tag:blogger.com,1999:blog-2198942534740642384.comments2018-04-21T15:12:25.621-07:00Econometrics Beat: Dave Giles' BlogDave Gileshttp://www.blogger.com/profile/05389606956062019445noreply@blogger.comBlogger3904125tag:blogger.com,1999:blog-2198942534740642384.post-7776713601460276672018-04-21T15:12:25.621-07:002018-04-21T15:12:25.621-07:00If all of your series have been transformed approp...If all of your series have been transformed appropriately to make them stationary, then the 2SLS estimator will be consistent.Dave Gileshttps://www.blogger.com/profile/05389606956062019445noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-43270320029831411882018-04-21T12:42:06.503-07:002018-04-21T12:42:06.503-07:00Thanks for your prompt reply. After transformation...Thanks for your prompt reply. After transformation, all of my variables are stationary at first difference with constant. is 2SLS correct to use now?Najia Mughalhttps://www.blogger.com/profile/17566253642073390422noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-56404896285251111282018-04-18T13:36:35.779-07:002018-04-18T13:36:35.779-07:00For 2SLS to be consistent, all of the data need to...For 2SLS to be consistent, all of the data need to be stationary - so, you will have to transform your variables before applying 2SLS.Dave Gileshttps://www.blogger.com/profile/05389606956062019445noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-62239826225417496972018-04-18T13:10:45.106-07:002018-04-18T13:10:45.106-07:00Hello Sir,
Thanks alot for writing such a useful p...Hello Sir,<br />Thanks alot for writing such a useful post. Howevr, i have a question about the stationarity of the time series. I am trying to estimate an equation in which dependent variable is stationary at 2nd difference while all other variables are stationary at level or 1st difference. Will it be appropriate to use 2SLS on such data? if not, which technique should i move towards.<br />Najia Mughalhttps://www.blogger.com/profile/17566253642073390422noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-14903090633612920132018-04-14T12:00:41.640-07:002018-04-14T12:00:41.640-07:00Very thorough and clear, can you please talk more ...Very thorough and clear, can you please talk more about dynamic stability, I think that all stable processes are stationary, but vice-versa is not true.Amrendra Singhhttps://www.blogger.com/profile/08642319242703680042noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-22204432571862505402018-04-07T07:13:03.062-07:002018-04-07T07:13:03.062-07:00Sean - I had a lot of posts in 2013 - which one, s...Sean - I had a lot of posts in 2013 - which one, specifically, are you referring to?Dave Gileshttps://www.blogger.com/profile/05389606956062019445noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-70063347087553244022018-04-06T16:30:52.641-07:002018-04-06T16:30:52.641-07:00Hi Dave,
I have read your previous post in 2013 r...Hi Dave,<br /><br />I have read your previous post in 2013 regarding how you "tricked" eviews into generating multiple lags in order to choose the maximum lag. However, I have tried to replicate your method on eviews 10 and it did not work out. Can you give me some advice on this issue. Thanks!<br /><br />By the way, I am new to eviews.Seannoreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-82984622044466609332018-04-04T13:32:02.003-07:002018-04-04T13:32:02.003-07:00Ivan - there could be all sorts of reasons. For in...Ivan - there could be all sorts of reasons. For instance: 1. Inappropriate choices of lag lengths in the ARDL model; 2. Same problem in the ECM; 3. Autocorrelation in errors of one or other of the 2 models; 4. Existence of unit roots at the seasonal frequencies (if, for instance, you are using quarterly or monthly data).Dave Gileshttps://www.blogger.com/profile/05389606956062019445noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-87316213662193873852018-04-04T12:10:06.654-07:002018-04-04T12:10:06.654-07:00Informative and useful!! It is pleasure to read su...Informative and useful!! It is pleasure to read such scientific masterpieces.Benyhttps://www.blogger.com/profile/13109569218146019654noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-26746969999785354412018-04-04T09:22:43.793-07:002018-04-04T09:22:43.793-07:00Great post, thanks a lot! More useful than much of...Great post, thanks a lot! More useful than much of my classesRafael Cattanhttps://www.blogger.com/profile/14094572834400556505noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-23225559008542655462018-04-04T01:18:01.051-07:002018-04-04T01:18:01.051-07:00Dear professor, I am using the Pesaran approach an...Dear professor, I am using the Pesaran approach and the general one to ECM I would like to know and I don't understand why I get a non significant Bound test in the former but a very significant and negative ECT in the latter. Thank you very much.Iván Sotohttps://www.blogger.com/profile/01422968472273266007noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-41214770103888853732018-04-02T13:10:58.111-07:002018-04-02T13:10:58.111-07:00Thank you Dr Giles! I have learned a lot from your...Thank you Dr Giles! I have learned a lot from your blog. It's very generous of you to share these materials. Nguyen Hue Lienhttps://www.blogger.com/profile/12841037751956118328noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-54286874195551399622018-03-19T13:17:44.645-07:002018-03-19T13:17:44.645-07:00Thanks - sorry the posts haven't been as regul...Thanks - sorry the posts haven't been as regular lately.Dave Gileshttps://www.blogger.com/profile/05389606956062019445noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-83047944555018495912018-03-19T13:14:09.504-07:002018-03-19T13:14:09.504-07:00Hi, I read your blogs on a regular basis. Your hum...Hi, I read your blogs on a regular basis. Your humoristic style is awesome, keep up the good work!Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-1197721583779796202018-03-18T16:20:06.721-07:002018-03-18T16:20:06.721-07:00Dave,
You and your readers might be interested to...Dave,<br /><br />You and your readers might be interested to know that there is an undergraduate version of the game, hosted by Oeconomica at the University of Chicago. Details and signup (open to undergrads everywhere) here: https://metricsgame.squarespace.com/about/BJHnoreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-83379304050163700822018-03-17T03:06:40.234-07:002018-03-17T03:06:40.234-07:00Hi,
I have read your Data science blog.It"...Hi,<br /><br /><br /><br />I have read your<a href="https://goo.gl/eaSdhz" rel="nofollow"> Data science</a> blog.It"s very attractive and impressive.Very useful to me, I like it your blog<br />Thanks for sharing this blog.......<br /><br />Thank you<br />priya<br />priya Eeranagulahttps://www.blogger.com/profile/12274636215063409104noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-43482465278856242972018-03-02T01:57:19.722-08:002018-03-02T01:57:19.722-08:00So you sir have been blogging consistently since 2...So you sir have been blogging consistently since 2011, I should learn from you sir.<br />Consistency does miracles for a blog I say.kim ian tumblodhttps://www.blogger.com/profile/16564071550408519750noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-8277419401571437942018-02-27T10:02:04.635-08:002018-02-27T10:02:04.635-08:00No, I don't see any problem with this.No, I don't see any problem with this.Dave Gileshttps://www.blogger.com/profile/05389606956062019445noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-3695101601977041632018-02-27T10:00:57.381-08:002018-02-27T10:00:57.381-08:00Hello Prof Giles,
Do you see any problems of usin...Hello Prof Giles,<br /><br />Do you see any problems of using weekly data instead of daily data in VECM if my time period is just 2 years long. I'm examining price discovery process between CDS and Bond markets.<br /><br />Thanks in advance.Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-37657066327005937182018-02-26T07:19:05.080-08:002018-02-26T07:19:05.080-08:00Stefan - yes - thanks for spotting this.
DaveStefan - yes - thanks for spotting this.<br /><br />DaveDave Gileshttps://www.blogger.com/profile/05389606956062019445noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-46073674055214508012018-02-26T04:20:53.020-08:002018-02-26T04:20:53.020-08:00Dear Professor,
I have question regarding to sett...Dear Professor,<br /><br />I have question regarding to setting up the VAR model. You write that we need to add the next variables:<br /> <br />1. (Linear) trend<br />2. D2,t-k (where k, the maximum lag length, is 2 in our case)<br />3. Trend*D2,t-k<br />4. I2,t ; I2,t-1; ......; I2,(t-(k-1); where again, k = 2 in our case.<br /><br />However, if we look at your Eviews file, we see that you added only the three last variables: D2(-2) T*D2(-2) I2 I2(-1). So, you did not add the trend in the beginning.<br /><br />Should it look like T D2(-2) T*D2(-2) I2 I2(-1) ?<br /><br />Best regards and many thanks for this post,<br />StefanStepan Ryzhkovhttps://www.blogger.com/profile/04669724991964814221noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-79598602794827443132018-02-23T09:59:24.802-08:002018-02-23T09:59:24.802-08:00Hello.This article was extremely motivating, parti...Hello.This article was extremely motivating, particularly since I was browsing <br />for thoughts on this matter last week.Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-52053881985342349572018-02-23T08:47:27.703-08:002018-02-23T08:47:27.703-08:00Coming from a background in statistics rather than...Coming from a background in statistics rather than econ, I would like to share some of my thoughts on this discussion.<br /><br />For this discussion you use a latent variable specification of the probit model. If a latent variable is to be assumed, a normal random variable seems like a pretty natural choice. This latent variable specification allows you to introduce heteroscedasticity into the model as you discussed. <br />The probit models tends to not be seen much outside of economics; elsewhere everyone tends to default to logit models. Of course the logit model can be given an almost identical latent variable specification: Y* = XB + e, where e is instead assumed to be logistic distributed.<br /><br />For the logit model, however, this specification is quite uncommon. Logistic distributions are a somewhat exotic distribution, they are unlikely to come about naturally in the same way as normal distribution (central limit theorem and maximal entropy considerations). Instead the logit model is usually specified as LOG-ODDS = XB. While the two specifications are mathematically identical, with the alternative specification we think of the observed responses as bernoulli random variables with varying propensities to success. No latent variable is introduced. This is a (to me at least) a much more natural specification as the logistic distribution is such an unnatural distribution. This alternative specification has an important consequence though, to introduce the same kind of heteroskedasticity as in the probit model, the link function would have to vary for different individuals. This would break the log-odds interpretation of the logit model, and so this kind of heteroscedasticity doesn't make much sense in logit models. What to make then of the results of a (in the context of the probit model) heteroscedasticity test for the logit model? In this case it doesn't indicate heteroscedasticity, but rather indicates some kind of non-linearity in the effects or other misspecification. It seems to me then that the discussion you presented here heteroscedasticity actually is a more general discussion on model misspecification. To me, the choice of model (logit/probit), and even the specification of the model (link-function/latent-variable) comes in to play in understanding how to interpret the results of model misspecification test.Kroutonerhttps://www.blogger.com/profile/05758537158353883675noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-51704364283882719662018-02-20T05:09:08.555-08:002018-02-20T05:09:08.555-08:00Thank you Prof Thank you Prof GOPI KRISHNAN K.K.VIJAYARAGHAVANhttps://www.blogger.com/profile/02981320029069586508noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-52224977343841866382018-02-19T15:35:16.357-08:002018-02-19T15:35:16.357-08:00Professor Giles-This is a great blog! You have pos...Professor Giles-This is a great blog! You have posted lots of interesting things on the ARDL Bounds Testing approach to cointegration. One question I had, and you may have touched on this earlier, is the requirement for one of the variables to be weakly exogenous for the ARDL method to be valid. I can't seem to understand this reading the actual 2001 paper, but in Walter Enders "Applied Econometric Time Series", 3rd edition, on page 411 the author states that to use the error correction test of the ARDL it is necessary to assume that one of the variables is weakly exogenous. If so would this mean that if all variables in a system react to the error correction term, that the ARDL method is not valid? Thanks for any insight, <br />Bill MilesWilliam Milesnoreply@blogger.com