tag:blogger.com,1999:blog-2198942534740642384.comments2015-09-03T00:05:21.075-07:00Econometrics Beat: Dave Giles' BlogDave Gileshttp://www.blogger.com/profile/05389606956062019445noreply@blogger.comBlogger2961125tag:blogger.com,1999:blog-2198942534740642384.post-83723735083983319032015-09-02T12:19:17.225-07:002015-09-02T12:19:17.225-07:00I´m sure that the gain is affected, but the phase ...I´m sure that the gain is affected, but the phase I don´t know. I am tempted to think that the phase is affected as in the moving average filter.Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-53246440161848547132015-09-02T10:12:55.385-07:002015-09-02T10:12:55.385-07:00Nicolas - Both, I believe.
DNicolas - Both, I believe.<br /><br />DDave Gileshttp://www.blogger.com/profile/05389606956062019445noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-76858888374864851782015-09-02T10:06:46.748-07:002015-09-02T10:06:46.748-07:00Hi Dave,
Regarding to the post the H-P filter and...Hi Dave,<br /><br />Regarding to the post the H-P filter and unit roots, when you stated that Cogley and Nason (1995) and Phillips and Jin (2015) mention that the filter can generate spurious cycles are in terms of gain, right? i.e. from the frequency domain perspective the relative contribution of each frequency. Or in terms of phase?, the position of the series with respect to the time axis or both.<br /><br />Thanks for the excellent post. <br /><br />NicolasR.<br />Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-35836183852645470652015-09-02T09:04:22.030-07:002015-09-02T09:04:22.030-07:00I suggest you address this to the EViews forum.I suggest you address this to the EViews forum.Dave Gileshttp://www.blogger.com/profile/05389606956062019445noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-8599322879557388332015-09-02T08:52:12.437-07:002015-09-02T08:52:12.437-07:00Good Day
With respect to the direction of influenc...Good Day<br />With respect to the direction of influence, I am not certain how this should be interpreted. Apart from referring to theory, how should the signs be interpreted out of Eviews9.<br /><br />My confusion stems from the fact that in Johanson Test result in eviews8 the signs in the cointegration equation were swapped i.e. if they were -ve they were to be interpreted as +ve. <br /><br />My Eviews9 ARDL results are below<br /><br />Cointeq = GVT_BONDS – (-0.2733*GDP__ + 0.9637*CPI__ -1.7030<br /> *CA_GDP__ + 0.3897*BD_GDP__ -0.1901*LEADING_INDICATOR<br /> -0.0006*NET_BORROWING + 0.0001*NET_PURCHASES + 20.9160 )<br /><br />Variable Coefficient Prob.<br /> GDP__ -0.273306 0.2663<br /> CPI__ 0.963655 0.0049<br /> CA_GDP__ -1.702984 0.0042<br /> BD_GDP__ 0.389691 0.2213<br /> LEADING_INDICATOR -0.190125 0.0001<br /> NET_BORROWING -0.000605 0.0027<br /> NET_PURCHASES 0.000053 0.8282<br /> C 20.915959 0.0000<br />Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-58240655108747698392015-09-01T12:00:32.886-07:002015-09-01T12:00:32.886-07:00Or use TY if you want to analyze the relatioship i...Or use TY if you want to analyze the relatioship in term of G causality.<br />http://davegiles.blogspot.com/2011/04/testing-for-granger-causality.htmlAnonymousnoreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-12935380858978265522015-09-01T10:11:01.920-07:002015-09-01T10:11:01.920-07:00No, you don't.No, you don't.Dave Gileshttp://www.blogger.com/profile/05389606956062019445noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-10659158557905717842015-09-01T08:52:58.697-07:002015-09-01T08:52:58.697-07:00Dear professor before I estimate the ardl should I...Dear professor before I estimate the ardl should I have to perform the causality test? if the answer is yes, then how should I proceed if I have some variables that are I(1) and some I(0), because I know can estimate the ardl with different integrated series, but I cannot perform the causality test. ThanksAnonymousnoreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-34864086057638396742015-08-30T14:59:33.323-07:002015-08-30T14:59:33.323-07:00This is extremely helpful, very clear explaination...This is extremely helpful, very clear explaination. Thank you very much!Nguyễn Minh Nguyênhttp://www.blogger.com/profile/13087195881394834732noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-78507859626680139222015-08-29T07:25:45.712-07:002015-08-29T07:25:45.712-07:00Abdul - assuming that you have an intercept in you...Abdul - assuming that you have an intercept in your model, you will need to construct THREE (not four) dummy variables. You mustn't follow the other procedure - if you do, you're IMPOSING the relative impacts of the different regimes in advance. <br /><br />Most people would just use OLS. If it's the ratio aspect that bothers you, you can run a Beta regression - see http://davegiles.blogspot.ca/2013/07/allocation-models-with-bounded.htmlDave Gileshttp://www.blogger.com/profile/05389606956062019445noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-18471962843729070262015-08-29T07:16:40.309-07:002015-08-29T07:16:40.309-07:00That's analagous to the "unit root" ...That's analagous to the "unit root" case, and has the same adverse implications. The system isn't stationary.Dave Gileshttp://www.blogger.com/profile/05389606956062019445noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-4794043366700802015-08-29T03:48:13.980-07:002015-08-29T03:48:13.980-07:00Dear Prof Giles
Nice blog Sir, My question is rega...Dear Prof Giles<br />Nice blog Sir, My question is regarding the Image of Inverse roots of AR characteristics of Polynomials. As on of the observation is just on the boundary of circle. Could we consider this system stable enough to proceed further Faisal Sherhttp://www.blogger.com/profile/16355528359488434880noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-4763313187262000722015-08-29T00:35:46.975-07:002015-08-29T00:35:46.975-07:00Professor thanks for sharing these valuable inform...Professor thanks for sharing these valuable information. i have quick question.<br />i have a ownership variables which has four different kind of values. <br />1) no major shareholder<br />2) having 25% share<br />3) having 50% indirect ownership<br />4) having more than 50% direct ownership<br />how should i make the dummy variables ?<br />1) create four dummy variables with 0 and 1?<br />or <br />2) put 1 -4 in a single variable ranging between 1-4 and run the regression?<br /><br />NEXT <br />i need to know which regression is best suited for these as they are my independent variable and dependent variable is a a ratio (return on average equity). <br />thanks a lot <br />Abdul Qayyumhttp://www.blogger.com/profile/07183932286991010273noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-33133308138928450722015-08-27T10:47:33.875-07:002015-08-27T10:47:33.875-07:00Denzil - thanks for the thoughtful comments - and ...Denzil - thanks for the thoughtful comments - and the references! D.Dave Gileshttp://www.blogger.com/profile/05389606956062019445noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-19965490453217262932015-08-27T10:45:17.187-07:002015-08-27T10:45:17.187-07:00Thanks - typo! Fixed now.Thanks - typo! Fixed now.Dave Gileshttp://www.blogger.com/profile/05389606956062019445noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-43141333678371977362015-08-27T07:21:10.725-07:002015-08-27T07:21:10.725-07:00Maybe I'm just confused ( ianae) but in the li...Maybe I'm just confused ( ianae) but in the lin-log case isn't the coefficient beta / xi? That doesn't change the conclusion though.Unknownhttp://www.blogger.com/profile/14194210589133048249noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-59469839866363403122015-08-27T06:26:08.139-07:002015-08-27T06:26:08.139-07:00David,
As always I enjoy your posts.
This partic...David,<br />As always I enjoy your posts.<br /> <br />This particular topic is one that has long been of interest to me. Ron Bewley and I did some work on your second example of estimating long-run responses in dynamic models (Bewley and Fiebig, 1990). More recently I have revisited the problem in yet another context. This time with discrete choice models where coefficient estimates by themselves are typically not of interest and analysts often estimate ratios of parameters to produce Marginal Rates of Substitution and in particular marginal willingness to pay (WTP) where the parameter in the denominator relates to price or cost. <br /><br />This literature has moved to greater use of random coefficient models such as mixed logit (McFadden and Train, 2000) and extensions (Fiebig et al., 2010). In the case of normally distributed random coefficients and where WTP is the focus you now have a case where the true, as distinct from estimated, object of interest is a ratio of normals. Because of the non-existence of moments problem, advice is often given that the price coefficient should be specified as a fixed rather than random parameter in order to avoid the problem. Having gone ahead and estimated WTP from such a specification, analysts then typically estimate WTP ignoring the reoccurrence of the problem they initially sought to resolve! <br /><br />As is often the case, convenience is not necessarily a good objective in specifying an econometric model and so I’ve never been convinced by the advice to leave price with a fixed parameter. Why shouldn’t there be heterogeneity in how people respond to price? In Bartels et al. (2006) we do in fact allow for random coefficients on price and then we essentially use the Hinkley (1969) work to argue that what we have is reasonable for our example. Simulation evidence provided by Meijer and Rousendal (2006) supports such an approach and specifically recommend against treating the cost coefficient as fixed rather than random. <br /><br />Daly et al. (2011) stress that the non-existence of moments problem is not confined to cases where normality of the cost parameter is assumed. They also point out the risks of simulating from these distributions and inferring incorrectly that the moments exist. <br /><br />References<br />Bartels, R., Fiebig, D.G. and van Soest, A. (2006), “Consumers and experts: An econometric analysis of the demand for water heaters”, Empirical Economics, 31, 369–391.<br />Bewley, R. and Fiebig, D.G. (1990), “Why are long-run parameter estimates so disparate?” The Review of Economics and Statistics, 72(2), 345-349.<br />Daly, A., Hess, S. and Train, K., (2011), “Assuring Finite Moments for Willingness to Pay in Random Coefficient Models”, Transportation, 39(1), 19-31.<br />Fiebig, D.G., Keane, M., Louviere, J.J., Wasi, N., (2010), “The generalized multinomial logit: accounting for scale and coefficient heterogeneity”, Marketing Science, 29(3), 393–421.<br />McFadden, D. and Train, K., (2000), “Mixed MNL models for discrete response”, Journal of Applied Econometrics 15(5), 447–470.<br />Meijer, E. and Rouwendal, J., (2006), “Measuring welfare effects in models with random coefficients”, Journal of Applied Econometrics 21(1), 227-244.<br />Denzilhttps://www.business.unsw.edu.au/our-people/denzilfiebignoreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-3774013062584206032015-08-26T12:16:54.640-07:002015-08-26T12:16:54.640-07:00Sal - option (2), for reasons given in the origina...Sal - option (2), for reasons given in the original paper.Dave Gileshttp://www.blogger.com/profile/05389606956062019445noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-56036137771088468622015-08-26T12:03:13.143-07:002015-08-26T12:03:13.143-07:00Dear Prof.
If I have, for example, five variables...Dear Prof. <br />If I have, for example, five variables. The null hypothesis of no-cointegration would be H0: α1=α2=α3=α4=α5=0. What is the correct form for the alternative hypothesis of cointegration? Is it <br /> 1) (α1≠α2≠α3≠α4≠α5≠0), or <br /> 2) At least one the α's is not zero, or<br /> 3) α1≠0, α2≠0, α3≠0, α4≠0, α5≠0, or<br /> 4) Some other form<br /><br />Could you also please explain. <br /><br />Thanks<br /><br />Sal<br />ahmed Nusairhttp://www.blogger.com/profile/04468745555328997554noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-6927017229498283482015-08-25T07:30:31.044-07:002015-08-25T07:30:31.044-07:00Thanks! Fixed! And bonus marks for reading to the ...Thanks! Fixed! And bonus marks for reading to the end!Dave Gileshttp://www.blogger.com/profile/05389606956062019445noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-4357939398091359812015-08-25T07:26:49.961-07:002015-08-25T07:26:49.961-07:00The ARDL bounds testing requires that no variables...The ARDL bounds testing requires that no variables be I(2), whether or not there are breaks.Dave Gileshttp://www.blogger.com/profile/05389606956062019445noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-89420848585702475102015-08-25T06:38:55.329-07:002015-08-25T06:38:55.329-07:00Dear Professor,
Is it not necessary to check tha...Dear Professor, <br /><br />Is it not necessary to check that the underlying variables are not I(2) when structural breaks are present?Seyihttp://www.blogger.com/profile/02526123681802992008noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-22784933769640710352015-08-25T04:43:30.848-07:002015-08-25T04:43:30.848-07:00"The bottom line -
Just because your choice o...<i>"The bottom line -<br />Just because your choice of estimator ensures "good" properties for the"</i><br /><br />Sentence fragment alert! Sentence fragment alert!<br />And a fragment that it is difficult for the reader to make sense of...marcel proustnoreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-15717167046015000662015-08-23T16:05:49.921-07:002015-08-23T16:05:49.921-07:00Thank you, professor. You are 100% awesome!Thank you, professor. You are 100% awesome!JJhttp://www.blogger.com/profile/18031970964590382017noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-68689625402163050802015-08-23T16:05:37.433-07:002015-08-23T16:05:37.433-07:00Here are a couple of references that may help you:...Here are a couple of references that may help you:<br />http://www.aebrjournal.org/uploads/6/6/2/2/6622240/paper_2.pdf<br /><br />https://www.researchgate.net/publication/227347359_Testing_for_Granger_causality_in_heterogeneous_mixed_panelsDave Gileshttp://www.blogger.com/profile/05389606956062019445noreply@blogger.com