Re: st: Reemedy for serial correlation in Panel Data

["D. Demetriou" <dd358@cam.ac.uk>]

Dear David,

Thank you so much for your immediate reply!

Ok then, here are the details:

I am trying to estimate the impact of homeownership on a selection of 
social indicators (e.g child outcomes, crime, health outcomes, etc)

Controls: Regional Income, Unemployemnt, some demographics, etc

For each dependent variable a procedure of determining the correct 
specification is followed: not one model is appropriate for all. e.g. some 
require fixed effects, others mixed effects and in some cases the 
in-between variation is so low that it makes sense to use simple OLS.

Please see below an example below:


                                 (Std. Err. adjusted for 9 clusters in 
region) 
-------------------------------------------------------------------------------
             |               Robust
      crime1 | Coef. Std. Err. z P>|z| [95% Conf. Interval] 
--------------+----------------------------------------------------------------
     incvars | -.9100782 .2706087 -3.36 0.001 -1.440461 -.379695
  hownership | -.5674226 .2205213 -2.57 0.010 -.9996363 -.1352088
   totalmigr | -.0281261 .0251894 -1.12 0.264 -.0774964 .0212442
  primsector | 2.692268 .7704074 3.49 0.000 1.182297 4.202238 
policefor~sss | .0821489 .0816743 1.01 0.315 -.0779298 .2422275
   regsegrve | .1994468 .1346516 1.48 0.139 -.0644656 .4633591
         ILO | .9975996 .5199506 1.92 0.055 -.0214848 2.016684
  popabove60 | -.1586686 .3314961 -0.48 0.632 -.808389 .4910519
 populations | 2.410613 .3840222 6.28 0.000 1.657944 3.163283
       _cons | 52.07961 13.64308 3.82 0.000 25.33968 78.81955 
-------------------------------------------------------------------------------
	

Your help is greatly appreciated!

Yours,

DD

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/