random walk with a drift. I have already carried out the estimations using the above model. Now I would like to model e(t)or the 'Output Gap' as an AR1 process. viz. e(t) = ae(t-1) +z(t) But I am unable to incorporate this change in the model. It would be extremely useful if anyone having a program for the same could kindly agree to lend it to me. Regards, Kshitija Donde. ________________________________________________________________________ Get Your Private, Free E-mail from MSN Hotmail at http://www.hotmail.com From ???@??? Mon Apr 24 22:33:44 2000 Received: from localhost (localhost [127.0.0.1]) by amethyst.efs.mq.edu.au (8.9.1/8.9.1) with ESMTP id WAA09362 for ; Mon, 24 Apr 2000 22:30:04 +1000 Message-Id: <200004241230.WAA09362@amethyst.efs.mq.edu.au> Received: from efs01.efs.mq.edu.au by localhost with POP3 (fetchmail-5.0.0) for robt@localhost (single-drop); Mon, 24 Apr 2000 22:30:05 +1000 (EET) Received: from SpoolDir by EFS01 (Mercury 1.40); 24 Apr 100 22:25:49 GMT+1000 From: JohnVelis@intesasgr.it To: "RATS Discussion List" Subject: Oggetto: Re: Switching Regimes Date: Mon, 24 Apr 2000 14:25:41 +0200 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 Simon. Thanks for your note of a few weeks ago regarding the TVTP modification of the RATS Markov program. This weekend, I finally managed to get a look at it. When you say that all I have to so is modify the filter and smoother probabilities, I take that to mean the following lines in the program: rp1=f1*(p21*(1-pstar{1})+(1-p12)*pstar{1}) (and the analog for rp2). My suspicion from looking at the thing very quickly is that I would have to re.write p12 and p21 as something like: (b01+b11*(exogenousvariable{1})/(1+b01+b11*(exogenousvaribale{1}) Does that seem right to you? Also, in your considered opinion, are there any drawbacks to simply maximizing the log-likelihood using the BHHH method in RATS as opposed to more complicated numerical algorithms like the one in Kim and Nelson or the EM algorithm that Hamilton has employed? Many thanks for your help and input. Best, -jov John Velis Chief Economist Intesa Asset Management, SGR Foro Buonaparte 35 20121 Milano ITALIA Tel: 39-02-721-48-525 Fax: 39-02-721-48-500 johnvelis@intesasgr.it From ???@??? Mon Apr 24 23:03:37 2000 Received: from localhost (localhost [127.0.0.1]) by amethyst.efs.mq.edu.au (8.9.1/8.9.1) with ESMTP id WAA08412 for ; Mon, 24 Apr 2000 22:55:04 +1000 Message-Id: <200004241255.WAA08412@amethyst.efs.mq.edu.au> Received: from efs01.efs.mq.edu.au by localhost with POP3 (fetchmail-5.0.0) for robt@localhost (single-drop); Mon, 24 Apr 2000 22:55:04 +1000 (EET) Received: from SpoolDir by EFS01 (Mercury 1.40); 24 Apr 100 22:51:04 GMT+1000 From: "Christopher F. Baum" To: "RATS Discussion List" Subject: archives Date: Mon, 24 Apr 2000 08:50:58 -0400 Errors-to: Reply-to: "RATS Discussion List" Sender: Maiser@efs01.efs.mq.edu.au X-listname: X-Mailer: Mulberry/2.0.0 (MacOS) (via Mercury MTS (Bindery) v1.40) MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit The archiving mechanism for RATS-L seems to have lost entries for January through April 10 (it stopped working when Y2K arrived) as well as some for last December. I have reinstated postings of the monthly items on RATS-L on the web at http://fmwww.bc.edu/ec-p/software/rats/ratsl.html Kit ----------------------------------------------------------------- Kit Baum baum@bc.edu http://fmwww.bc.edu/ec-v/baum.fac.html From ???@??? Tue Apr 25 00:03:27 2000 Received: from localhost (localhost [127.0.0.1]) by amethyst.efs.mq.edu.au (8.9.1/8.9.1) with ESMTP id AAA16208 for ; Tue, 25 Apr 2000 00:00:04 +1000 Message-Id: <200004241400.AAA16208@amethyst.efs.mq.edu.au> Received: from efs01.efs.mq.edu.au by localhost with POP3 (fetchmail-5.0.0) for robt@localhost (single-drop); Tue, 25 Apr 2000 00:00:05 +1000 (EET) Received: from SpoolDir by EFS01 (Mercury 1.40); 24 Apr 100 23:36:06 GMT+1000 From: JohnVelis@intesasgr.it To: "RATS Discussion List" Subject: Oggetto: Oggetto: Re: Switching Regimes Date: Mon, 24 Apr 2000 15:35:46 +0200 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=windows-1257 Content-Transfer-Encoding: 8bit X-Mailer: Mercury MTS (Bindery) v1.40 Dear Fellow RATS-ers: This is the second time in about a month that I had intended to reply to an individual RATS-list user, yet instead unknowingly sent the message to the entire list. I thought I had changed the reply default settings on my email software, but apparently my this earlier attempt was insufficient. I apologize to all of you for the inadvertent ‘spam.’ Then again, if any of you have opinions on what I asked in the note, please feel free to reply. My apologies once again, and thanks. Regards, John Velis