You didn't like this one also? On 7/21/06, Talha Yalta <talhayalta(a)gmail.com&gt; wrote: -- A positive attitude may not solve all your problems, but it will annoy enough people to make it worth the effort. - Herm Allbright (1876-1944) --

Is this topic really necessary for the development of the gretl gui? ----- Original Message ----- From: Frederick Fagal To: Gretl list Sent: Saturday, July 22, 2006 11:53 PM Subject: Re: [Gretl-users] Re: Splash Screen Mark-II Lurker here...I think Talha needs some encouragement. I think a litttle splash screeen used SOMEWHERE can help Gretl. Good to have the acronym explained. Sex sells. In the old time radio forum old-timers are amazed that shiny radios sell for big bucks (refinished to be shinier than when new). Maybe place the full Gretl girl image in the background near the last crumb/bean. Maybe a smaller Hansel (from the rear) ahead of Gretl. Then have an info box near the bottom of the moon. Keep plugging away everyone. I used Gretl with a low level stat class a few years ago and it was very useful... Talha Yalta <talhayalta(a)gmail.com&gt; wrote: You didn't like this one also? On 7/21/06, Talha Yalta wrote: -- A positive attitude may not solve all your problems, but it will annoy enough people to make it worth the effort. - Herm Allbright (1876-1944) -- _______________________________________________ Gretl-users mailing list Gretl-users(a)ricardo.ecn.wfu.edu http://ricardo.ecn.wfu.edu/mailman/listinfo/gretl-users __________________________________________________ Do You Yahoo!? Tired of spam? Yahoo! Mail has the best spam protection around http://mail.yahoo.com ------------------------------------------------------------------------------ _______________________________________________ Gretl-users mailing list Gretl-users(a)ricardo.ecn.wfu.edu http://ricardo.ecn.wfu.edu/mailman/listinfo/gretl-users

Hi guys, I tried the Engle-Granger cointegration test but I noticed something. Here is my procedure: 1.I estimated a equatation in cointegration dialogue with the following variables l_CPI, l_REER, MMR and l_Y using 12 lags and got these results down. 2. These ADF tests for these variables are wright and the results are the same if you do ADF tests through main Gretl window using the same number of lags. 3.In step 5 we have the cointegration results and they are the same if you estimate a OLS model through main Gretl window. 4.In step 6 we have ADF tests for the residuals. Tests are without a constant. I tried to check the same test through main Gretl window using the same specification ie. I saved residuals from OLS regression (which I done through the main Gretl window) and tested with the ADF test without a constant. Here are the results: Step 6: Dickey-Fuller test on residuals Augmented Dickey-Fuller tests, order 12, for uhat sample size 86 unit-root null hypothesis: a = 1 test without constant estimated value of (a - 1): -0,333671 test statistic: t = -2,46579 asymptotic p-value 0,4903 Augmented Dickey-Fuller tests, order 12, for uhat sample size 86 unit-root null hypothesis: a = 1 test without constant model: (1 - L)y = (a-1)*y(-1) + ... + e estimated value of (a - 1): -0,333671 test statistic: t = -2,46579 asymptotic p-value 0,01324 Test statistics and estimated values, sample size are the same, but p-values are different? cointegration and from the second (from OLS saved residuals) that there is a cointegration relationship. Why is that? Did I make same mistaque in comparing? In addition I have some one suggestion. There sould be a possibility in E-G cointegration to have a possibility to do ADF tests-test down from maximal lag order or to have a possibility to see full ADF tests output in automatic E-G cointegration procedure. With unique lag order specification one can't decide which is the wright lag order. *********************************** Step 1: testing for a unit root in l_CPI Augmented Dickey-Fuller tests, order 12, for l_CPI sample size 86 unit-root null hypothesis: a = 1 test with constant estimated value of (a - 1): -0,0107669 test statistic: t = -1,2609 asymptotic p-value 0,6499 with constant and trend estimated value of (a - 1): -0,0838183 test statistic: t = -2,51286 asymptotic p-value 0,3218 with constant and quadratic trend estimated value of (a - 1): -0,111113 test statistic: t = -1,86159 asymptotic p-value 0,8653 Step 2: testing for a unit root in l_REER Augmented Dickey-Fuller tests, order 12, for l_REER sample size 86 unit-root null hypothesis: a = 1 test with constant estimated value of (a - 1): -0,0393688 test statistic: t = -1,28046 asymptotic p-value 0,641 with constant and trend estimated value of (a - 1): -0,244764 test statistic: t = -4,98476 asymptotic p-value 0,0001 with constant and quadratic trend estimated value of (a - 1): -0,132398 test statistic: t = -1,67802 asymptotic p-value 0,9135 Step 3: testing for a unit root in MMR Augmented Dickey-Fuller tests, order 12, for MMR sample size 86 unit-root null hypothesis: a = 1 test with constant estimated value of (a - 1): -0,0881019 test statistic: t = -1,97264 asymptotic p-value 0,2992 with constant and trend estimated value of (a - 1): -0,137154 test statistic: t = -2,13296 asymptotic p-value 0,5267 with constant and quadratic trend estimated value of (a - 1): -0,263064 test statistic: t = -2,29448 asymptotic p-value 0,6817 Step 4: testing for a unit root in l_Y Augmented Dickey-Fuller tests, order 12, for l_Y sample size 86 unit-root null hypothesis: a = 1 test with constant estimated value of (a - 1): 0,0899723 test statistic: t = 1,56751 asymptotic p-value 0,9995 with constant and trend estimated value of (a - 1): -1,13912 test statistic: t = -3,52897 asymptotic p-value 0,0363 with constant and quadratic trend estimated value of (a - 1): -1,06705 test statistic: t = -2,83268 asymptotic p-value 0,3813 Step 5: cointegrating regression Cointegrating regression - OLS estimates using the 99 observations 1998:01-2006:03 Dependent variable: l_CPI VARIABLE COEFFICIENT STDERROR T STAT P-VALUE const 5,03993 0,562006 8,968 <0,00001 *** l_REER -0,305748 0,0911986 -3,353 0,00115 *** MMR -0,0121330 0,00102131 -11,880 <0,00001 *** l_Y 0,225401 0,0419834 5,369 <0,00001 *** Unadjusted R-squared = 0,845111 Adjusted R-squared = 0,840219 Durbin-Watson statistic = 0,633496 First-order autocorrelation coeff. = 0,668083 Step 6: Dickey-Fuller test on residuals Augmented Dickey-Fuller tests, order 12, for uhat sample size 86 unit-root null hypothesis: a = 1 test without constant estimated value of (a - 1): -0,333671 test statistic: t = -2,46579 asymptotic p-value 0,4903 P-values based on MacKinnon (JAE, 1996) There is evidence for a cointegrating relationship if: (a) The unit-root hypothesis is not rejected for the individual variables. (b) The unit-root hypothesis is rejected for the residuals (uhat) from the cointegrating regression. Augmented Dickey-Fuller tests, order 12, for uhat sample size 86 unit-root null hypothesis: a = 1 test without constant model: (1 - L)y = (a-1)*y(-1) + ... + e estimated value of (a - 1): -0,333671 test statistic: t = -2,46579 asymptotic p-value 0,01324 P-values based on MacKinnon (JAE, 1996) _________________________________________________________________ Windows Live™ Messenger has arrived. Click here to download it for free! http://imagine-msn.com/messenger/launch80/?locale=en-gb

Ok, but.... All ADF tests on individual variables are right ie. thay are the same when calculating from EG ADF tests and ADF tests from the main gretl window, except for the residuals. Only ADF tests for the residuals are different. You mean that there is a difference in distribution only for the residuals? (coefficients are the same in EG and OLS) _________________________________________________________________ Windows Live™ Messenger has arrived. Click here to download it for free! http://imagine-msn.com/messenger/launch80/?locale=en-gb

On Mon, 24 Jul 2006, john w wrote: Please take a look at MacKinnon's 1996 article. The distributions, and hence the p-values, are *not* the same in the two cases of (a) a "stand-alone" ADF test on a single time-series and (b) an EG test based on the residuals from a cointegrating regression. In the latter case the distribution of what MacKinnon calls the tau statistic depends on the number of (possibly) cointegrated variables. Allin Cottrell

Shouldn't one look at AIC and BIC for this one? john w <johnw2006(a)hotmail.com&gt; wrote: Thnx Sven and Allin, Now I have another question related to EG cointegration in gretl. How do I know which is the optimal lag order in EG coint test? Thanx _________________________________________________________________ Windows Live� Messenger has arrived. Click here to download it for free! http://imagine-msn.com/messenger/launch80/?locale=en-gb _______________________________________________ Gretl-users mailing list Gretl-users(a)ricardo.ecn.wfu.edu http://ricardo.ecn.wfu.edu/mailman/listinfo/gretl-users --------------------------------- Yahoo! Music Unlimited - Access over 1 million songs.Try it free.

Thnx again Allin, I think that skip function is not working... When this option is checked then initial variable DF testing should be excluded. Right? But now isn't. _________________________________________________________________ Be the first to hear what's new at MSN - sign up to our free newsletters! http://www.msn.co.uk/newsletters

On Tue, 25 Jul 2006, john w wrote: Yes. I've now checked, and it seems that X-12-ARIMA only supports monthly or quarterly series. I'll have to disable the menu item for other data frequencies. Allin.

On Tue, 25 Jul 2006, john w wrote: There is now a new Windows snapshot in place, with a few more Engle-Granger refinements. Allin.

Can I make a brief comment on this debate. A residual based test for cointegration is base on the residuals from a cointegrating regression. Depending on whether the variables in the cointegrating regression have non zero drifts on should include a constants or a trend in the cointegration. If this is done properly there is no need to include a constant or a trend in the cointegrating regression. The ADF statistic may, however, depend to some extent on the inclusion of a constant or a trend in the original cointegrating regression. Can I recommend the account in Hayashi , F (2000), Econometrics, Princeton University Press. John C Frain Economics Department Trinity College Dublin Dublin 2 On 26/07/06, john w <johnw2006(a)hotmail.com&gt; wrote: -- John C Frain

Sorry that my previous email was done in such a hurry. I think that you have understood me perfectly. GRETL was already consistent with what I said. John C Frain Economics Department Trinity College Dublin On 26/07/06, Allin Cottrell <cottrell(a)wfu.edu&gt; wrote: -- John C Frain

On Tue, 25 Jul 2006, Sven Schreiber wrote: Thanks. It's not covered at present, for Engle-Granger (though it is in the Johansen test). Yes, it should be there for completeness. Allin.

On Sun, Jul 23, 2006 at 10:17:30AM +0200, Riccardo Jack Lucchetti wrote: I agree. I agree, also about the excessive "coldness" of the current proposal (long live the little girl! :-), but I realise that it's just a matter of personal opinion, and I don't want Talha to feel let down, I appreciate his goodwill. Cri -- GPG/PGP Key-Id 0x943A5F0E - http://www.linux.it/~cri/cri.asc Free software, free society - http://www.fsfeurope.org

Thanks very much for the encouragement but I see that they have their minds set on the existing image, at least for now. I thought this is one thing that I could do to help and I did it. I also agree that this discussion is unnecessarily long now. So I will just a make a few final comments of my own: 1- I strongly disagree with the logic that: no-one is making money out of gretl -> we don't have to SELL gretl -> gretl has no need to "look professional". However, I strongly agree that: The thing is, most people still don't know about GPL and other technical merits of gretl. When I show my bleeding edge xgl/compiz enabled linux desktop to people, the reaction I get is "And all this is free???". They cannot yet grasp the underlying philosophy. Similarly, people that I show gretl has the impression that it looks basic and amateurish, even though it is quite the contrary. First impressions are important. 2- This is why I proposed a more professional looking splash screen. The keyword here is "more professional". I am not a professional graphic designer in the sense that I never got paid for doing any graphic design. However, I did a few things and I consider myself better than most people. The problem with the existing image is that it is ripped from a web log. There is no copyright info there because that is in turn ripped from a children's tale book probably. Consequently, I thought an original design would be an improvement over what was already there. 3- The second design is not a splash screen. It is intended as an "about" screen as Allin proposed a few days ago. This is why it is bigger and more square-like. 4- I really admire all the work you are putting into this project. Allin and Jack and the other guys involved is a source of inspiration. Of course it is your right to have the final saying over all issues. I don't feel let down or disappointed. Really :) I did something I knew I could do, so I did it. If you find a use of it, feel free to use any of the two designs but this is it from me for now. As I have more time available in the near future, I would like to continue to make some small contributions to the project. Maybe I can help with localization or ducumentation. Have a great day... Talha (I cannot say anything about the quality of code, but being written in C and all the attention to detail, it must be very good) 1- The second one