tag:blogger.com,1999:blog-6288862798546085706.post6854841646548293459..comments2020-11-30T06:17:09.023-05:00Comments on Econometrics By Simulation: Checking for differences in estimates by groupFrancishttp://www.blogger.com/profile/16658586705916884436noreply@blogger.comBlogger3125tag:blogger.com,1999:blog-6288862798546085706.post-34659530894029492892013-02-13T00:02:16.284-05:002013-02-13T00:02:16.284-05:00Thanks for this post!Thanks for this post!Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-6288862798546085706.post-63234520176558555722012-12-20T11:39:37.588-05:002012-12-20T11:39:37.588-05:00It is a somewhat arbitrary choice. I just wanted ...It is a somewhat arbitrary choice. I just wanted the error to have a variance of 4 so that there is less explained variance. I could have specified it similarly as rnormal(1,2) however I don't like that formulation because the normal distribution sometimes has the second parameter the variance and sometimes the standard deviation. rnormal()*2 is less ambiguous.Francishttps://www.blogger.com/profile/16658586705916884436noreply@blogger.comtag:blogger.com,1999:blog-6288862798546085706.post-76273341448639317062012-12-13T23:47:12.882-05:002012-12-13T23:47:12.882-05:00Thanks for the interesting post. I was wondering w...Thanks for the interesting post. I was wondering why you have used rnormal()*2 to generate the error term. Why not just rnormal()?alinoreply@blogger.com