Return-Path: Received: from zaphod.bc.edu (zaphod.bc.edu [136.167.2.207]) by monet.bc.edu (8.8.7/8.8.7) with ESMTP id PAA315048 for ; Fri, 3 Dec 1999 15:51:03 -0500 From: maiser@efs.mq.edu.au Received: (from root@localhost) by zaphod.bc.edu (8.8.7/8.8.7) with X.500 id PAA29332 for baum@mail1.bc.edu; Fri, 3 Dec 1999 15:51:03 -0500 Received: from sunb.ocs.mq.edu.au (sunb.ocs.mq.edu.au [137.111.1.11]) by zaphod.bc.edu (8.8.7/8.8.7) with ESMTP id PAA48458 for ; Fri, 3 Dec 1999 15:50:46 -0500 Received: from efs1.efs.mq.edu.au (efs1.efs.mq.edu.au [137.111.64.8]) by sunb.ocs.mq.edu.au (8.9.2/8.9.2) with ESMTP id HAA17613 for ; Sat, 4 Dec 1999 07:50:35 +1100 (EST) Received: from EFS1/SpoolDir by efs1.efs.mq.edu.au (Mercury 1.40); 4 Dec 99 07:49:30 GMT+1000 Received: from SpoolDir by EFS1 (Mercury 1.40); 4 Dec 99 07:49:29 GMT+1000 To: baum@bc.edu Date: Sat, 4 Dec 99 7:49:28 GMT+1000 Subject: Re: Message-ID: From: Hazem Daouk To: "RATS Discussion List" Subject: Non-linear optimization Date: Fri, 5 Nov 1999 14:17:29 -0500 (EST) 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, I am estimating a (complicated) non-linear model using NLLS. For one of the coefficients, Rats gives me zeros for the standard error, t-stat, and signif. Why is that? and what can I do to get significance level? In my model, this coefficient was put with an exponential function to be restricted to be positive. Could this be the problem? Especially that the "unrestricted" coefficient would have come out negative if I did not put the exp(.) function. Below I include a portion of the code and the output it produces (a3 is the coefficient with the problem). I'd appreciate any help.. 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 CODE: NLPAR(SUBITS=400) nonlin a0 a2 a3 a4 frml harvey = a0+(exp(a2*trade)/(1+exp(a2*trade)))*tvcov*EXP(a3)+ (1-(exp(a2*trade)/(1+exp(a2*trade))))*var*exp(a4) com a2=0.1;com a3=1;com a4=0.1;com a0=0.1 nlls(frml=harvey,smpl=sm5,iterations=400,trace) exret / residd OUTPUT: Normal Completion. Halt at 0 Non-Linear Optimization, Iteration 1. Subiterations 1 Old Function = 5.252497e+001 New Function = 2.909955e+001 New Coefficients: 0.006177 1.199929 0.069795 -0.622495 Non-Linear Optimization, Iteration 2. Subiterations 1 Old Function = 2.909955e+001 New Function = 2.900665e+001 New Coefficients: 0.006528 5.491344 -1.359536 -0.582580 Non-Linear Optimization, Iteration 3. Subiterations 2 Old Function = 2.900665e+001 New Function = 2.898794e+001 New Coefficients: 0.006467 10.709016 -4.880339 0.359211 Non-Linear Optimization, Iteration 4. Subiterations 2 Old Function = 2.898794e+001 New Function = 2.898448e+001 New Coefficients: 0.005957 8.472328 -85.702892 0.327469 Non-Linear Optimization, Iteration 5. Subiterations 1 Old Function = 2.898448e+001 New Function = 2.897542e+001 New Coefficients: 0.003933 9.720479 -85.702892 0.440164 Non-Linear Optimization, Iteration 6. Subiterations 3 Old Function = 2.897542e+001 New Function = 2.897522e+001 New Coefficients: 0.003870 9.034350 -85.702892 0.407671 Non-Linear Optimization, Iteration 7. Subiterations 1 Old Function = 2.897522e+001 New Function = 2.897522e+001 New Coefficients: 0.003873 9.151043 -85.702892 0.409557 Non-Linear Optimization, Iteration 8. Subiterations 3 Old Function = 2.897522e+001 New Function = 2.897522e+001 New Coefficients: 0.003867 9.089302 -85.702892 0.406687 Non-Linear Optimization, Iteration 9. Subiterations 3 Old Function = 2.897522e+001 New Function = 2.897522e+001 New Coefficients: 0.003867 9.091584 -85.702892 0.406779 Non-Linear Optimization, Iteration 10. Subiterations 1 Old Function = 2.897522e+001 New Function = 2.897522e+001 New Coefficients: 0.003867 9.091446 -85.702892 0.406758 Non-Linear Optimization, Iteration 11. Subiterations 3 Old Function = 2.897522e+001 New Function = 2.897522e+001 New Coefficients: 0.003867 9.091519 -85.702892 0.406762 Dependent Variable EXRET - Estimation by Nonlinear Least Squares Iterations Taken 11 Panel(354) of Monthly Data From 1//1969:12 To 51//1999:05 Usable Observations 2080 Degrees of Freedom 2076 Total Observations 18054 Skipped/Missing 15974 Centered R**2 0.001564 R Bar **2 0.000122 Uncentered R**2 0.003689 T x R**2 7.672 Mean of Dependent Variable 0.0054539854 Std Error of Dependent Variable 0.1181479316 Standard Error of Estimate 0.1181407447 Sum of Squared Residuals 28.975221030 Durbin-Watson Statistic 1.783496 Variable Coeff Std Error T-Stat Signif ******************************************************************************* 1. A0 0.00386701 0.00282371 1.36948 0.17099795 2. A2 9.09151936 7.31158700 1.24344 0.21384616 3. A3 -85.70289226 0.00000000 0.00000 0.00000000 4. A4 0.40676163 0.65018245 0.62561 0.53163854 ---------- End of message ---------- From: "CHENG MING-YU" To: "RATS Discussion List" Subject: Outlier Date: Sat, 06 Nov 1999 00:33:04 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 Dear all How should I get rid of outliers in my analysis? MYCheng ______________________________________________________ Get Your Private, Free Email at http://www.hotmail.com ---------- End of message ---------- From: "CHENG MING-YU" To: "RATS Discussion List" Subject: Outlier Date: Sat, 06 Nov 1999 00:40:57 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 Dear all How should I get rid of outliers in my analysis? Thanks MYCheng ______________________________________________________ Get Your Private, Free Email at http://www.hotmail.com ---------- End of message ---------- From: "Ravindra A. Yatawara" To: "RATS Discussion List" Subject: var.src Date: Sun, 7 Nov 1999 00:19:54 -0500 (EST) 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 Hi All I am trying to get the residuals of a var so that i can convert them to the demand and supply shocks in a la blanchard quah, but cannot seem to do it. I can get the graph but is there a way i can get the series (numbers). (I estimate a two variable VAR-inflation and output and calculate bootsrapped impulse response functions) any advice much appreciated. ravi ____________________ Ravi A. Yatawara Department of Economics 1012 International Affairs Building Columbia University New York, NY 10027 Tel: 212-666-5445 Fax: 212-854-8059 email: ray1@columbia.edu ---------- End of message ---------- From: kim soyoung To: "RATS Discussion List" Subject: impulse response functions in a cointegrated system Date: Mon, 8 Nov 1999 02:21:45 -0600 (CST) 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 Collegues, I am interested in calculating impulse response functions in a cointegrated system using RATS (not other softwares). I would appreciate very much if someone can provide a program or let me know where i can obtain the program. Thank you. Soyoung Kim ---------- End of message ---------- From: Norman J Morin To: "RATS Discussion List" Subject: Re: var.src Date: Mon, 08 Nov 1999 09:50:43 -0500 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 "Ravindra A. Yatawara" on 11/07/99 12:19:54 AM Please respond to RATS Discussion List To: RATS Discussion List cc: (bcc: Norman J Morin/RS-MA/FRBOG/US) Subject var.src : Hi All I am trying to get the residuals of a var so that i can convert them to the demand and supply shocks in a la blanchard quah, but cannot seem to do it. I can get the graph but is there a way i can get the series (numbers). (I estimate a two variable VAR-inflation and output and calculate bootsrapped impulse response functions) any advice much appreciated. ravi Ravi, You should be able to access a vector of series "residvec" that contains all the reduced-form residuals. So, if you have a two-variable VAR, residvec(1) should be a series containing the residuals from the first variable in the system and residvec(2) should contain those from the second. When you quit the VAR procedure, there should be a bunch of text printed to the screen that lists what information is saved and where it is saved to. Regards, Norm -- Norman J. Morin --------------------------------------------------------- Division of Research and Statistics * Mail Stop 82 Board of Governors of the Federal Reserve System Washington, D.C. 20551 * (202) 452-2476 norman.j.morin@frb.gov * nmorin@frb.gov * m1njm00@frb.gov --------------------------------------------------------- ---------- End of message ---------- From: Norman J Morin To: "RATS Discussion List" Subject: Re: var.src Date: Mon, 08 Nov 1999 09:46:33 -0500 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 "Ravindra A. Yatawara" on 11/07/99 12:19:54 AM Please respond to RATS Discussion List To: RATS Discussion List cc: (bcc: Norman J Morin/RS-MA/FRBOG/US) Subject var.src : Hi All I am trying to get the residuals of a var so that i can convert them to the demand and supply shocks in a la blanchard quah, but cannot seem to do it. I can get the graph but is there a way i can get the series (numbers). (I estimate a two variable VAR-inflation and output and calculate bootsrapped impulse response functions) any advice much appreciated. ravi ____________________ Ravi A. Yatawara Department of Economics 1012 International Affairs Building Columbia University New York, NY 10027 Tel: 212-666-5445 Fax: 212-854-8059 email: ray1@columbia.edu ---------- End of message ---------- From: Dr Yue Ma To: "RATS Discussion List" Subject: Markvo switching model Date: Tue, 9 Nov 1999 05:41:43 +0000 (GMT) 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 Hi I have run the recent Markov switching model from your Newsletter Dec 1998 successfully (http://www.estima.com/procs/markov.prg). I would like to ask you how to change the codes for a 3-state model and how to calculate the transition probabilities (i.e. the probabilities at each state). Many thanks Yue Ma ---------- End of message ---------- From: Dr Yue Ma To: "RATS Discussion List" Subject: Markvo switching model Date: Tue, 9 Nov 1999 06:03:16 +0000 (GMT) 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 Hi I have run the recent Markov switching model from your Newsletter Dec 1998 successfully (http://www.estima.com/procs/markov.prg). I would like to ask you how to change the codes for a 3-state model and how to calculate the transition probabilities (i.e. the probabilities at each state). Many thanks Yue Ma ---------- End of message ---------- From: "Iacoviello,M (pg)" To: "RATS Discussion List" Subject: RE: var.src Date: Tue, 9 Nov 1999 13:36:42 -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 (5.5.2448.0) (via Mercury MTS (Bindery) v1.40) Content-Type: text/plain Ravi: You run your VAR and get everything you need. source(noecho) c:\winrats\var.src @VAR 1921:1 1938:1 B0 #growth inflation Then once you ve done with the VAR type something like this: make varresd # residvec compute shocks=varresd*FACTOR write shocks The "shocks" matrix corresponds to your (2) structural shocks, serially uncorrelated and orthogonal to each other. Each line corresponds to a year, each column to a shock (first is supply, second demand) Regards Matteo P.S. I would appreciate if anyone in the list who's on VARs can confirm that this is not wrong. ---------- End of message ---------- From: Konstantin Kholodilin To: "RATS Discussion List" Subject: Impulse-Responses with non-Choleski decomposition Date: Tue, 9 Nov 1999 16:18:16 -0100 (GMT+1) 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! I am trying to do the Impulse-Response analysis with the Monte Carlo confidence bands, but with eigenvalue-eigenvector decomposition instead of the Choleski one. However, I still did not find the way how to implement this, because I have to change somehow the SWISH matrix which is usually calculated using Choleski decomposition. The straightforward attempts to insert the eigenvector matrix there bring very strange results. I would be very grateful if you could help me. Sincerely yours, Konstantin ---------- End of message ---------- From: "Konstantinos Tsatsaronis" To: "RATS Discussion List" Subject: Re: Impulse-Responses with non-Choleski decomposition Date: Tue, 09 Nov 1999 17:19:04 +0100 Errors-to: Reply-to: "RATS Discussion List" Sender: Maiser@efs1.efs.mq.edu.au X-listname: X-Mailer: Novell GroupWise 5.5 (via Mercury MTS (Bindery) v1.40) Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: quoted-printable Another way would be to take the identified (structural) errors and bootstr= ap your system by redrawing from their values. In this case you are not usi= ng the Wishart distribution but the "observed" one. Kostas Tsatsaronis >>> Konstantin Kholodilin 11/09/99 06:18pm >>> Dear RATS users! I am trying to do the Impulse-Response analysis with the Monte Carlo confidence bands, but with eigenvalue-eigenvector decomposition instead of the Choleski one. However, I still did not find the way how to implement this, because I have to change somehow the SWISH matrix which is usually calculated using Choleski decomposition. The straightforward attempts to insert the eigenvector matrix there bring very strange results. I would be very grateful if you could help me. Sincerely yours, Konstantin DISCLAIMER: Any e-mail messages from the Bank for International Settlements= are sent in good faith, but shall not be binding nor construed as constitu= ting any obligation on the part of the Bank. CONFIDENTIALITY NOTICE: This e-mail contains confidential information, whic= h 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. ---------- End of message ---------- From: Woo Kai Yin To: "RATS Discussion List" Subject: Re: Markvo switching model Date: Wed, 10 Nov 1999 01:27:05 +0800 Errors-to: Reply-to: "RATS Discussion List" Sender: Maiser@efs1.efs.mq.edu.au X-listname: X-Mailer: Mozilla 3.01C-IMS (Win95; I) (via Mercury MTS (Bindery) v1.40) MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Dr Yue Ma wrote: > > Hi > > I have run the recent Markov switching model from your Newsletter Dec > 1998 successfully (http://www.estima.com/procs/markov.prg). > > I would like to ask you how to change the codes for a 3-state model and > how to calculate the transition probabilities (i.e. the probabilities at > each state). > > Many thanks > > Yue Ma Dear Dr.Ma, I have no idea. But I can forward your questions to the RATS mailing list. regards, KY ---------- End of message ---------- From: Woo Kai Yin To: "RATS Discussion List" Subject: RE: markov switching model Date: Wed, 10 Nov 1999 01:29:59 +0800 Errors-to: Reply-to: "RATS Discussion List" Sender: Maiser@efs1.efs.mq.edu.au X-listname: X-Mailer: Mozilla 3.01C-IMS (Win95; I) (via Mercury MTS (Bindery) v1.40) MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Dear RATS users, I have run the recent Markov switching model from your Newsletter Dec 1998 successfully (http://www.estima.com/procs/markov.prg). I would like to ask you how to change the codes for a 3-state model and how to calculate the transition probabilities (i.e. the probabilities at each state). Many thanks Kevin Dept of Economics, Hong Kong Shue Yan college. ---------- End of message ---------- From: Woo Kai Yin To: "RATS Discussion List" Subject: RE:markov switching model Date: Wed, 10 Nov 1999 01:45:09 +0800 Errors-to: Reply-to: "RATS Discussion List" Sender: Maiser@efs1.efs.mq.edu.au X-listname: X-Mailer: Mozilla 3.01C-IMS (Win95; I) (via Mercury MTS (Bindery) v1.40) MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Dear RATS users, I have run the recent Markov switching model from your Newsletter Dec 1998 successfully (http://www.estima.com/procs/markov.prg). I would like to ask you how to change the codes for a 3-state model and how to calculate the transition probabilities (i.e. the probabilities at each state). Many thanks Kai-yin Woo Senior Lecturer, Dept of Economics, HOng KOng Shue Yan College. ---------- End of message ---------- From: "Ant�nio Rua" To: "RATS Discussion List" Subject: Fractional difference Date: Tue, 09 Nov 1999 14:48:42 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 Content-Transfer-Encoding: quoted-printable X-Mailer: Mercury MTS (Bindery) v1.40 Dear RATS users, i have been trying to fractional difference a series, that is, to apply a= =20 non-integer difference (1-L)^d (with d non-integer) to a series. How can = i=20 do this in RATS? Can anyone help me? (I=B4ve talked with other collegues = but=20 their were not able to help me) Best regards, Ant=F3nio Rua (Phd student) ______________________________________________________ Get Your Private, Free Email at http://www.hotmail.com ---------- End of message ---------- From: Woo Kai Yin To: "RATS Discussion List" Subject: RE: Date: Wed, 10 Nov 1999 10:32:51 +0800 Errors-to: Reply-to: "RATS Discussion List" Sender: Maiser@efs1.efs.mq.edu.au X-listname: X-Mailer: Mozilla 3.01C-IMS (Win95; I) (via Mercury MTS (Bindery) v1.40) MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Dear RATS users, Last time, I sent my request for four times but as I sent out, "host unknown" shows up. There might be technical problems in my server. So, I feel regretful for inconvenience caused. regards, KY ---------- End of message ---------- From: Giuseppe De Arcangelis To: "RATS Discussion List" Subject: Problems with RATS386 in a DOS window Date: Fri, 12 Nov 1999 18:36:09 +0100 Errors-to: Reply-to: "RATS Discussion List" Sender: Maiser@efs1.efs.mq.edu.au X-listname: X-Mailer: Mozilla 4.6 [en] (Win98; I) (via Mercury MTS (Bindery) v1.40) MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Sometimes I cannot run rats386 in a dos window (within windows98) and I get the following message: ILLEGAL ADDRESS HAS CAUSED A PAGE FAULT absolute address = error code = 0004 eax = FF01CB70 esi = FF0238DC flags = 0082 ds = 00CF ebx = 0000001B edi = FF023044 eip = 00001415 es = 008F ecx = 000027F9 ebp = FF03AA58 cs = 0097 fs = 00B7 edx = FF0238DC esp = FF03AA24 ss = 00BF gs = 0000 Do you have any clue? Giuseppe De Arcangelis -- ******************************************************************************* Prof. Giuseppe De Arcangelis ph. +39 0805049043 Ass. Prof. of International Economics fax +39 0804049149 University of Bari e-mail: Dip. di Sc. Economiche and CIDEI http://cidei.eco.uniroma1.it/~gdearc/ Via Camillo Rosalba, 53 I-70124 BARI (Italy) ---------- End of message ---------- From: daniela marconi To: "RATS Discussion List" Subject: Re: Problems with RATS386 in a DOS window Date: Sun, 14 Nov 1999 16:23:00 -0800 (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; charset=us-ascii X-Mailer: Mercury MTS (Bindery) v1.40 --- Giuseppe De Arcangelis wrote: > > Sometimes I cannot run rats386 in a dos window > (within windows98) and I > get the following message: > > ILLEGAL ADDRESS HAS CAUSED A PAGE FAULT > absolute address = > error code = 0004 > eax = FF01CB70 esi = FF0238DC flags = 0082 > ds = 00CF > ebx = 0000001B edi = FF023044 eip = > 00001415 es = 008F > ecx = 000027F9 ebp = FF03AA58 cs = 0097 > fs = 00B7 > edx = FF0238DC esp = FF03AA24 ss = 00BF > gs = 0000 > > > Do you have any clue? > > Giuseppe De Arcangelis > > -- > ******************************************************************************* > > Prof. Giuseppe De Arcangelis ph. +39 > 0805049043 > Ass. Prof. of International Economics fax +39 > 0804049149 > University of Bari > e-mail: > Dip. di Sc. Economiche and CIDEI > http://cidei.eco.uniroma1.it/~gdearc/ > Via Camillo Rosalba, 53 > I-70124 BARI (Italy) > It doesn't depend on windows98, often I get the same within windows95 and the only solution I found is to restart the computer and run rats386 again. Daniela Marconi ===== __________________________________________________ Do You Yahoo!? Bid and sell for free at http://auctions.yahoo.com ---------- End of message ---------- From: Peter Summers To: "RATS Discussion List" Subject: Re: Problems with RATS386 in a DOS window Date: Mon, 15 Nov 1999 12:49:09 +1000 Errors-to: Reply-to: "RATS Discussion List" Sender: Maiser@efs1.efs.mq.edu.au X-listname: X-Mailer: QUALCOMM Windows Eudora Pro Version 4.1 (via Mercury MTS (Bindery) v1.40) Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" If my memory serves me correctly, this has happened to me when I do something like sending an undefined or non-existent series name/number to a procedure (I don't recall the exact cause). If you're calling a proc which requires supplementary cards, you might want to check that these are specified correctly. I do seem to recall that the cause is something which would ordinarily give an error message if done without calling any procs or functions. I run on windows NT v.4, so I agree with Daniela that it's not a windows problem. At 16:23 14/11/99 -0800, you wrote: > > >--- Giuseppe De Arcangelis >wrote: >> >> Sometimes I cannot run rats386 in a dos window >> (within windows98) and I >> get the following message: >> >> ILLEGAL ADDRESS HAS CAUSED A PAGE FAULT >> absolute address = >> error code = 0004 >> eax = FF01CB70 esi = FF0238DC flags = 0082 >> ds = 00CF >> ebx = 0000001B edi = FF023044 eip = >> 00001415 es = 008F >> ecx = 000027F9 ebp = FF03AA58 cs = 0097 >> fs = 00B7 >> edx = FF0238DC esp = FF03AA24 ss = 00BF >> gs = 0000 >> >> >> Do you have any clue? >> >> Giuseppe De Arcangelis >> >> -- >> >*************************************************************************** **** >> >> Prof. Giuseppe De Arcangelis ph. +39 >> 0805049043 >> Ass. Prof. of International Economics fax +39 >> 0804049149 >> University of Bari >> e-mail: >> Dip. di Sc. Economiche and CIDEI >> http://cidei.eco.uniroma1.it/~gdearc/ >> Via Camillo Rosalba, 53 >> I-70124 BARI (Italy) >> > > >It doesn't depend on windows98, often I get the same >within windows95 and the only solution I found is to >restart the computer and run rats386 again. > >Daniela Marconi > > >===== > >__________________________________________________ >Do You Yahoo!? >Bid and sell for free at http://auctions.yahoo.com ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Dr. Peter Summers Senior Research Fellow Melbourne Institute of Applied Economic and Social Research Faculty of Economics and Commerce The University of Melbourne Victoria 3010 AUSTRALIA (03) 9344-5313 (phone) [61-3-9344-5313 outside Australia] (03) 9344-5630 (fax) [61-3-9344-5630 outside Australia] p.summers@iaesr.unimelb.edu.au ---------- End of message ---------- From: "Iacoviello,M (pg)" To: "RATS Discussion List" Subject: historical decomposition with a VAR Date: Mon, 15 Nov 1999 11:46:24 -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 (5.5.2448.0) (via Mercury MTS (Bindery) v1.40) Content-Type: text/plain Dear all, I am interested in calculating the historical decomposition of a vector of series from my estimated VAR. I have estimated the moving average representation as well as the series structural shocks. Has anybody written a code that I can use / modify for my purposes? ANy suggestion would be very appreciated. Yours faithfully Matteo Iacoviello ---------- End of message ---------- From: "Dr. J. Dannenbaum" To: "RATS Discussion List" Subject: AW: Problems with RATS386 in a DOS window Date: Mon, 15 Nov 1999 12:46:50 -0000 Errors-to: Reply-to: "RATS Discussion List" Sender: Maiser@efs1.efs.mq.edu.au X-listname: Organization: Universit�t Hamburg X-Mailer: Microsoft Internet E-Mail/MAPI - 8.0.0.4211 (via Mercury MTS (Bindery) v1.40) With me, the problem of running RATS386 in a DOS window always occur after using some other DOS programs. Restarting windows95 or NT will always solve the problem. The other possible error has been using a German letter in a graph-header. Here, a restart obviously doesn't help. In general, I got the feeling RATS386 in a DOS window causes less trouble and displays more stability than using WinRATS 32. Joachim -----Ursprungliche Nachricht----- Von: Peter Summers [SMTP:p.summers@iaesr.unimelb.edu.au] Gesendet am: Montag, 15. November 1999 02:49 An: RATS Discussion List Betreff: Re: Problems with RATS386 in a DOS window If my memory serves me correctly, this has happened to me when I do something like sending an undefined or non-existent series name/number to a procedure (I don't recall the exact cause). If you're calling a proc which requires supplementary cards, you might want to check that these are specified correctly. I do seem to recall that the cause is something which would ordinarily give an error message if done without calling any procs or functions. I run on windows NT v.4, so I agree with Daniela that it's not a windows problem. At 16:23 14/11/99 -0800, you wrote: > > >--- Giuseppe De Arcangelis >wrote: >> >> Sometimes I cannot run rats386 in a dos window >> (within windows98) and I >> get the following message: >> >> ILLEGAL ADDRESS HAS CAUSED A PAGE FAULT >> absolute address = >> error code = 0004 >> eax = FF01CB70 esi = FF0238DC flags = 0082 >> ds = 00CF >> ebx = 0000001B edi = FF023044 eip = >> 00001415 es = 008F >> ecx = 000027F9 ebp = FF03AA58 cs = 0097 >> fs = 00B7 >> edx = FF0238DC esp = FF03AA24 ss = 00BF >> gs = 0000 >> >> >> Do you have any clue? >> >> Giuseppe De Arcangelis >> >> -- >> >*********************************************************************** **** **** >> >> Prof. Giuseppe De Arcangelis ph. +39 >> 0805049043 >> Ass. Prof. of International Economics fax +39 >> 0804049149 >> University of Bari >> e-mail: >> Dip. di Sc. Economiche and CIDEI >> http://cidei.eco.uniroma1.it/~gdearc/ >> Via Camillo Rosalba, 53 >> I-70124 BARI (Italy) >> > > >It doesn't depend on windows98, often I get the same >within windows95 and the only solution I found is to >restart the computer and run rats386 again. > >Daniela Marconi > > >===== > >__________________________________________________ >Do You Yahoo!? >Bid and sell for free at http://auctions.yahoo.com ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Dr. Peter Summers Senior Research Fellow Melbourne Institute of Applied Economic and Social Research Faculty of Economics and Commerce The University of Melbourne Victoria 3010 AUSTRALIA (03) 9344-5313 (phone) [61-3-9344-5313 outside Australia] (03) 9344-5630 (fax) [61-3-9344-5630 outside Australia] p.summers@iaesr.unimelb.edu.au ---------- End of message ---------- From: "Konstantinos Tsatsaronis" To: "RATS Discussion List" Subject: Re: historical decomposition with a VAR Date: Mon, 15 Nov 1999 13:17:53 +0100 Errors-to: Reply-to: "RATS Discussion List" Sender: Maiser@efs1.efs.mq.edu.au X-listname: X-Mailer: Novell GroupWise 5.5 (via Mercury MTS (Bindery) v1.40) Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: quoted-printable Did you look at section 8.7 (p.8-16) of the manual? 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 >>> "Iacoviello,M (pg)" 11/15/99 12:46pm >>> Dear all,=20 I am interested in calculating the historical decomposition of a vector of series from my estimated VAR. I have estimated the moving average representation as well as the series structural shocks. Has anybody written a code that I can use / modify for my purposes? ANy suggestion would be very appreciated. Yours faithfully Matteo Iacoviello DISCLAIMER: Any e-mail messages from the Bank for International Settlements= are sent in good faith, but shall not be binding nor construed as constitu= ting any obligation on the part of the Bank. CONFIDENTIALITY NOTICE: This e-mail contains confidential information, whic= h 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. ---------- End of message ---------- From: Daniel_Porath@dsgv.de To: "RATS Discussion List" Subject: gamma distribution Date: Mon, 15 Nov 1999 15:18:32 +0100 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, does anybody know how to simulate 2 or more gamma distributed series with a cross correlation of zero? Or with any other specified vcv matrix? Thanks Daniel ---------- End of message ---------- From: Daniel_Porath@dsgv.de To: "RATS Discussion List" Subject: gamma distribution Date: Mon, 15 Nov 1999 15:32:41 +0100 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, does anybody know how to simulate 2 or more gamma distributed series with a cross correlation of zero? Or with any other specified vcv matrix? Thanks Daniel ---------- End of message ---------- From: Giuseppe De Arcangelis To: "RATS Discussion List" Subject: Re: Problems with RATS386 in a DOS window Date: Tue, 16 Nov 1999 15:35:37 +0100 Errors-to: Reply-to: "RATS Discussion List" Sender: Maiser@efs1.efs.mq.edu.au X-listname: X-Mailer: Mozilla 4.6 [en] (Win98; I) (via Mercury MTS (Bindery) v1.40) MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit I perfectly agree with both Peter and Daniela. RATS386 crashes when you do something incorrectly with input-output operations, and "many" times (but not always) the problem is solved by restarting the computer. But my point was exactly to avoid the restarting affair (...quite annoying when you have to do it every 10-15 runs). I recently noticed that if I run RATS386 within a DOS window (instead of the full-screen option), I get the "ILLEGAL ADDRESS" error less often. On the other hand the system crashes when in my program there is an "open plot" and "graph" instruction: after the first graph the operating system gets locked and I have to restart the computer. I perfectly agree that RATS386 is much much more stable than WinRATS32: if I try to run my (heavy) programs within WinRATS32 I almost immediately get a memory error. I hope that the RATS programmers get our messages..... Giuseppe Peter Summers wrote: > If my memory serves me correctly, this has happened to me when I do > something like sending an undefined or non-existent series name/number to a > procedure (I don't recall the exact cause). If you're calling a proc which > requires supplementary cards, you might want to check that these are > specified correctly. I do seem to recall that the cause is something which > would ordinarily give an error message if done without calling any procs or > functions. I run on windows NT v.4, so I agree with Daniela that it's not a > windows problem. > > At 16:23 14/11/99 -0800, you wrote: > > > > > >--- Giuseppe De Arcangelis > >wrote: > >> > >> Sometimes I cannot run rats386 in a dos window > >> (within windows98) and I > >> get the following message: > >> > >> ILLEGAL ADDRESS HAS CAUSED A PAGE FAULT > >> absolute address = > >> error code = 0004 > >> eax = FF01CB70 esi = FF0238DC flags = 0082 > >> ds = 00CF > >> ebx = 0000001B edi = FF023044 eip = > >> 00001415 es = 008F > >> ecx = 000027F9 ebp = FF03AA58 cs = 0097 > >> fs = 00B7 > >> edx = FF0238DC esp = FF03AA24 ss = 00BF > >> gs = 0000 > >> > >> > >> Do you have any clue? > >> > >> Giuseppe De Arcangelis > >> > >> -- > >> > >*************************************************************************** > **** > >> > >> Prof. Giuseppe De Arcangelis ph. +39 > >> 0805049043 > >> Ass. Prof. of International Economics fax +39 > >> 0804049149 > >> University of Bari > >> e-mail: > >> Dip. di Sc. Economiche and CIDEI > >> http://cidei.eco.uniroma1.it/~gdearc/ > >> Via Camillo Rosalba, 53 > >> I-70124 BARI (Italy) > >> > > > > > >It doesn't depend on windows98, often I get the same > >within windows95 and the only solution I found is to > >restart the computer and run rats386 again. > > > >Daniela Marconi > > > > > >===== > > > >__________________________________________________ > >Do You Yahoo!? > >Bid and sell for free at http://auctions.yahoo.com > > ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ > Dr. Peter Summers > Senior Research Fellow > Melbourne Institute of Applied Economic and Social Research > Faculty of Economics and Commerce > The University of Melbourne > Victoria 3010 > AUSTRALIA > > (03) 9344-5313 (phone) [61-3-9344-5313 outside Australia] > (03) 9344-5630 (fax) [61-3-9344-5630 outside Australia] > > p.summers@iaesr.unimelb.edu.au ---------- End of message ---------- From: Giuseppe De Arcangelis To: "RATS Discussion List" Subject: Re: historical decomposition with a VAR Date: Tue, 16 Nov 1999 15:41:49 +0100 Errors-to: Reply-to: "RATS Discussion List" Sender: Maiser@efs1.efs.mq.edu.au X-listname: X-Mailer: Mozilla 4.6 [en] (Win98; I) (via Mercury MTS (Bindery) v1.40) MIME-Version: 1.0 Content-Type: multipart/mixed; This is a multi-part message in MIME format. --------------02C0F16B5EC56849B7190014 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Dear Matteo, I send you (and to the list) a proc that I wrote some time ago excatly for the historical decomposition of series (similar to Shapiro-Watson, 1988). I hope it is useful. Giuseppe "Iacoviello,M (pg)" wrote: > Dear all, > > I am interested in calculating the historical decomposition of a vector of > series from my estimated VAR. I have estimated the moving average > representation as well as the series structural shocks. Has anybody written > a code that I can use / modify for my purposes? > > ANy suggestion would be very appreciated. > > Yours faithfully > > Matteo Iacoviello --------------02C0F16B5EC56849B7190014 Content-Type: application/x-unknown-content-type-SRC_auto_file; name="Hist.src" Content-Transfer-Encoding: base64 Content-Disposition: inline; filename="Hist.src" KiAgICAgICAgICAgICAgICAgICAqKioqKioqKioqKioqKioNCiogICAgICAgICAgICAgICAg ICAgKiogIEhJU1QuU1JDICoqDQoqICAgICAgICAgICAgICAgICAgICoqKioqKioqKioqKioq Kg0KKg0KKglSQVRTIFByb2NlZHVyZSBmb3IgSGlzdG9yaWNhbCBEZWNvbXBvc2l0aW9uIG9m IHRoZSBGb3JlY2FzdCBFcnJvcg0KKg0KKgkJYnkgR2l1c2VwcGUgRGUgQXJjYW5nZWxpcw0K KiAgVW5pdmVyc2l0eSBvZiBNaWNoaWdhbiBhbmQgVW5pdmVyc2l0YScgZGkgUm9tYSwgIkxh IFNhcGllbnphIg0KKg0KKgkJCU9jdG9iZXIgMTk5NQ0KKg0KKlRoaXMgcHJvY2VkdXJlIGdp dmVzIHRoZSBoaXN0b3JpY2FsIGRlY29tcG9zaXRpb24gb2YgdGhlIGZvcmVjYXN0IGVycm9y DQoqb2YgZWFjaCBvbmUgb2YgdGhlIHNlcmllcyBpbmNsdWRlZCBpbiBhIFZBUi4gSXQgdGFr ZXMgdGhlIHJlc2lkdWFscyBvZg0KKnRoZSBmaXJzdCBzdGFnZSBWQVIsIHRyYW5zZm9ybXMg dGhlbSBpbnRvIHN0cnVjdHVyYWwgc2hvY2tzIGFuZCB0aGVuDQoqbGluZWFybHkgY29tYmlu ZXMgdGhlbSBpbiBvcmRlciB0byBmaW5kIHRoZSBuLXN0ZXAtYWhlYWQgZm9yZWNhc3QgZXJy b3INCipieSB1c2luZyB0aGUgd2VpZ2h0cyBnaXZlbiBieSB0aGUgc3RydWN0dXJhbCBpbXB1 bHNlIHJlc3BvbnNlIGZ1bmN0aW9ucy4NCioNCipUaGlzIHByb2NlZHVyZSBzaG91bGQgYmUg dXNlZCB0b2dldGhlciB3aXRoIHR3byBvdGhlciBwcm9jZWR1cmVzLA0KKmluaXRpYWxseSBp bnRyb2R1Y2VkIGJ5IEFudG9uaW8gTGF6emFyb3R0aSBhbmQgTWFyaW8gU2VnaGVsaW5pIGFu ZA0KKnVwZGF0ZWQgYnkgdGhlIGF1dGhvcjogKDEpIFNWQVIuU1JDIG9yIFNSX1NWQVIuU1JD LCB3aGljaCBjaGVja3MNCipib3RoIHRoZSBvcmRlciBhbmQgdGhlIHJhbmsgY29uZGl0aW9u IGZvciBpZGVudGlmaWNhdGlvbg0KKm9mIHRoZSBTVkFSIGFuZCBwZXJmb3JtcyB0aGUgZXN0 aW1hdGlvbiBvZiB0aGUNCipoaWdoLWZyZXF1ZW5jeSBtYXRyaWNlczsgKDIpIElNUC5TUkMs IHdoaWNoIGdpdmVzIGltcHVsc2UNCipyZXNwb25zZSBmdW5jdGlvbnMgKGJvdGggZm9yIHRo ZSB2YXJpYWJsZXMgZW50ZXJlZCBpbiBkaWZmZXJlbmNlDQoqb3IgaW4gdGhlIGxldmVsKSBh bmQgcmVsYXRpdmUgZXhhY3Qgc3RhbmRhcmQgZXJyb3JzIChzZWUgR2lhbm5pbmksIDE5OTIs DQoqb3IgSGFtaWx0b24sIDE5OTQsIHAuIDMzNikuDQoqDQoqQSBncmFwaGljYWwgZmFjaWxp dHkgaXMgb3B0aW9uYWxseSBwcm92aWRlZCBpbiB0aGUgcHJvY2VkdXJlLg0KKg0KKiAgIFN5 bnRheA0KKg0KKiAgICBAaGlzdChuZm9yPSxncmFwaD0scHJpbnQ9LGdyaWR2ZWM9KSByZWRy ZXNpZCBhIGIgaW1wdWxzZSBsYWJzZXIgIA0KKg0KKiAgICAJCS0gcmVkcmVzaWQgOiByZXNp ZHVhbHMgZnJvbSB0aGUgZmlyc3Qtc3RhZ2UgaW4gdGhlIFZBUg0KKiAgICAJCSAgICAgICAg ICAgIGVzdGltYXRpb24gKG5vbi1zdHJ1Y3R1cmFsIHNob2NrcykNCioJCS0gYSA6IG1hdHJp eCBBIG9mIHRoZSBoaWdoIGZyZXF1ZW5jeSBjb21iaW5hdGlvbiBvZiB0aGUNCioJCSAgICAg IG5vbi1zdHJ1Y3R1cmFsIHJlc2lkdWFscyAob3V0cHV0IG9mIFNWQVIuU1JDKQ0KKgkJLSBi IDogbWF0cml4IEIgb2YgdGhlIGhpZ2gtZnJlcXVlbmN5IGNvbWJpbmF0aW9uIG9mIHRoZQ0K KgkJICAgICAgc3RydWN0dXJhbCByZXNpZHVhbHMgKG91dHB1dCBvZiBTVkFSLlNSQykNCioJ CS0gaW1wdWxzZSA6IG1hdHJpeCBvZiB0aGUgaW1wdWxzZSByZXNwb25zZSBmdW5jdGlvbnMN CioJCSAgICAgICAgICAgIChvdXRwdXQgSU1QUkVTUCBmcm9tIElNUC5TUkMpDQoqCQktIGxh YnZhciA6IHZlY3RvciBvZiBsYWJlbHMgb2YgdGhlIHZhcmlhYmxlIG5hbWVzIChzYW1lDQoq CQkgICAgICAgICAgIGlucHV0IGFzIGZvciBHUkFJUkYuU1JDKQ0KKgkJLSBsYWJzaG9jayA6 IHZlY3RvciBvZiBsYWJlbHMgb2YgdGhlIHNob2NrIG5hbWVzIChzYW1lDQoqCQkgICAgICAg ICAgIGlucHV0IGFzIGZvciBHUkFJUkYuU1JDKQ0KKg0KKglPcHRpb25zOg0KKgkJLSBncmlk dmVjIDogdmVjdG9yIG9mIGRhdGVzIHRvIGFwcGVhciBpbiB0aGUgZ3JpZCBvZiB0aGUNCioJ CSAgICAgICAgICAgIGdyYXBoaWNhbCByZXByZXNlbnRhdGlvbiBbMF0NCioJCS0gbmZvciA6 IG51bWJlciBvZiBzdGVwcyBhaGVhZCBmb3Igd2hpY2ggdG8gY29uc3RydWN0IHRoZQ0KKgkJ CSB0aGUgZGVjb21wb3NpdGlvbiBbNF0NCioJCS0gZ3JhcGggOiBncmFwaGljYWwgb3B0aW9u IFsxXQ0KKgkJLSBwcmludCA6IHByaW50aW5nIG9wdGlvbiB0byBvYnRhaW4gYm90aCB0aGUg bWF0cml4IG9mDQoqCQkgICAgICAgICAgYWxsIHRoZSBkZWNvbXBvc2l0aW9ucyBhbmQgdGhl IHJlbGF0aXZlIHdlaWdodHMNCioJCS0gbmdyYXBoIDogbnVtYmVyIG9mIGdyYXBocyBwZXIg cGFnZTsgWzBdIGZvciBhbGwgZ3JhcGhzDQoqCQkJICAgaW4gb25lIHBhZ2Ugb3IgY2hvb3Nl IGEgbnVtYmVyICANCioNCioJT3V0cHV0Og0KKgkJLSBoIDogdmVjdG9yW3Nlcmllc10gdGhh dCBjb250YWlucyBhbGwgdGhlIGNvbXBvbmVudHMNCioJCSAgICAgIG9mIGVhY2ggZm9yZWNh c3QgZXJyb3IuIFRoZSBvcmRlciBmb3IgYW4gbi12YXJzIFZBUg0KKgkJICAgICAgaXMgdGhl IGZvbGxvd2luZzogdGhlIGZpcnN0IG4gc2VyaWVzIGFyZSB0aGUNCioJCSAgICAgIGNvbXBv bmVudHMgb2YgdGhlIG4gc3RydWN0dXJhbCBzaG9ja3Mgb24gdGhlIGZpcnN0DQoqCQkgICAg ICB2YXJpYWJsZSBhbmQgdGhlIG4rMSBzZXJpZXMgaXMgdGhlIHRvdGFsDQoqCQkgICAgICBm b3JlY2FzdCBlcnJvciBmb3IgdGhlIGZpcnN0IHZhcmlhYmxlLg0KKgkJICAgICAgRGltZW5z aW9uOiAjdmFyc14yKyN2YXJzDQoqCQktIHdoc3QgOiB2ZWN0b3Jbc2VyaWVzXSB3aXRoIHRo ZSB3ZWlnaHRzIG9mIGVhY2gNCioJCSAgICAgICAgIGNvbXBvbmVudCBvbiB0aGUgdG90YWwg Zm9yZWNhc3QgZXJyb3Igb2YgZWFjaA0KKgkJICAgICAgICAgdmFyaWFibGUuIFRoZSBvcmRl ciBpcyB0aGUgc2FtZSBhcyBpbiAiaCIsDQoqCQkJIGJ1dCB0aGVyZSBpcyBubyB0b3RhbCBm b3JlY2FzdCBlcnJvciBzaW5jZQ0KKgkJCSB0aGUgd2VpZ2h0cyB3aWxsIHN1bSB0byBvbmUg YnkgZGVmaW5pdGlvbi4gDQoqCQkJIERpbWVuc2lvbjogI3ZhcnNeMg0KKgkJLSBoaXN0Iy5y Z2YgOiByYXRzIGdyYXBoaWNzIGZpbGUgZm9yIHRoZSBoaXN0b3JpY2FsDQoqCQkgICAgICAg ICAgICAgIGRlY29tcG9zaXRpb24gb2YgdmFyaWFibGUgIyAoIz0xLC4uLG52YXJzKQ0KKgkJ LSB3aGlzdC5yZ2YgOiByYXRzIGdyYXBoaWNzIGZpbGUgd2l0aCB0aGUgd2VpZ2h0cyBvZg0K KgkJCSAgICAgIGVhY2ggZGlzdHVyYmFuY2Ugb24gYWxsIHRoZSB2YXJpYWJsZXMNCioNCioq KioqKioqKioqKioqKioqKioqKioqKioqKioqKioqKioqKioqKioqKioqKioqKioqKioqKioq KioqKioqKioqKioqKioqICAgICAgCQkgICAgICAgICAgICANCioNCnByb2NlZHVyZSBoaXN0 IHJlZHJlc2lkIGEgYiBpbXB1bHNlIGxhYnZhciBsYWJzaG9jayBncmlkdmVjDQoqDQp0eXBl IHZlY3RvcltzZXJpZXNdIHJlZHJlc2lkDQp0eXBlIHJlY3QgYSBiIGltcHVsc2UNCnR5cGUg bHZlY3QgbGFidmFyIGxhYnNob2NrDQoqDQpvcHRpb24gaW50ZWdlciBuZm9yIDQNCm9wdGlv biBzd2l0Y2ggZ3JhcGggMSANCm9wdGlvbiBzd2l0Y2ggcHJpbnQgMA0Kb3B0aW9uIGluZGV4 IGdyaWR2ZWMNCm9wdGlvbiBpbnRlZ2VyIG5ncmFwaCAwIA0KICAgICAgKioqKioqICAgDQog ICAgICAqKioqKiogICBUaGlzIHNlY3Rpb24gZGVjbGFyZXMgdGhlIHZhcmlhYmxlcw0KICAg ICAgKioqKioqDQpsb2NhbCBzZXJpZXMgZmVyciBmZXJ0b3QgZ3JkDQpsb2NhbCByZWN0IGFh YmIgYWJpbnYgDQpsb2NhbCBsYWJlbCB3aHN0MSBoc3QxDQpsb2NhbCB2ZWN0b3Jbc2VyaWVz XSB5eSBzdHJ1Y3JlcyB6eiB3dyB3aCB3ZWlnaHQgd2hoDQpsb2NhbCByZWN0W3N0cmluZ10g c2hkbGFiDQpsb2NhbCB2ZWN0W3N0cmluZ10gaGRsYWIgdmVjbGFiMg0KbG9jYWwgcmVhbCBu bg0KbG9jYWwgaW50ZWdlciBpIGogayBudmFyIHN0YXJ0cCBlbmRwIG52IG5zdGVwcyBuc2hr IHggZ3AgbmcgbmcyIG5nZGlmZiAkDQpuZ2RpZmYyIHkNCioNCmRlY2xhcmUgdmVjdG9yW3Nl cmllc10gaA0KZGVjbGFyZSB2ZWN0b3Jbc2VyaWVzXSB3aHN0DQoqDQppbnF1aXJlKHNlcmll cz1yZWRyZXNpZCgxKSkgc3RhcnRwIGVuZHAgDQppbnF1aXJlKG1hdHJpeD1pbXB1bHNlKSBu diBuc3RlcHMNCmlucXVpcmUobWF0cml4PWdyaWR2ZWMpIGdwDQpjb21wdXRlIG52YXI9Zml4 KHNxcnQobnYpKQ0KICAgKioqKg0KICAgKioqKiogVGhlIGZvbGxvd2luZyBzdGF0ZXMgdGhh dCB0aGUgbnVtYmVyIG9mIHN0cnVjdHVyYWwgc2hvY2tzDQogICAqKioqKiBpcyBlcXVhbCB0 byB0aGUgbnVtYmVyIG9mIHZhcmlhYmxlcw0KICAgKioqKg0KY29tcHV0ZSBuc2hrPW52YXIN CioNCmRpbSBhYWJiKG52YXIsbnZhcikgeXkobnZhcikgc3RydWNyZXMobnZhcikgaGRsYWIo bnZhcisxKSB6eihudmFyKQ0KZGltIHd3KG5mb3IpIGFiaW52KG52YXIsbnZhcikgd2VpZ2h0 KG52YXIpIHdoaChudmFyKQ0KZGltIHNoZGxhYihudmFyLG52YXIpIHZlY2xhYjIobnZhcikN CmRpbSBoKG52YXIqKG52YXIrMSkpIHdoc3QobnZhcipudmFyKQ0KKg0KICAgKioqKg0KICAg KioqKioqIFRoZSBmb2xsb3dpbmcgZm9ybXMgdHdvIHNlcmllcyBmb3IgdGhlIGdyaWQgdmFs dWVzDQogICAqKioqKiogdG8gYmUgaW5zZXJ0ZWQgaW4gaGlzdG9yaWNhbCBkZWNvbXBvc2l0 aW9uDQogICAqKioqDQpzZXQgZ3JkIHN0YXJ0cCBlbmRwID0gMA0KaWYgJWRlZmluZWQoZ3Jp ZHZlYykNCiB7DQogZG8gaT0xLGdwDQogICBjb21wdXRlIGdyZChncmlkdmVjKGkpKT0xDQog ZW5kIGRvIGkgICANCiB9DQoNCklmIG5mb3ItMT5uc3RlcHMNCiB7DQogZGlzICdUaGUgcHJv Z3JhbSBjYW5ub3QgY29tcHV0ZSB0aGUgRkQgc2luY2UgdGhlIG51bWJlciBvZiBzdGVwcycN CiBkaXMgJ2luIHRoZSBpbXB1bHNlIHJlc3BvbnNlIGZ1bmN0aW9ucyBpcyB0b28gbG93LicN CiBkaXMgJ1JlLXJ1biB0aGUgcHJldmlvdXMgcHJvY2VkdXJlIGZvciBhIGhpZ2hlciBudW1i ZXIgb2Ygc3RlcHMsJw0KIGRpcyAnb3IgZGVjcmVhc2UgbmZvcicNCiB9DQoNCmNvbXB1dGUg YWFiYj1pbnYoYikqYQ0KY29tcHV0ZSBhYmludj1pbnYoYWFiYikNCg0KICAgICAgKioqKioN CiAgICAgICoqKioqKiogVGhpcyBwYXJ0IGNvbXB1dGVzIHRoZSBvcnRob2dvbmFsIGlubm92 YXRpb25zDQogICAgICAqKioqKg0KDQpkbyBpPTEsbnZhcg0KICAgIGRvIGo9MSxuc2hrLTEN CiAgICAgIHNldCB6eigxKSBzdGFydHAgZW5kcCA9IGFhYmIoaSwxKSpyZWRyZXNpZCgxKQ0K ICAgICAgc2V0IHp6KGorMSkgc3RhcnRwIGVuZHAgPSB6eihqKSArIGFhYmIoaSxqKzEpKnJl ZHJlc2lkKGorMSkNCiAgICBlbmQgZG8gaiANCiAgc2V0IHN0cnVjcmVzKGkpIHN0YXJ0cCBl bmRwID0genoobnNoaykgDQplbmQgZG8gaQ0KDQogICAgICAqKioqKg0KICAgICAgKioqKioq KiBOb3cgYWxsIHRoZSBGb3JlY2FzdCBFcnJvciBTZXJpZXMgYXJlIHdyaXR0ZW4NCiAgICAg ICoqKioqKiogaW4gYSBiaWcgdmVjdCBvZiBzZXJpZXMgY2FsbGVkIGgNCiAgICAgICoqKioq DQpkbyBpPTEsbnZhcioobnZhcisxKQ0KICAgc2V0IGgoaSkgc3RhcnRwIGVuZHAgPSAwDQpl bmQgZG8gaQ0KKg0KKiAgICAgIA0KZG8gaT0xLG52YXINCiAgIGRvIGs9MSxuc2hrDQogICAg ICBzZXQgd3coMSkgc3RhcnRwK25mb3IgZW5kcCA9IDANCiAgICAgICAgIGRvIGo9MSxuZm9y LTENCiAgICAgICAgICAgICAgc2V0IHd3KGorMSkgc3RhcnRwK25mb3IgZW5kcCA9IHd3KGop KyQNCiAgICAgICAgICAgICAgICBpbXB1bHNlKG5zaGsqKGstMSkraSxqKSpzdHJ1Y3Jlcyhr KSh0LWorMSkNCiAgICAgICAgIGVuZCBkbyBqDQogICAgICBzZXQgaCgobnZhcisxKSooaS0x KStrKSBzdGFydHArbmZvciBlbmRwID0gd3cobmZvcikgICAgICANCiAgIGVuZCBkbyBrDQpl bmQgZG8gaQ0KDQpkbyBpPTEsbnZhcg0KICAgZG8gaz0xLG5zaGstMQ0KICAgICAgc2V0IHl5 KDEpIHN0YXJ0cCtuZm9yIGVuZHAgPSBoKChudmFyKzEpKihpLTEpKzEpDQogICAgICBzZXQg eXkoaysxKSBzdGFydHArbmZvciBlbmRwID0geXkoaykraCgobnZhcisxKSooaS0xKStrKzEp DQogICBlbmQgZG8gaw0KICBzZXQgaChpKihudmFyKzEpKSBzdGFydHArbmZvciBlbmRwID0g eXkobnNoaykNCmVuZCBkbyBpDQoNCiAgICAgICoqKioqDQogICAgICAqKioqKioqIFRoZSBu ZXh0IHZlY3Qgb2Ygc2VyaWVzIGNvbnRhaW5zIHRoZSB3ZWlnaHRzIG9mDQogICAgICAqKioq KioqIHRoZSBmb3JlY2FzdCBlcnJvciBvZiBlYWNoIHNob2NrIGluIHRoZSB0b3RhbA0KICAg ICAgKioqKioqKiBmb3JlY2FzdCBlcnJvciBvZiB0aGUgdmFyaWFibGUNCiAgICAgICoqKioq DQoNCmRvIGk9MSxudmFyDQogICBkbyBrPTEsbnNoay0xDQogICAgICBzZXQgeXkoMSkgc3Rh cnRwK25mb3IgZW5kcCA9IGFicyhoKChudmFyKzEpKihpLTEpKzEpKQ0KICAgICAgc2V0IHl5 KGsrMSkgc3RhcnRwK25mb3IgZW5kcCA9IHl5KGspK2FicyhoKChudmFyKzEpKihpLTEpK2sr MSkpDQogICBlbmQgZG8gaw0KICBzZXQgd2hoKGkpIHN0YXJ0cCtuZm9yIGVuZHAgPSB5eShu c2hrKQ0KZW5kIGRvIGkNCg0KICAgICAgDQpkbyBpPTEsbnZhcg0KICAgZG8gaz0xLG5zaGsN CiAgICAgIHNldCB3aHN0KG52YXIqKGktMSkraykgc3RhcnRwK25mb3IgZW5kcCA9JA0KICAg ICAgMTAwKmFicyhoKChudmFyKzEpKihpLTEpK2spKS93aGgoaSkNCiAgIGVuZCBkbyBrDQpl bmQgZG8gaSAgICAgIA0KDQpJZiBwcmludD09MQ0Kew0KZGlzICdIaXN0b3JpY2FsIEZvcmVj YXN0IEVycm9yIERlY29tcG9zaXRpb24nIG5mb3IgJyBTdGVwcyBBaGVhZCcNCmRpcyAnKE5v dGljZTogdGhlIGZpcnN0IG4gY29sdW1ucyBhcmUgdGhlIGNvbnRyaWJ1dGlvbnMgb2YgdGhl Jw0KZGlzICcgZmlyc3QgbiBzdHJ1Y3R1cmFsIHNob2NrcyBvbiB0aGUgZmlyc3QgdmFyaWFi bGU7IHRoZSAobisxKS10aCcNCmRpcyAnIGNvbHVtbiBpcyB0aGUgdG90YWwgZm9yZWNhc3Qg ZXJyb3Igb24gdGhlIGZpcnN0IHZhcmlhYmxlLCcNCmRpcyAnIGFuZCBzbyBvbiknDQpwcmlu dCBzdGFydHAgZW5kcCBoDQpkaXMgJyAnDQpkaXMgJ1dlaWdodHMgb2YgdGhlIERpZmZlcmVu dCBTaG9ja3Mgb24gdGhlIFRvdGFsIEZvcmVjYXN0IEVycm9yJw0KZGlzICcoU2FtZSBvcmRl ciBhcyBmb3IgdGhlIEhpc3RvcmljYWwgRGVjb21wb3NpdGlvbiBhYm92ZSknDQpwcmludCBz dGFydHAgZW5kcCB3aHN0DQp9DQoqDQoqDQpJZiBncmFwaA0KICB7DQogICAqKioqKioqDQog ICAqKioqKioqICAgVGhpcyBzZWN0aW9uIHBlcmZvcm1zIHRoZSBncmFwaCBvZiB0aGUgRm9y ZWNhc3QgRXJyb3INCiAgICoqKioqKiogICBEZWNvbXBvc2l0aW9uDQogICAqKioqKioqDQoN CiAgaWYgbmdyYXBoPT0wDQogKioqKiogIA0KICAgIHsNCiAgICBkaXMoc3RvcmU9aGRsYWIo MSkpICdUb3RhbCcNCiAgICAqDQogICAgZG8gaT0xLG52YXINCiAgICAgZGlzKHN0b3JlPWhk bGFiKGkrMSkpICdGb3JlY2FzdCBFcnJvciBvZiAnIGxhYnZhcihpKSAnICcgbmZvciAkDQog ICAgICAgJyBTdGVwcyBBaGVhZCcNCiAgICBlbmQgZG8gaQ0KICAgICoNCiAgICAqDQogICAg ZG8gaT0xLG52YXINCiAgICAgZG8gaj0xLG52YXINCiAgICAgZGlzKHN0b3JlPXNoZGxhYihp LGopKSAnQ29udHJpYnV0aW9uIG9mICcgbGFic2hvY2soaikgJA0KICAgICAgICAgICAgICAg ICAnIG9uIHRoZSBGRSBvZiAnIGxhYnZhcihpKQ0KICAgICBlbmQgZG8gag0KICAgIGVuZCBk byBpDQogICAgKg0KICAgIGRvIGk9MSxudmFyDQogICAgICBjb21wdXRlIFtsYWJlbF0gaHN0 MT0naGlzdCcraSsnLnJnZicNCiAgICAgIG9wZW4gcGxvdCAmaHN0MQ0KICAgICAgZ3JwYXJt KGJvbGQpIGhsYWJlbCAxOA0KICAgICAgZ3JwYXJtIGF4aWxhYmVsIDI0DQogICAgICBzcGdy YXBoKHZmaWVsZHM9bnZhcisxKQ0KICAgICAgc21wbCBzdGFydHArbmZvciBlbmRwDQogICAg ICBzZXQgZmVydG90IHN0YXJ0cCtuZm9yIGVuZHAgPSBoKChudmFyKzEpKmkpDQogICAgICBn cmFwaChoZWFkZXI9aGRsYWIoaSsxKSwgc3ViaGVhZGVyPSBoZGxhYigxKSwkDQogICAgICAg IHRpY2tzLGRhdGVzLGdyaWQ9Z3JkKSAxIDENCiAgICAgICMgZmVydG90DQogICAgICBkbyBr PTEsbnZhcg0KICAgICAgICBzZXQgZmVyciBzdGFydHArbmZvciBlbmRwID0gaCgobnZhcisx KSooaS0xKStrKQ0KICAgICAgICBncmFwaChzdWJoZWFkZXI9IHNoZGxhYihpLGspLCB0aWNr cyxkYXRlcyxncmlkPWdyZCkgMSBrKzENCiAgICAgICAgIyBmZXJyDQogICAgICBlbmQgZG8g aw0KICAgICAgc3BncmFwaChkb25lKSANCiAgICBlbmQgZG8gaQ0KDQogICAqKioqKioqDQog ICAqKioqKioqICAgVGhpcyBzZWN0aW9uIHBlcmZvcm1zIHRoZSBncmFwaCBvZiB0aGUgRm9y ZWNhc3QgRXJyb3INCiAgICoqKioqKiogICBEZWNvbXBvc2l0aW9uIFdlaWdodHMgZm9yIGVh Y2ggdmFyaWFibGUgYW5kIGVhY2ggc2hvY2sNCiAgICoqKioqKioNCg0KDQogICAgZG8gaT0x LG52YXINCiAgICAgIGRpcyhzdG9yZT12ZWNsYWIyKGkpKSAnV2VpZ2h0cyBpbiB0aGUnJA0K ICAgICAgIG5mb3IgJ1N0ZXAtQWhlYWQgRm9yZWNhc3QgRXJyb3Igb2YgJyBsYWJ2YXIoaSkN CiAgICBlbmQgZG8gaSANCg0KICAgIG9wZW4gcGxvdCB3aGlzdC5yZ2YgDQoNCiAgICBncnBh cm0oYm9sZCkgaGxhYmVsIDE4DQogICAgZ3JwYXJtIGF4aWxhYmVsIDI0DQogICAgc3BncmFw aCh2ZmllbGRzPW5zaGspDQogICAgc21wbCBzdGFydHArbmZvciBlbmRwDQogICAgZG8gaT0x LG52YXINCiAgICAgIGRvIGs9MSxuc2hrDQogICAgICAgIHNldCB3ZWlnaHQoaykgc3RhcnRw K25mb3IgZW5kcCA9IHdoc3QobnZhciooaS0xKStrKQ0KICAgICAgICBsYWJlbHMgd2VpZ2h0 KGspDQogICAgICAgICMgbGFic2hvY2soaykNCiAgICAgIGVuZCBkbyBrDQogICAgICBpZiBp PT0xDQogICAgICAgew0KICAgICAgIGxpc3QgeCA9IDEgdG8gbnNoaw0KICAgICAgIGdyYXBo KHN0eWxlPXN0YWNrZWQsaGVhZGVyPSB2ZWNsYWIyKGkpLCB0aWNrcywkDQogICAgICAgICAg a2V5PWJlbG93LGRhdGVzLGdyaWQ9Z3JkLG1heD0xMTApIG5zaGsgaSANCiAgICAgICBjYXJk cyB3ZWlnaHQoeCkgL3gNCiAgICAgICB9DQogICAgICAgZWxzZQ0KICAgICAgIHsNCiAgICAg ICBsaXN0IHggPSAxIHRvIG5zaGsNCiAgICAgICBncmFwaChzdHlsZT1zdGFja2VkLGhlYWRl cj0gdmVjbGFiMihpKSwgdGlja3MsJA0KICAgICAgICAgIGRhdGVzLGdyaWQ9Z3JkLG1heD0x MTApIG5zaGsgaSANCiAgICAgICBjYXJkcyB3ZWlnaHQoeCkgL3gNCiAgICAgICB9DQogICAg ZW5kIGRvIGkgIA0KICAgIHNwZ3JhcGgoZG9uZSkgDQogICAgfQ0KICAqKioqICANCiAgIGVs c2UgaWYgbmdyYXBoPT0xDQogICoqKiogDQogICAgew0KICAgIGRpcyhzdG9yZT1oZGxhYigx KSkgJ1RvdGFsJw0KICAgICoNCiAgICBkbyBpPTEsbnZhcg0KICAgIGRpcyhzdG9yZT1oZGxh YihpKzEpKSAnRm9yZWNhc3QgRXJyb3Igb2YgJyBsYWJ2YXIoaSkgJyAnIG5mb3IgJA0KICAg ICAgICcgU3RlcHMgQWhlYWQnDQogICAgZW5kIGRvIGkNCiAgICAqDQogICAgKg0KICAgIGRv IGk9MSxudmFyDQogICAgICBkbyBqPTEsbnZhcg0KICAgICAgICBkaXMoc3RvcmU9c2hkbGFi KGksaikpICdDb250cmlidXRpb24gb2YgJyBsYWJzaG9jayhqKSAkDQogICAgICAgICAgICAg ICAgICcgb24gdGhlIEZFIG9mICcgbGFidmFyKGkpDQogICAgICBlbmQgZG8gag0KICAgIGVu ZCBkbyBpDQogICAgKg0KICAgIGRvIGk9MSxudmFyDQogICAgICBkbyBqPWksbnZhcisxIA0K ICAgICAgICBjb21wdXRlIFtsYWJlbF0gaHN0MT0naGlzdCcraStqKycucmdmJw0KICAgICAg ICBvcGVuIHBsb3QgJmhzdDENCiAgICAgICAgZ3JwYXJtKGJvbGQpIGhsYWJlbCAxOA0KICAg ICAgICBncnBhcm0gYXhpbGFiZWwgMjQNCiAgICAgICAgc21wbCBzdGFydHArbmZvciBlbmRw DQogICAgICAgIGlmIGo9PTENCiAgICAgICAgew0KICAgICAgICBzZXQgZmVydG90IHN0YXJ0 cCtuZm9yIGVuZHAgPSBoKChudmFyKzEpKmkpDQogICAgICAgIGdyYXBoKGhlYWRlcj1oZGxh YihpKzEpLCBzdWJoZWFkZXI9IGhkbGFiKDEpLCQNCiAgICAgICAgICB0aWNrcyxkYXRlcyxn cmlkPWdyZCkgMSAxDQogICAgICAgICMgZmVydG90DQogICAgICAgIH0NCiAgICAgICAgZWxz ZQ0KICAgICAgICB7DQogICAgICAgIHNldCBmZXJyIHN0YXJ0cCtuZm9yIGVuZHAgPSBoKChu dmFyKzEpKihpLTEpK2opDQogICAgICAgIGdyYXBoKHN1YmhlYWRlcj0gc2hkbGFiKGksaiks IHRpY2tzLGRhdGVzLGdyaWQ9Z3JkKSAxIGorMQ0KICAgICAgICAjIGZlcnINCiAgICAgICAg fQ0KICAgICAgZW5kIGRvIGoNCiAgICBlbmQgZG8gaQ0KDQogICAgKioqKioqKg0KICAgICoq KioqKiogICBUaGlzIHNlY3Rpb24gcGVyZm9ybXMgdGhlIGdyYXBoIG9mIHRoZSBGb3JlY2Fz dCBFcnJvcg0KICAgICoqKioqKiogICBEZWNvbXBvc2l0aW9uIFdlaWdodHMgZm9yIGVhY2gg dmFyaWFibGUgYW5kIGVhY2ggc2hvY2sNCiAgICAqKioqKioqDQoNCg0KICAgIGRvIGk9MSxu dmFyDQogICAgICBkaXMoc3RvcmU9dmVjbGFiMihpKSkgJ1dlaWdodHMgaW4gdGhlJyQNCiAg ICAgICBuZm9yICdTdGVwLUFoZWFkIEZvcmVjYXN0IEVycm9yIG9mICcgbGFidmFyKGkpDQog ICAgZW5kIGRvIGkgDQoNCiAgICBncnBhcm0oYm9sZCkgaGxhYmVsIDE4DQogICAgZ3JwYXJt IGF4aWxhYmVsIDI0DQogICAgc21wbCBzdGFydHArbmZvciBlbmRwDQogICAgZG8gaT0xLG52 YXINCiAgICAgIGRvIGs9MSxuc2hrDQogICAgICAgIHNldCB3ZWlnaHQoaykgc3RhcnRwK25m b3IgZW5kcCA9IHdoc3QobnZhciooaS0xKStrKQ0KICAgICAgICBsYWJlbHMgd2VpZ2h0KGsp DQogICAgICAgICMgbGFic2hvY2soaykNCiAgICAgIGVuZCBkbyBrDQogICAgICBjb21wdXRl IFtsYWJlbF0gd2hzdDE9J3doaXN0JytpKycucmdmJw0KICAgICAgb3BlbiBwbG90ICZ3aHN0 MQ0KICAgICAgaWYgaT09MQ0KICAgICAgICB7DQogICAgICAgIGxpc3QgeCA9IDEgdG8gbnNo aw0KICAgICAgICBncmFwaChzdHlsZT1zdGFja2VkLGhlYWRlcj0gdmVjbGFiMihpKSwgdGlj a3MsJA0KICAgICAgICAgIGtleT1iZWxvdyxkYXRlcyxncmlkPWdyZCxtYXg9MTEwKSBuc2hr IGkgDQogICAgICAgIGNhcmRzIHdlaWdodCh4KSAveA0KICAgICAgICB9DQogICAgICAgIGVs c2UNCiAgICAgICAgew0KICAgICAgICBsaXN0IHggPSAxIHRvIG5zaGsNCiAgICAgICAgZ3Jh cGgoc3R5bGU9c3RhY2tlZCxoZWFkZXI9IHZlY2xhYjIoaSksIHRpY2tzLCQNCiAgICAgICAg ICBkYXRlcyxncmlkPWdyZCxtYXg9MTEwKSBuc2hrIGkgDQogICAgICAgIGNhcmRzIHdlaWdo dCh4KSAveA0KICAgICAgICB9DQogICAgZW5kIGRvIGkgIA0KICAgIH0NCiAgKioqKg0KICAg IGVsc2UNCiAgKioqKiAgDQogICAgew0KICAgIGRpcyhzdG9yZT1oZGxhYigxKSkgJ1RvdGFs Jw0KICAgICoNCiAgICBkbyBpPTEsbnZhcg0KICAgIGRpcyhzdG9yZT1oZGxhYihpKzEpKSAn Rm9yZWNhc3QgRXJyb3Igb2YgJyBsYWJ2YXIoaSkgJyAnIG5mb3IgJA0KICAgICAgICcgU3Rl cHMgQWhlYWQnDQogICAgZW5kIGRvIGkNCiAgICAqDQogICAgKg0KICAgIGRvIGk9MSxudmFy DQogICAgICBkbyBqPTEsbnZhcg0KICAgICAgICBkaXMoc3RvcmU9c2hkbGFiKGksaikpICdD b250cmlidXRpb24gb2YgJyBsYWJzaG9jayhqKSAkDQogICAgICAgICAgICAgICAgICcgb24g dGhlIEZFIG9mICcgbGFidmFyKGkpDQogICAgICBlbmQgZG8gag0KICAgIGVuZCBkbyBpDQog ICAgKg0KICAgIGNvbXB1dGUgbmc9Zml4KG52YXIvbmdyYXBoKSsxDQogICAgY29tcHV0ZSBu Z2RpZmY9bmcqbmdyYXBoLShudmFyKzEpDQogICAgZG8gaT0xLG52YXINCiAgICAgIGRvIGo9 MSxuZw0KICAgICAgICBjb21wdXRlIFtsYWJlbF0gaHN0MT0naGlzdCcraStqKycucmdmJw0K ICAgICAgICBvcGVuIHBsb3QgJmhzdDENCiAgICAgICAgZ3JwYXJtKGJvbGQpIGhsYWJlbCAx OA0KICAgICAgICBncnBhcm0gYXhpbGFiZWwgMjQNCiAgICAgICBpZiBqPT0xDQogICAgICAg IHsNCiAgICAgICAgc3BncmFwaCh2ZmllbGRzPW5ncmFwaCkNCiAgICAgICAgc21wbCBzdGFy dHArbmZvciBlbmRwDQogICAgICAgIHNldCBmZXJ0b3Qgc3RhcnRwK25mb3IgZW5kcCA9IGgo KG52YXIrMSkqaSkNCiAgICAgICAgZ3JhcGgoaGVhZGVyPWhkbGFiKGkrMSksIHN1YmhlYWRl cj0gaGRsYWIoMSksJA0KICAgICAgICAgIHRpY2tzLGRhdGVzLGdyaWQ9Z3JkKSAxIDENCiAg ICAgICAgIyBmZXJ0b3QNCiAgICAgICAgZG8gaz0xLG5ncmFwaC0xDQogICAgICAgICAgc2V0 IGZlcnIgc3RhcnRwK25mb3IgZW5kcCA9IGgoKG52YXIrMSkqKGktMSkraykNCiAgICAgICAg ICBncmFwaChzdWJoZWFkZXI9IHNoZGxhYihpLGspLCB0aWNrcyxkYXRlcyxncmlkPWdyZCkg MSAkDQogICAgICAgICAgICAgIGsrMQ0KICAgICAgICAgICMgZmVycg0KICAgICAgICBlbmQg ZG8gaw0KICAgICAgICBzcGdyYXBoKGRvbmUpDQogICAgICAgIH0NCiAgICAgICBlbHNlIGlm IGo9PW5nDQogICAgICAgIHsNCiAgICAgICAgc3BncmFwaCh2ZmllbGRzPW5ncmFwaC1uZ2Rp ZmYpDQogICAgICAgIGRvIGs9MSxuZ3JhcGgtbmdkaWZmDQogICAgICAgICBpZiBrPT0xDQog ICAgICAgICAgew0KICAgICAgICAgIHNldCBmZXJyIHN0YXJ0cCtuZm9yIGVuZHAgPSBoKChu dmFyKzEpKihpLTEpKyhuZy0xKSpuZ3JhcGgray0xKQ0KICAgICAgICAgIGdyYXBoKGhlYWRl cj1oZGxhYihpKzEpLHN1YmhlYWRlcj0gc2hkbGFiKGksKG5nLTEpKm5ncmFwaCtrLTEpLCQN CiAgICAgICAgICAgIHRpY2tzLGRhdGVzLGdyaWQ9Z3JkKSAxIGsNCiAgICAgICAgICAjIGZl cnINCiAgICAgICAgICB9DQogICAgICAgICBlbHNlDQogICAgICAgICAgew0KICAgICAgICAg IHNldCBmZXJyIHN0YXJ0cCtuZm9yIGVuZHAgPSBoKChudmFyKzEpKihpLTEpKyhuZy0xKSpu Z3JhcGgray0xKQ0KICAgICAgICAgIGdyYXBoKHN1YmhlYWRlcj0gc2hkbGFiKGksKG5nLTEp Km5ncmFwaCtrLTEpLCB0aWNrcyxkYXRlcywkDQogICAgICAgICAgICBncmlkPWdyZCkgMSBr DQogICAgICAgICAgIyBmZXJyDQogICAgICAgICAgfQ0KICAgICAgICBlbmQgZG8gaw0KICAg ICAgICBzcGdyYXBoKGRvbmUpDQogICAgICAgIH0NCiAgICAgICBlbHNlDQogICAgICAgIHsN CiAgICAgICAgc3BncmFwaCh2ZmllbGRzPW5ncmFwaCkNCiAgICAgICAgZG8gaz0xLG5ncmFw aA0KICAgICAgICAgaWYgaz09MQ0KICAgICAgICAgIHsNCiAgICAgICAgICBzZXQgZmVyciBz dGFydHArbmZvciBlbmRwID0gaCgobnZhcisxKSooaS0xKSsoai0xKSpuZ3JhcGgray0xKQ0K ICAgICAgICAgIGdyYXBoKGhlYWRlcj1oZGxhYihpKzEpLHN1YmhlYWRlcj0gc2hkbGFiKGks KGotMSkqbmdyYXBoK2stMSksJA0KICAgICAgICAgICAgdGlja3MsZGF0ZXMsZ3JpZD1ncmQp IDEgaw0KICAgICAgICAgICMgZmVycg0KICAgICAgICAgIH0NCiAgICAgICAgIGVsc2UNCiAg ICAgICAgICB7DQogICAgICAgICAgc2V0IGZlcnIgc3RhcnRwK25mb3IgZW5kcCA9IGgoKG52 YXIrMSkqKGktMSkrKGotMSkqbmdyYXBoK2stMSkNCiAgICAgICAgICBncmFwaChzdWJoZWFk ZXI9IHNoZGxhYihpLChqLTEpKm5ncmFwaCtrLTEpLCB0aWNrcyxkYXRlcywkDQogICAgICAg ICAgICBncmlkPWdyZCkgMSBrDQogICAgICAgICAgIyBmZXJyDQogICAgICAgICAgfQ0KICAg ICAgICBlbmQgZG8gaw0KICAgICAgICBzcGdyYXBoKGRvbmUpDQogICAgICAgIH0NCiAgICAg IGVuZCBkbyBqIA0KICAgIGVuZCBkbyBpDQoNCiAgICAqKioqKioqDQogICAgKioqKioqKiAg IFRoaXMgc2VjdGlvbiBwZXJmb3JtcyB0aGUgZ3JhcGggb2YgdGhlIEZvcmVjYXN0IEVycm9y DQogICAgKioqKioqKiAgIERlY29tcG9zaXRpb24gV2VpZ2h0cyBmb3IgZWFjaCB2YXJpYWJs ZSBhbmQgZWFjaCBzaG9jaw0KICAgICoqKioqKioNCg0KDQogICAgZG8gaT0xLG52YXINCiAg ICAgIGRpcyhzdG9yZT12ZWNsYWIyKGkpKSAnV2VpZ2h0cyBpbiB0aGUnJA0KICAgICAgIG5m b3IgJ1N0ZXAtQWhlYWQgRm9yZWNhc3QgRXJyb3Igb2YgJyBsYWJ2YXIoaSkNCiAgICBlbmQg ZG8gaSANCg0KICAgIGNvbXB1dGUgbmcyPWZpeChudmFyLTEvbmdyYXBoKSsxDQogICAgY29t cHV0ZSBuZ2RpZmYyPW5nMipuZ3JhcGgtbnZhcg0KDQogICAgc21wbCBzdGFydHArbmZvciBl bmRwDQogICAgICBkbyBqPTEsbmcyDQogICAgICAgIGNvbXB1dGUgW2xhYmVsXSB3aHN0MT0n d2hpc3QnK2orJy5yZ2YnDQogICAgICAgIG9wZW4gcGxvdCAmd2hzdDENCiAgICAgICAgZ3Jw YXJtKGJvbGQpIGhsYWJlbCAxOA0KICAgICAgICBncnBhcm0gYXhpbGFiZWwgMjQNCiAgICAg ICAgc3BncmFwaCh2ZmllbGRzPW5ncmFwaCkNCiAgICAgICBpZiBqPT1uZzINCiAgICAgICAg ew0KICAgICAgICBkbyBpPTEsbmdkaWZmMiANCiAgICAgICAgIGRvIGs9MSxuc2hrDQogICAg ICAgICAgIHNldCB3ZWlnaHQoaykgc3RhcnRwK25mb3IgZW5kcCA9IHdoc3QoKG52YXIqKCgo bmcyLTEpKm5ncmFwaCtpKS0xKSkraykNCiAgICAgICAgICAgbGFiZWxzIHdlaWdodChrKQ0K ICAgICAgICAgICAjIGxhYnNob2NrKGspDQogICAgICAgICBlbmQgZG8gaw0KICAgICAgICAg aWYgaT09MQ0KICAgICAgICAgICB7DQogICAgICAgICAgIGxpc3QgeCA9IDEgdG8gbnNoaw0K ICAgICAgICAgICBncmFwaChzdHlsZT1zdGFja2VkLGhlYWRlcj0gdmVjbGFiMigobmcyLTEp Km5ncmFwaCtpKSwgdGlja3MsJA0KICAgICAgICAgICAgICBrZXk9YmVsb3csZGF0ZXMsZ3Jp ZD1ncmQsbWF4PTExMCkgbnNoayBpDQogICAgICAgICAgIGNhcmRzIHdlaWdodCh4KSAveA0K ICAgICAgICAgICB9DQogICAgICAgICAgZWxzZQ0KICAgICAgICAgICB7DQogICAgICAgICAg IGxpc3QgeCA9IDEgdG8gbnNoaw0KICAgICAgICAgICBncmFwaChzdHlsZT1zdGFja2VkLGhl YWRlcj0gdmVjbGFiMigobmcyLTEpKm5ncmFwaCtpKSwgdGlja3MsJA0KICAgICAgICAgICAg ICBkYXRlcyxncmlkPWdyZCxtYXg9MTEwKSBuc2hrIGkNCiAgICAgICAgICAgY2FyZHMgd2Vp Z2h0KHgpIC94DQogICAgICAgICAgIH0NCiAgICAgICAgICBlbmQgZG8gaSANCiAgICAgICAg IH0NCiAgICAgICAgZWxzZQ0KICAgICAgICAgeyANCiAgICAgICAgIGRvIGk9MSxuZ3JhcGgN CiAgICAgICAgICAgZG8gaz0xLG5zaGsNCiAgICAgICAgICAgICBzZXQgd2VpZ2h0KGspIHN0 YXJ0cCtuZm9yIGVuZHAgPSB3aHN0KG52YXIqKChqLTEpKm5ncmFwaCtpLTEpK2spDQogICAg ICAgICAgICAgbGFiZWxzIHdlaWdodChrKQ0KICAgICAgICAgICAgICMgbGFic2hvY2soaykN CiAgICAgICAgICAgZW5kIGRvIGsNCiAgICAgICAgICBpZiBpPT0xDQogICAgICAgICAgIHsN CiAgICAgICAgICAgbGlzdCB4ID0gMSB0byBuc2hrDQogICAgICAgICAgIGdyYXBoKHN0eWxl PXN0YWNrZWQsaGVhZGVyPSB2ZWNsYWIyKChqLTEpKm5ncmFwaCtpKSwgdGlja3MsJA0KICAg ICAgICAgICAgIGtleT1iZWxvdyxkYXRlcyxncmlkPWdyZCxtYXg9MTEwKSBuc2hrIGkgDQog ICAgICAgICAgIGNhcmRzIHdlaWdodCh4KSAveA0KICAgICAgICAgICB9DQogICAgICAgICAg ZWxzZQ0KICAgICAgICAgICB7DQogICAgICAgICAgIGxpc3QgeCA9IDEgdG8gbnNoaw0KICAg ICAgICAgICBncmFwaChzdHlsZT1zdGFja2VkLGhlYWRlcj0gdmVjbGFiMigoai0xKSpuZ3Jh cGgraSksIHRpY2tzLCQNCiAgICAgICAgICAgICAgZGF0ZXMsZ3JpZD1ncmQsbWF4PTExMCkg bnNoayBpDQogICAgICAgICAgIGNhcmRzIHdlaWdodCh4KSAveA0KICAgICAgICAgICB9DQog ICAgICAgICBlbmQgZG8gaQ0KICAgICAgICAgfQ0KICAgICAgICBzcGdyYXBoKGRvbmUpDQog ICAgICBlbmQgZG8gaiANCiAgICB9DQogIH0NCioNCmVuZCBoaXN0CQ0KKioNCioNCg== --------------02C0F16B5EC56849B7190014-- ---------- End of message ---------- From: "Estima" To: "RATS Discussion List" Subject: Re: Problems with RATS386 in a DOS window Date: Tue, 16 Nov 1999 16:07:25 -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 perfectly agree that RATS386 is much much more stable than WinRATS32: if I try > to run my (heavy) programs within WinRATS32 I almost immediately get a memory > error. Do you mean that you get an M4 error message from RATS indicating that you don't have enough memory available? Or do you mean that RATS crashes with a Windows error message? Either way, please get in touch with us directly so we can identify and fix any problems. For example, if you have a problem that crashes, try executing it one line at a time to see which line causes the problem. Then, send us a copy of the program along with a description of where it fails and what happens when it fails. We may ask you to send us the data file as well. Thanks, Tom Maycock -- ------------------------------------------------------------ | Estima | Sales: (800) 822-8038 | | P.O. Box 1818 | (847) 864-8772 | | Evanston, IL 60204-1818 | Support: (847) 864-1910 | | USA | Fax: (847) 864-6221 | | http://www.estima.com | estima@estima.com | ------------------------------------------------------------ ---------- End of message ---------- From: "Estima" To: "RATS Discussion List" Subject: Re: Problems with RATS386 in a DOS window Date: Tue, 16 Nov 1999 16:04:34 -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) Regarding issues with RATS386 and Windows 95/98/NT: If you are getting an error message when trying to start the program, this is almost certainly a DOS-mode memory management issue. This is due to the fact that the fairly sophisticated extended/expanded/virtual memory manager used in RATS386 predates the most recent versions of Windows, and thus isn't always able to handle all situations (if anyone has seen some good _recent_ DOS extenders/compatible compiler combinations, please let us know). I've noticed that this sometimes occurs when you have several other (Windows) programs open, so closing other apps sometimes helps. However, I have recently found a setup that seems to work well. First, I strongly recommend running RATS386 from a DOS prompt. Create a copy of your MS-DOS prompt icon, and right-click to bring up the Properties menu. From the "Program" tab, selected the "Advanced" button, and turn on the "Prevent MS-DOS-based programs from detecting Windws". This DOS-prompt setting seems to work well. As for the stability of WinRATS-32 vs. RATS386, my experience hasn't revealed any significant differences between the two. First, let's note that bugs in RATS fall into two basic categories: 1) a problem with the implementation of RATS instructions, functions, syntax parser, etc. These are problems that are directly related to executing RATS instructions, and are usually reproduceable. If a program repeatedly fails, try executing it one line at a time to see if you can find the problematic instruction or section, and get in touch with us. 2) A general category of problems I would refer to as "interface" issues. This includes memory management, mouse clicks, menu operations, working with windows, graphs, API calls, etc. These tend to be more "random" in appearance, less reproduceable, harder to diagnose. Type (1) errors would generally effect both WinRATS-32 and RATS386 in more or less the same way, and this has been largely true in our experience. As for type (2) problems, there's more chance for error with a Windows app, because a lot more is going on. Fortuantely, the number of instabilities related to the Windows implementation itself has been surprising small since the release of the first Windows version. Remember that we certainly can't fix any problems unless we know about them. If you are running into problems, don't just curse at your computer--drop us a line or give us a call. I can't make any guarentees, as some problems can be _very_ difficult to diagnose and fix. However, many problems either already have been fixed by a more recent version, or can be diagnosed and fixed so the next version behaves properly. Again: we can't fix 'em if we don't know about 'em. Thanks, Tom Maycock Estima -- ------------------------------------------------------------ | Estima | Sales: (800) 822-8038 | | P.O. Box 1818 | (847) 864-8772 | | Evanston, IL 60204-1818 | Support: (847) 864-1910 | | USA | Fax: (847) 864-6221 | | http://www.estima.com | estima@estima.com | ------------------------------------------------------------ ---------- End of message ---------- From: Yemane Wolde-rufael To: "RATS Discussion List" Subject: Residual-based tests for cointegration in models with regime shif Date: Thu, 18 Nov 1999 08:04:10 -0800 (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; charset=us-ascii X-Mailer: Mercury MTS (Bindery) v1.40 Dear RATS Fellows I am looking for a RATS code for the Gregory and Hansen "Residual-based tests for cointegration in models with regime shifs" Journal of Econometrics, 70 (1996) 99-126. I would appreciate if you could help. Many thanks Yemane Wolde-Rufael __________________________________________________ Do You Yahoo!? Bid and sell for free at http://auctions.yahoo.com ---------- End of message ---------- From: Yemane Wolde-rufael To: "RATS Discussion List" Subject: Gregory and Hansen: Residual-based tests for cointegration in Date: Thu, 18 Nov 1999 09:55:00 -0800 (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; charset=us-ascii X-Mailer: Mercury MTS (Bindery) v1.40 Dear RATS Fellows I am looking for a RATS code for the Gregory and Hansen "Residual-based tests for cointegration in models with regime shifs" Journal of Econometrics, 70 (1996) 99-126. I would appreciate if you could help. Many thanks Yemane Wolde-Rufael __________________________________________________ Do You Yahoo!? Bid and sell for free at http://auctions.yahoo.com ---------- End of message ---------- From: Galindo Andrade Arturo To: "RATS Discussion List" Subject: Impulse response function for a ECM Date: Tue, 23 Nov 1999 11:26:11 -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; Content-Transfer-Encoding: quoted-printable Dear All, =BFDoes anyone know how to estimate impulse response functions for a = ECM using Malcolm? In advance thanks for any advice. Regards, Arturo Galindo ---------- End of message ---------- From: Javier Ord��ez To: "RATS Discussion List" Subject: Date: Thu, 25 Nov 1999 10:51:00 +0100 Errors-to: Reply-to: "RATS Discussion List" Sender: Maiser@efs1.efs.mq.edu.au X-listname: X-Mailer: Windows Eudora Light Version 3.0.1 (32) (via Mercury MTS (Bindery) v1.40) Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Dear Rats Users: Sorry for a simple question but...does anybody know how to estimate dynamic correlations between two variables? Thanks in advance Javi ---------- End of message ----------