tag:blogger.com,1999:blog-2198942534740642384.comments2015-07-31T09:14:56.829-07:00Econometrics Beat: Dave Giles' BlogDave Gileshttp://www.blogger.com/profile/05389606956062019445noreply@blogger.comBlogger2868125tag:blogger.com,1999:blog-2198942534740642384.post-31564222726043860672015-07-29T18:34:55.297-07:002015-07-29T18:34:55.297-07:00Yes, when the support is [0 , 1]. I've correct...Yes, when the support is [0 , 1]. I've corrected the expression for the fourth central moment. Thanks!Dave Gileshttp://www.blogger.com/profile/05389606956062019445noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-54342956256021052062015-07-29T11:45:29.405-07:002015-07-29T11:45:29.405-07:00Well said in understandable words. Thank you. Well said in understandable words. Thank you. Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-37964168812079181282015-07-29T08:46:02.817-07:002015-07-29T08:46:02.817-07:00Very useful page, thank you. I am just a bit confu...Very useful page, thank you. I am just a bit confused about the example using the uniform distribution. Isn't 9/5 the value of kurtosis in the uniform distribution?<br />Thank you.<br />ClaudioAnonymousnoreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-85326241930252688562015-07-27T23:32:00.670-07:002015-07-27T23:32:00.670-07:00De Luca, G., J. R. Magnus, and F. Peracchi, 2015 i...De Luca, G., J. R. Magnus, and F. Peracchi, 2015 is a really nice paper, thank you!vasjahttp://www.blogger.com/profile/00275279763749474696noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-21942691448718179382015-07-27T09:53:48.816-07:002015-07-27T09:53:48.816-07:00Niaz - please check directly with the EViews team....Niaz - please check directly with the EViews team.Dave Gileshttp://www.blogger.com/profile/05389606956062019445noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-25509250353860730462015-07-27T06:49:23.830-07:002015-07-27T06:49:23.830-07:00Dear Dave, thanks for your very usefull turtorials...Dear Dave, thanks for your very usefull turtorials.<br />I would ask you that, PMG in eviews9 doesnt support Hausman test for slope homogeneity, correct?<br />Best wishes<br />NiazUnknownhttp://www.blogger.com/profile/06662075294702926258noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-52231275157427047992015-07-23T13:31:27.650-07:002015-07-23T13:31:27.650-07:00That would be fine if you're really sure that ...That would be fine if you're really sure that there is just the one break. Keep in mind that the dummy variable is simply shifting the intercept in the model, so this give you the answer to your second question - you would treat the dummy variable in exactly the same way that treat the intercept. So, you would not be differencing/lagging it. If there is no cointegration, then a simple ARDL model (not the sort used for bounds testing) would provide a useful basis for examining short-run effects. For instance, see http://davegiles.blogspot.ca/2013/03/ardl-models-part-i.html . Finally, I don't have any posts on stochastic simulation - why not leave me a request on the "Readers' Forum" page and I'll see what I can do. If you use the "Search" on the blog page (right sidebar) you'll find a handful of posts on forecasting.Dave Gileshttp://www.blogger.com/profile/05389606956062019445noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-29145823126552127192015-07-23T13:23:08.015-07:002015-07-23T13:23:08.015-07:00Valerie: Yes, this often happens, perhaps not surp...Valerie: Yes, this often happens, perhaps not surprisingly because the IC are looking at the "fit" of the model (with a penalty for complexity), whereas autocorrelation may be arising because of incorrect functional form, etc. If this occurs, you often need to increase the max. lag length that's suggested by the IC. That's OK. The main thing is to be happy with the specification of the "base" model. It sounds as if you are referring to the TY procedure where you then add lags of the variables (but don't include these extra lags in the null hypothesis) when testing for Granger non-causality. Adding them is just a "trick" to ensure that the test statistic you're using has the usual asymptotic distribution. That being so, you don;t have to be so concerned about the AC etc. in the "final" model on which the testing is based.Dave Gileshttp://www.blogger.com/profile/05389606956062019445noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-70072088951899302012015-07-23T08:41:02.073-07:002015-07-23T08:41:02.073-07:00thank you.two final questions please. are there an...thank you.two final questions please. are there any scenario where the specified lag length chosen by the information criteria, does not still remove the problem of autocorrelation?if there is, are we allowed to increase the lag length ourselves? secondly, if the lag length chosen is e.g 7 and which solves the AC problem in the residuals + the AR condition,then estimating the var(7) in which case we include one extra lag (p+m, variables are all I(1)) when specifying the exogenous do we still have to check the AC and AR graph of the new specified model? just wondering. thanks ~ ValerieAnonymousnoreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-54581752634462110852015-07-23T08:20:13.078-07:002015-07-23T08:20:13.078-07:00There are 2 quite different things going on here, ...There are 2 quite different things going on here, One is testing for autocorrelation in the residuals of the model. The other is checking to see if the estimated coefficients of the VAR model imply a dynamically stable autoregressive structure. Unless the inverse roots of the characteristic equation associated with VAR lag structure are all inside the unit circle, the model is dynamically unstable - a shock to the model will just grow and grow. You wouldn't want to use a model with that feature.Dave Gileshttp://www.blogger.com/profile/05389606956062019445noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-81269204528232052632015-07-23T03:09:40.673-07:002015-07-23T03:09:40.673-07:00hi dave,
asthis is the most recent post you get to...hi dave,<br />asthis is the most recent post you get to reply, i have question concerning T-Y granger causality test in your previous post. Does the AR graph really matter? because when i estimated a VAR(4) model selected by the information criteria, there was no problem of Auto correlation but however the on AR graph,few of the points where outside the circle. when i estimated a var(3) all the points where inside but there was a problem on auto correlation...please what do you think is wrong? thanks...~valerieAnonymousnoreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-87836516260570013662015-07-22T20:27:23.187-07:002015-07-22T20:27:23.187-07:00HELLO,
Thanks for the great post. However i have a...HELLO,<br />Thanks for the great post. However i have a question, is it okay to include a dummy variable to capture a break the data for a long period of time say (20002Q1-2010Q4,if you have justification of an event that is likely to cause such break in the series) 2) when using a VAR (from your ARDL 2 POST) to obtain the lag of the dependent variable, are we to specify the dummy variable as an exogenous variable(in difference and in lagged level) as well? 3) what if i find no cointegration are there any conventional model to test the short run effect as Granger causality test only tells the direction of causality? lastly,(not related to this post) please do you have a post on stochatic simulation method of forecasting or any forecasting related post?i l really look forward to your reply. Thanks very many.Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-82667858241839348812015-07-22T16:35:41.214-07:002015-07-22T16:35:41.214-07:00Hello Professor Giles,I have found your posts and ...Hello Professor Giles,I have found your posts and blog very helpful in my self improvement.I am right now trying to model non linear cointegration and i understand i am to use the so called Threshold Cointegration proposed by Enders and Siklos (2001). It will be very kind and helpful of you to explain the threshold cointegration procedure in a step by step approach.I am trying to model pass-through effects of interest rates from monetary policy rate to lending rate.I must confess i know not how to even proceed on this.I am using monthly interest rates from january 2006 to April 2015.Regards and Thanks.Bala.Bala Yusufhttp://www.blogger.com/profile/14023226808928618005noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-17869417576860571092015-07-21T17:31:16.238-07:002015-07-21T17:31:16.238-07:00I suggest you post this in the EViews forum: http:...I suggest you post this in the EViews forum: http://forums.eviews.com/Dave Gileshttp://www.blogger.com/profile/05389606956062019445noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-84869481677860075902015-07-21T12:23:19.659-07:002015-07-21T12:23:19.659-07:00Dear Mr. Giles,
thanks a lot for your work here on...Dear Mr. Giles,<br />thanks a lot for your work here on the blog.<br /><br />I have a question regarding the second version of the ARDLbounds add-in for eviews 7:<br /><br />When selecting "No autocorrelation in Resids" as criterion, is column F, i.e. "P of Wald test" the appriopriate column to look at? And if so, is the Null no autocorrelation or autocorrelation?<br /><br />Thanks in advance, Philipp<br /><br />(I also asked Yashar Tarverdi, the writer of the add-in, per mail. I will post the answer here if he replies. I only thought that maybe you are faster :) )Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-18986102282009031252015-07-21T11:24:38.024-07:002015-07-21T11:24:38.024-07:00There`s nothing wrong with those negative values. ...There`s nothing wrong with those negative values. An unrestricted ecm is just a term to describe the particular form of the regression model being used - you won`t find a special option for it in EViews, or any other package.Dave Gileshttp://www.blogger.com/profile/05389606956062019445noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-73289103331294275982015-07-21T08:39:26.397-07:002015-07-21T08:39:26.397-07:00Yes - and you will have to allow for any I(1) vari...Yes - and you will have to allow for any I(1) variables.Dave Gileshttp://www.blogger.com/profile/05389606956062019445noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-34069211144050163482015-07-21T05:30:42.442-07:002015-07-21T05:30:42.442-07:00please sir, what happens if you find no co integra...please sir, what happens if you find no co integration?can you just estimate a short run relationship?Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-5551751175963685202015-07-21T05:12:22.847-07:002015-07-21T05:12:22.847-07:00dear prof, during my lag selection process i got n...dear prof, during my lag selection process i got negative numbers for SC AIC etc....and each of the criteria suggested 0 lag length...please what do you think is wrong as i am entirely confused :( thank you (p.s i am a beginner to using eviews) and lastly, where do we have the "unrestricted ECM" on eviews, i have only seen unrestricted VAR.Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-88281438646781753502015-07-20T11:04:11.649-07:002015-07-20T11:04:11.649-07:00Osman - no problem. They were good questions.Osman - no problem. They were good questions.Dave Gileshttp://www.blogger.com/profile/05389606956062019445noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-3023582578497115182015-07-20T11:03:00.292-07:002015-07-20T11:03:00.292-07:00Dear Dave,
Thank you for this instructive post.
O...Dear Dave,<br /><br />Thank you for this instructive post.<br />Osman.Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-42231874018311404422015-07-19T12:42:14.924-07:002015-07-19T12:42:14.924-07:00Use the B-P test.
See ; http://davegiles.blogsp...Use the B-P test. <br />See ; http://davegiles.blogspot.ca/2015/05/alternative-tests-for-serial.htmlDave Gileshttp://www.blogger.com/profile/05389606956062019445noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-88462371404461609432015-07-19T12:40:28.471-07:002015-07-19T12:40:28.471-07:00Andres - see these posts:
http://davegiles.blogs...Andres - see these posts: <br /><br />http://davegiles.blogspot.ca/2011/04/testing-for-granger-causality.html<br />http://davegiles.blogspot.ca/2011/10/var-or-vecm-when-testing-for-granger.html<br />http://davegiles.blogspot.ca/2012/04/surplus-lag-granger-causality-testing.html<br />Dave Gileshttp://www.blogger.com/profile/05389606956062019445noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-36252477104004125692015-07-19T12:31:08.035-07:002015-07-19T12:31:08.035-07:00I'd do some causality testing. Here's why....I'd do some causality testing. Here's why.<br />If there HAD BEEN cointegration, then there HAS to be Granger causality one way or the other. If there NO COINTEGRATION, then there may or may not be G-causality. It's worth testing for it.Dave Gileshttp://www.blogger.com/profile/05389606956062019445noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-7146176619659861002015-07-19T12:22:31.506-07:002015-07-19T12:22:31.506-07:00Aditya: Glad the post was helpful. For this situat...Aditya: Glad the post was helpful. For this situation, I agree that an ARDL is definitely appropriate. You definitely should include the differenced term on the right side, regardless of BIC. In the situation you suggest I'd use one lag (as long as the errors are serially independent - other wise additional lags, regardless of BIC.)Dave Gileshttp://www.blogger.com/profile/05389606956062019445noreply@blogger.com