Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: Please reply


From   nicola.baldini2@unibo.it
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Please reply
Date   Sun, 30 Sep 2007 19:22:00 +0200

You will increase your change to get an answer by (1) using a more informative subject (2) reading some statistical manuals and then re-posting a question that sounds more Stata-related than merely statistical.
If I were you, my strategy would be:
(1) using -xtreg- followed by -xttest0-
(2) if the test is NOT significant, then use -regress-
(3) if the test is significant, then (a) use -xtoverid- (you can download it by typing ssc install xtoverid), and (b) if this test is significant, then turn to -xtreg, fe-
Obviously, you may have heteroskedasticity and autocrrelation problems, but this is another story.

Nicola

At 02.33 28/09/2007 -0400, Amirul Ahsan wrote:
>Hi,
>
>I was wandering if you could kindly reply to one my question. I am doing an analsys where I have data of 36 countries for 15 years each. I need to put them all together to run regression. What I did are as follows:
>
>- -created a pool object
>- -did not use fixed or random effect
>- -used OLS
>
>what should I call this regression now
>
>- -a pooled regression or 
>- -OLS regression
>- -or a pooled OLS regression
>
>The answers I have got are satisfactory, only what name should I give it?
*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index