tag:blogger.com,1999:blog-2198942534740642384.comments2014-08-21T14:25:03.593-07:00Econometrics Beat: Dave Giles' BlogDave Gileshttp://www.blogger.com/profile/05389606956062019445noreply@blogger.comBlogger2357125tag:blogger.com,1999:blog-2198942534740642384.post-72249263236975817852014-08-21T14:25:03.593-07:002014-08-21T14:25:03.593-07:00Yes, you can.Yes, you can.Dave Gileshttp://www.blogger.com/profile/05389606956062019445noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-27793500277524970542014-08-21T14:24:05.191-07:002014-08-21T14:24:05.191-07:00Professor Giles, I use the Schwartz-Bayesian infor...Professor Giles, I use the Schwartz-Bayesian information criterion to choose among different lag structures for models with trend, and then separately for models without trend. How, then, do I choose between these two models, especially if they select different lag lengths? Can I use SBC/AIC values to choose between models with and without trend?Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-73193266862241185162014-08-21T08:05:36.740-07:002014-08-21T08:05:36.740-07:00No - there is something wrong with what you have d...No - there is something wrong with what you have done.Dave Gileshttp://www.blogger.com/profile/05389606956062019445noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-73543962101136045932014-08-21T03:59:19.165-07:002014-08-21T03:59:19.165-07:00Prof Giles,
I have created the CV for my own dat...Prof Giles, <br /><br />I have created the CV for my own dataset. However, te results of the Hl(r) cointegration tests are somewhat weird. <br /><br />The CV for Hl(r) are for Zero coint eq 55.419, at most one coint eq 80.082 and at most two coint eq 55.419. Is it possible to have these types of CV values that go up and down? Any light on this matter will be highly appreciatedAnonymousnoreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-63234569492671906452014-08-19T13:44:50.786-07:002014-08-19T13:44:50.786-07:00Thanks a million for the response, much appreciate...Thanks a million for the response, much appreciated. Stevehttp://www.blogger.com/profile/04944872621902471586noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-19704252998322124122014-08-18T09:56:32.301-07:002014-08-18T09:56:32.301-07:00Steve. You can;t use the bounds test if any of you...Steve. You can;t use the bounds test if any of your variables are I(2). That's explicit in the original Pesaran papers and in my post. Some of the references in this earlier post may be helpful to you:<br />http://davegiles.blogspot.ca/2012/01/cointegration-analysis-with-i2-i1-data.htmlDave Gileshttp://www.blogger.com/profile/05389606956062019445noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-78076074251376314602014-08-18T01:37:24.226-07:002014-08-18T01:37:24.226-07:00Hi Professor Giles,
I've been trying to inve...Hi Professor Giles, <br /><br />I've been trying to investigate a possible cointegrating relationship between G and GDP and am having some trouble. After unit root tests taking into account two structural breaks it seems both series are I(2). There is some weak evidence of I(1) but most derivations as regards lags and the addition/deletion of a trend etc are giving I(2). I've completed the bounds procedure described but am wondering, given that I have structural breaks, and am dealing in all honesty with I(2) variables, what's the best approach to take from here?<br /><br />Thanks a lotStevehttp://www.blogger.com/profile/04944872621902471586noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-10900103456705477802014-08-17T08:05:25.566-07:002014-08-17T08:05:25.566-07:00Yes - this type of testing was discussed in Johans...Yes - this type of testing was discussed in Johansen's original 1988 paper, as well as in several subsequent papers by Johansen and Juselius (among others). You can see an application in their 1992 paper, in the Oxford Bulletin of Economics & Statistics) involving the demand for money. For a good overview of this type of testing, see: http://www.nuff.ox.ac.uk/economics/papers/2003/w10/BoswijkDoornik.pdf<br />I'll try to do a post on this at some stage.Dave Gileshttp://www.blogger.com/profile/05389606956062019445noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-56615690660497869852014-08-17T03:38:48.869-07:002014-08-17T03:38:48.869-07:00Dear Prof,
Have you heard about exclusion test, w...Dear Prof,<br /><br />Have you heard about exclusion test, which to be done after we found there is a cointegrating vector using Johansen procedure, to see which variable(s) do not participated in the cointegrating space? If yes, do not know how to run it? Thanks.Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-35997657341979286062014-08-16T22:07:21.473-07:002014-08-16T22:07:21.473-07:00My advisor often used to speak of some sort of &qu...My advisor often used to speak of some sort of "matrix inversion machine" from the pre modern computer days. Whenever he mentioned it he would make a motion with his hand like he was pulling a lever. Something like this is more or less exactly what I imagined.Jamesnoreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-3710961171939427562014-08-12T16:26:12.964-07:002014-08-12T16:26:12.964-07:00Yes, you can.Yes, you can.Dave Gileshttp://www.blogger.com/profile/05389606956062019445noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-71749023617773736742014-08-12T05:31:32.938-07:002014-08-12T05:31:32.938-07:00Dear Author, thank you for a practical description...Dear Author, thank you for a practical description of the modelling. I've been using ARDL method to test for cointegration between certain macroeconomic variables. The results exceed the upper bound both in F-statistic and in t-statistic of the lagged dependent variable. <br /><br />However, when I estimate the unrestricted ECM the coefficient of the ECM(-1) is significant, but the rest of the coefficients are not anymore. How should I take the result? Can I still claim that there's cointegration between variables?<br /><br />Thank you!<br />Best,<br />GeorgeGeorge Lapinlampinoreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-34521860776754895772014-08-11T20:55:56.727-07:002014-08-11T20:55:56.727-07:00Thanks, Professor.
Arun
IndiaThanks, Professor.<br />Arun<br />IndiaAVKhttp://www.blogger.com/profile/10129288260054638126noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-12687386022718586812014-08-09T09:27:01.057-07:002014-08-09T09:27:01.057-07:00Thanks very much for this reference.Thanks very much for this reference.Dave Gileshttp://www.blogger.com/profile/05389606956062019445noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-39211920856813732122014-08-09T09:25:48.623-07:002014-08-09T09:25:48.623-07:00Thanks - I'll be interested to check this out....Thanks - I'll be interested to check this out.Dave Gileshttp://www.blogger.com/profile/05389606956062019445noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-53772811121191537392014-08-09T09:19:59.369-07:002014-08-09T09:19:59.369-07:00Hendry and Krolzig (2005) showed that their improv...Hendry and Krolzig (2005) showed that their improved Gets algorithms with bias correction can overcome the biases you noted. I'd be curious if you have any reactions to that particular work/program.<br /><br />http://onlinelibrary.wiley.com/doi/10.1111/j.0013-0133.2005.00979.x/abstract?systemMessage=Wiley+Online+Library+will+be+disrupted+9th+Aug+from+10-2+BST+for+essential+maintenance.+Pay+Per+View+will+be+unavailable+from+10-6+BST.&userIsAuthenticated=false&deniedAccessCustomisedMessage=Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-90068969243775018872014-08-09T04:40:55.013-07:002014-08-09T04:40:55.013-07:00Very good blog entry. "FEVD" was used fa...Very good blog entry. "FEVD" was used far too often in empirical political analysis without questioning the underlying fundamentals.<br /><br />You might also be interested in a paper that discusses time-invariant regressors in a dynamic panel data setup:<br />http://papers.ssrn.com/sol3/papers.cfm?abstract_id=2386572Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-88199758678060088462014-08-08T03:30:57.659-07:002014-08-08T03:30:57.659-07:00Thanks for the summary. I also wrote a summary and...Thanks for the summary. I also wrote a summary and included some personal thoughts at http://blogs.sas.com/content/iml/2014/08/05/stiglers-seven-pillars-of-statistical-wisdom/Rick Wicklinhttp://www.blogger.com/profile/13919716786757842151noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-50938040964366681982014-08-07T08:26:12.367-07:002014-08-07T08:26:12.367-07:00You were right, I couldn't resist the title. B...You were right, I couldn't resist the title. But I also can't think of any examples of what you're talking about. I'm surprised that the applied model would be the <i>less</i> nuanced, since case-specific details are available.isomorphismeshttp://isomorphism.esnoreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-19808188679045532312014-08-07T05:10:37.008-07:002014-08-07T05:10:37.008-07:00Sir if we want to check the long run and short run...Sir if we want to check the long run and short run relationship between two variables by ARDL Approach then can we use control variables? if yes then how? will those variables be treated as exogenous variables?Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-14426447485053435282014-08-06T14:49:35.997-07:002014-08-06T14:49:35.997-07:001. No idea.
2. No idea.
3. Yes.
1. No idea.<br />2. No idea.<br />3. Yes.<br />Dave Gileshttp://www.blogger.com/profile/05389606956062019445noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-23748917458650038452014-08-06T03:17:10.803-07:002014-08-06T03:17:10.803-07:00Hello Prof
I really do appreciate your painstaking...Hello Prof<br />I really do appreciate your painstaking effort in analysing causality test. Your blog is simply educating. I'm your core fan here and I have been reading most of the articles which do help me appreciate statistics and econometrics better. I have few questions which I will be glad to have the answers promptly.<br />1. How can we carry out Markov switching Granger causality test with eviews 7?<br />2. What is the difference between using dummies to account for structural breaks and using Markov switching Granger causality test?<br />3. Can dummies be used for regime switching in Granger causality test?<br />Thanks in anticipation of your prompt response.<br />Nsisong Ekong(Nigeria)Nsisong Ekonghttp://www.blogger.com/profile/01283821808046029664noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-56397627480312449482014-08-06T00:28:51.767-07:002014-08-06T00:28:51.767-07:00A 2013 version of the paper can be found here:
htt...A 2013 version of the paper can be found here:<br />http://statweb.stanford.edu/~ckirby/brad/papers/2013ModelSelection.pdf<br />Eric de Souzanoreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-1436017700170712632014-08-04T15:05:38.786-07:002014-08-04T15:05:38.786-07:00You just enter them as additional "exogenous ...You just enter them as additional "exogenous variables" and they won't be included in the Granger causality test.Dave Gileshttp://www.blogger.com/profile/05389606956062019445noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-40970819529414136642014-08-04T08:24:48.725-07:002014-08-04T08:24:48.725-07:00Dear sir, i want to investigate the causal relatio...Dear sir, i want to investigate the causal relationship bt/w two time series apart from my independent and dependent variables i have to use some control variables also but have no idea how to use them in granger causality test is there any other method through which i also include my control variables.Wais Shirzaihttp://www.blogger.com/profile/08241151225720575221noreply@blogger.com