tag:blogger.com,1999:blog-2198942534740642384.post8797134137125406073..comments2023-10-24T03:16:41.009-07:00Comments on Econometrics Beat: Dave Giles' Blog: Good Old R-Squared!Dave Gileshttp://www.blogger.com/profile/05389606956062019445noreply@blogger.comBlogger18125tag:blogger.com,1999:blog-2198942534740642384.post-50858478412828293852017-11-17T09:25:40.341-08:002017-11-17T09:25:40.341-08:00Very low R-squared values often arise when cross-s...Very low R-squared values often arise when cross-section data are used. It's very common.Dave Gileshttps://www.blogger.com/profile/05389606956062019445noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-43761746461600364852017-11-17T09:23:29.888-08:002017-11-17T09:23:29.888-08:00Dear Prof Dave,
I ran a regression on a cross-sec...Dear Prof Dave,<br /><br />I ran a regression on a cross-sectional firm level data across different countries, but my R2 is about 0.05.<br /><br />This worries me as it seems my model do not explain much of the variation in the dependent variable.<br /><br />What do you suggest I do about this please?<br /><br />jghiughttps://www.blogger.com/profile/08115130223921442578noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-49976124077675577972016-12-05T09:37:15.903-08:002016-12-05T09:37:15.903-08:00That's an interesting question. I would use th...That's an interesting question. I would use the (unadjusted) R-squared for this purpose. It's not clear, though, what the distribution of the shared variance will be - I doubt if it is still Beta. You could always bootstrap the test of the hypothesis that you're interested in.Dave Gileshttps://www.blogger.com/profile/05389606956062019445noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-8828567361313027962016-11-28T21:21:47.297-08:002016-11-28T21:21:47.297-08:00I would like to test if the shared variance of two...I would like to test if the shared variance of two predictors x1 and x2 with a criterion y is non-zero. I can calculate the shared variance by taking the R-squared minus the squared semi-partial correlations of x1 and x2 to give me the shared variance. My first question is should I use the R squared or is it a better idea to use the adjusted r squared to compute the shared variance? More importantly, I would like to test if this shared variance is > 0. Can I still use the Beta distribution?Stats Enthusiasthttps://www.blogger.com/profile/06053304396615859793noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-58326521974386793092014-06-03T10:41:37.046-07:002014-06-03T10:41:37.046-07:00You obviously have access to the internet............You obviously have access to the internet.........................Dave Gileshttps://www.blogger.com/profile/05389606956062019445noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-78868881985466490802014-06-03T08:01:50.574-07:002014-06-03T08:01:50.574-07:00I am currently pursuing Master in Applied Statisti...I am currently pursuing Master in Applied Statistics.<br />To meet the continuous assessment requirements of Applied Econometrics course, I was required to perform an OLS regression research project on cross sectional data.<br />I am most grateful if Prof. may provide the appropriate assistance to enable me to have a cross sectional data for this econometric assignment.<br /><br />I am looking forward to hear from Prof. soon.Anonymoushttps://www.blogger.com/profile/02666488705751930155noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-28904920229425524772014-03-19T06:30:00.725-07:002014-03-19T06:30:00.725-07:00I Am studying the value relevance of earnings per ...I Am studying the value relevance of earnings per share and book value of equity after the adoptionof IFRS. I measure value relevance by using the Adj R2. I would like to compare AdjR2 of the period of preadoption and AdjR2 of the post adoption period. I would like to know if there is diferenc and if this difference is significant. I would like to know the differnt tests that I can use based on stata. THank you <br />Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-26352287634394493002014-02-23T04:23:23.435-08:002014-02-23T04:23:23.435-08:00Certainly.Certainly.Dave Gileshttps://www.blogger.com/profile/05389606956062019445noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-90828004026659940912014-02-23T04:17:23.671-08:002014-02-23T04:17:23.671-08:00In this case using bootstrap to calculate the R2&#...In this case using bootstrap to calculate the R2's standard error would it provide a viable alternative?Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-66987917238173952852013-10-11T11:13:36.384-07:002013-10-11T11:13:36.384-07:00Here are 2 references that might be of some help:
...Here are 2 references that might be of some help:<br /><br />http://166.111.121.20:9080/mathjournal/DBSX200004/dbsx200004005.caj.pdf<br /><br />http://www.tandfonline.com/doi/abs/10.1080/03610918908812798#.Ulg_iVCkr1oDave Gileshttps://www.blogger.com/profile/05389606956062019445noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-68759811290303127492013-10-11T11:03:16.852-07:002013-10-11T11:03:16.852-07:00Hate to say it, but that Z-test is nonsensical. Th...Hate to say it, but that Z-test is nonsensical. The main point to keep in mind is the following.A statistical test relates to a statement (hypothesis) about something in the POPULATION, not the sample. We use one or more sample statistics to test that hypothesis. Going back to your original comment, what you really want is a test of the hypothesis that the POPULATION R-squared for one model equals that for the other model, presumably against a one-sided alternative hypothesis. This test could be based on the 2 sample R-squared values, using knowledge of the respective distributions.<br /><br />There is a well-established statistics literature (going back at least to the 1930's) on the problem of testing the equality of simple (Pearson) correlations associated with Normal populations. Presumably this can be extended to the multiple regression case you're interested.<br /><br />I can't think of any "canned" software that's going to give you what you want.Dave Gileshttps://www.blogger.com/profile/05389606956062019445noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-64167388865841708142013-10-11T02:07:20.601-07:002013-10-11T02:07:20.601-07:00Thanks. The test I have in mind was was performed ...Thanks. The test I have in mind was was performed in the following paper: "The value relevance of German accounting measures: an empirical analysis" by Harris, Lang, and Möller (Journal of Accounting Research, Vol 32, No. 2 (1994)). The Z-statistic used is described in FN 38 on p. 198. The authors state that their test is based on Cramer (1987) even though I don't see any specific test proposed there.<br /><br />If Stata is not going to be of any help is there any other package that could give me the variances?Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-71158314261936716012013-10-10T11:32:02.078-07:002013-10-10T11:32:02.078-07:00Thank you. See my more recent post on the distribu...Thank you. See my more recent post on the distribution of R-squared at: http://davegiles.blogspot.ca/2013/10/more-on-distribution-of-r-squared.html#more<br /><br />Note that the results given there apply only if the null hypothesis (of no linear relationship between y and X) is TRUE. In general, the F distribution will have to be replaced with a non-central F distribution, and the Beta distribution will become non-central Beta distribution. This could then form the basis for constructing a test along the lines that you have in mind, although I haven't seen this done. Of course, it won't be a z-test! And STATA isn't going to be of any help!<br />Dave Gileshttps://www.blogger.com/profile/05389606956062019445noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-19573011912002140212013-10-10T11:23:44.637-07:002013-10-10T11:23:44.637-07:00very good article, thank you for that. I have one ...very good article, thank you for that. I have one question: for my own research I try to compare R-squared measures of one model that is fed with data derived under different accounting regimes (e.g. cash flow and earnings derived under local and international accounting standards). So, I get two R-squared measures, one if the model is fed with international accounting data and one if it is fed with the local accounting data. <br /><br />Is there a statistical test to compare both R-squared measures? If R-squared has a distribution one could use a z-test; the z-statistic could be: (R-squared1 - R-squared2) / sqrt[var(R-squared1) + var(R-squared2)] .<br /><br />The problem is: Stata would not give me the variances of the R-squared measures.<br /><br />I would appreciate your help, <br />thanks!<br /><br />Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-61174152778073165262013-05-03T11:01:32.410-07:002013-05-03T11:01:32.410-07:00Good post, I also changed my perspective. Thanks.Good post, I also changed my perspective. Thanks.Anonymoushttps://www.blogger.com/profile/01894713959715354935noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-58581605045047346162013-05-03T08:13:58.266-07:002013-05-03T08:13:58.266-07:00Nice post! Something that I haven't thought to...Nice post! Something that I haven't thought too much about.Charlie Gibbonshttp://cgibbons.usnoreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-28402335173777037382013-05-03T08:07:02.488-07:002013-05-03T08:07:02.488-07:00Good suggestion - thanks!Good suggestion - thanks!Dave Gileshttps://www.blogger.com/profile/05389606956062019445noreply@blogger.comtag:blogger.com,1999:blog-2198942534740642384.post-87961630457163215722013-05-02T22:21:57.249-07:002013-05-02T22:21:57.249-07:00Suggested future article: Describe and illustrate...Suggested future article: Describe and illustrate real examples of R squared's "dumb-bell" effect! .. and the corrolary --- sparcity of data in the tails. Anonymousnoreply@blogger.com