From: Gregory Lypny To: "RATS Discussion List" Subject: Stochastic Dominance Date: Thu, 31 Oct 96 10:10:15 -0500 Errors-to: Reply-to: "RATS Discussion List" Sender: Maiser@efs1.efs.mq.edu.au X-listname: x-mailer: Claris Emailer 1.1 (via Mercury MTS (Bindery) v1.30) Mime-Version: 1.0 Content-Type: text/plain; charset="US-ASCII" Anyone out there got routines to ranks series on the basis of first-, second- and third-degree stochastic dominance? Much obliged, Greg Gregory J. Lypny Associate Professor of Finance Director, Centre for Instructional Technology Mailing address: Contact: ------------------------------------------------------------------- Finance Department 514.848.2926 (voice) Concordia University 514.848.4500 (fax) 1455 De Maisonneuve Boulevard West LYPNY@VAX2.CONCORDIA.CA Montreal, QC H3G 1M8 ---------- End of message ---------- From: Peter Mansfield To: "RATS Discussion List" Subject: Switching Regimes Date: Wed, 13 Nov 1996 11:16:45 +1100 Errors-to: Reply-to: "RATS Discussion List" Sender: Maiser@efs1.efs.mq.edu.au X-listname: X-Mailer: Windows Eudora Pro Version 2.2 (32) (via Mercury MTS (Bindery) v1.30) Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Hello Colleagues, Estima's homepage includes access to RATS code written by Goerlich that computes one deterministic change in regime. Comments in the code say that it uses the procedure suggested by Goldfeld and Quandt in 1976. I am looking for RATS code that computes more than one switch. In addition, the code should also allow the switch to be gradual rather than necessarily at one point. Any pieces of code, suggestions or comments would be more than welcome! Thanks in advance for any assistance you might be able to provide. Peter Mansfield Peter J Mansfield EMail: peter.mansfield@accfin.utas.edu.au Dept of Accounting and Finance University of Tasmania _--_|\ GPO Box 252-86 / \ Phone: (03) 6226 7591 Hobart, Tasmania 7001 \_.--._/ Australia v Fax: (03) 6226 7845 ---------- End of message ---------- From: David Aadland To: "RATS Discussion List" Subject: Asymptotic Confidence Bounds Date: Thu, 21 Nov 1996 19:24:59 -0800 Errors-to: Reply-to: "RATS Discussion List" Sender: Maiser@efs1.efs.mq.edu.au X-listname: X-Mailer: Windows Eudora Light Version 1.5.2 (via Mercury MTS (Bindery) v1.30) Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" RATS users, Does anyone out there have experience using the SVAR and VMA procedures to calculate asymptotic confidence bounds around structural IRFs. In particular, I'm interested in obtaining confidence bounds around transitory and permanent responses to output obtained from Blanchard and Quah's long-restriction that demand shocks don't impact the long-run level of output. In this case, the VMA procedure provides the asymptotic confidence intervals for the change in output, but what I need is the asymptotic confidence intervals for output itself (i.e., the sum of the changes). If anyone knows of an available code for doing this, I'd appreciate the reference. David Aadland University of Oregon ---------- End of message ---------- From: Shuh Liang To: "RATS Discussion List" Subject: Imposing restrictions in the structural VAR estimation Date: Sat, 23 Nov 1996 03:39:17 -0800 Errors-to: Reply-to: "RATS Discussion List" Sender: Maiser@efs1.efs.mq.edu.au X-listname: MIME-version: 1.0 X-Mailer: Microsoft Internet Mail 4.70.1155 (via Mercury MTS (Bindery) v1.30) Content-type: text/plain; charset=ISO-8859-1 Content-transfer-encoding: 7bit Dear RATS users: Does anyone know how to impose a restriction of free parameters in a structural VAR estimation? Usinging the procedure BERNANKE.SRC, how to restrict free parameters, e.g., A(2,1) = - A (3,2), in the A matrix. Thanks. Shuh Liang ---------- End of message ---------- From: "F.Y.Kumah" To: "RATS Discussion List" Subject: Re: Imposing restrictions in the structural VAR estimation Date: Mon, 25 Nov 1996 09:43:53 MET Errors-to: Reply-to: "RATS Discussion List" Sender: Maiser@efs1.efs.mq.edu.au X-listname: Organization: Tilburg University X-mailer: Pegasus Mail for Windows (v2.23) (via Mercury MTS (Bindery) v1.30) Dear Shuh, I think you could impose that restriction by using FIND. Search for the usage of FIND in the RATS manual. All the best Francis On 23 Nov 96 at 3:39, Shuh Liang Shuh Liang wrote: > From: Shuh Liang > To: "RATS Discussion List" > Subject: Imposing restrictions in the structural VAR estimation > Date: Sat, 23 Nov 1996 03:39:17 -0800 > Reply-to: "RATS Discussion List" > Dear RATS users: > > Does anyone know how to impose a restriction of free parameters in a > structural VAR > estimation? > Usinging the procedure BERNANKE.SRC, how to restrict free parameters, e.g., > A(2,1) = - A (3,2), in the A matrix. > > > Thanks. > > Shuh Liang > **~~**~~**~~**~~**~~**~~**~~**~~**~~****~~**~~**~~**~~** Francis Y. Kumah CentER for Economic Research P. O. Box 90153 5000 LE Tilburg The Netherlands Phone (+31) 13 - 4668 221 Fax (+31) 13 - 4663 066 My Home Page: http://cwis.kub.nl/~few5/center/phd_stud/kumah/home.HTM **~~**~~**~~**~~**~~**~~**~~**~~**~~****~~**~~**~~**~~** ---------- End of message ---------- From: figura@econ.umd.edu To: "RATS Discussion List" Subject: RUNNING A MONTE CARLO ON A NEAR VAR Date: Mon, 25 Nov 1996 15:55:28 -0500 Errors-to: Reply-to: "RATS Discussion List" Sender: Maiser@efs1.efs.mq.edu.au X-listname: Organization: University of Maryland Mime-Version: 1.0 Content-Type: text/plain; charset="US-ASCII" Content-Transfer-Encoding: 7BIT X-Mailer: Connect2-SMTP 4.10.rc3D MHS to SMTP Gateway (via Mercury MTS (Bindery) v1.30) I would like to run a monte carlo on a near VAR system. If anyone has attempted such a program, I would appreciate any advice they might have. ---------- End of message ---------- From: Peter Summers To: "RATS Discussion List" Subject: Sing. values & Gen'l inverses Date: Wed, 27 Nov 1996 17:32:06 +1100 Errors-to: Reply-to: "RATS Discussion List" Sender: Maiser@efs1.efs.mq.edu.au X-listname: X-Mailer: Windows Eudora Pro Version 2.2 (32) (via Mercury MTS (Bindery) v1.30) Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Fellow RATS-ophiles, Does anyone have a reliable algorithm for computing the singular value decomposition and/or generalized inverse of a general matrix? I have tried 2 approaches, both of which "almost" work: 1) Translating the algorithm in Press et al's "Numerical Recipes" (pp. 60-64 in the 1986 ed.) from FORTRAN. Given a general matrix A, this returns U, W, and V such that A = U*%diag(W)*tr(V). Problem 1: U and V are supposed to be orthonormal, but aren't. Problem 2: U*%diag(W)*tr(V) often is not very "close" to A (i.e., sometimes not even the first decimal place is accurate). 2) Following the proof of Proposition 67 (p. 79) in P. J. Dhrymes's "Mathematics for Econometrics." This gives the same decomposition of A, based on the (non-zero) eigenvalues and eigenvectors of A'A and AA'. The resulting U and V come out orthonormal, but Problem 2 is even more serious here (i.e., often not even the signs are correct). Could this have anything to do with the precision with which RATS finds eigenvalues/vectors (and if so, should we be worried about that fact)? What I'm really after here is the Moore-Penrose generalized inverse, so I'd gladly give up trying to solve Problems 1&2 if someone's got such a routine. Any and all comments welcome. **************************************************************************** Peter Summers Research Fellow Melbourne Institute of Applied Economic and Social Research University of Melbourne Parkville, VIC 3052 AUSTRALIA ph: (03) 9344-5313 fax: (03) 9344-5630 email: p.summers@iaesr.unimelb.edu.au **************************************************************************** ---------- End of message ----------