Re: st: Time demean panel variables using -center command

[Nick Cox <njcoxstata@gmail.com>]

-center- and -oaxaca- are user-written commands, so please explain
where they come from. I don't know tribal habits here to be able to
answer your question.

Nick
njcoxstata@gmail.com


On 12 March 2014 07:07, Vaidyanathan Ganapathy <vaidyang@usc.edu> wrote:

> I have a panel data (id, time) and wondering what would be the best
> method to demean the dependent variable, which is natural logarithm of
> costs?  I tried using the -center command by Ben Jann which produces
> the demeaned variables case wise. Can we demean ln(dependent variable)
> as it is, or should the dependent variable be first time demeaned
> using original scale and then logarithm be applied?
>
> I basically used the -center command to demean ln(costs) to use the
> demeaned variables for regressions run on 2 separate groups (the goal
> is to run separate fixed effects models for 2 groups and compare the
> coefficients). However, when I compare coefficients of the variables
> from the two regressions (i.e. take the difference), the results are
> not meaningful. By not meaningful, I mean that the overall differences
> in coefficients are too small or getting dropped out.
>
> Is there something wrong with the approach of demeaning the dependent
> variable -  ln(costs), or is there something wrong in how the
> differentials were calculated (I am using the Oaxaca decomposition
> method to analyze differences between the coefficients)?
>
> Below is what I ran and the corresponding outputs -
>
> //De-mean the ln(dependent) and the indendent variables -
>
> by pcn: center lnallhccx2 tpcat2-tpcat6 bpdx2 chdx2 asthbrdx2 cnsdx2
> motordx2 physdevdx2 nddx2 chrnic1, casewise
>
> //Run OLS regression with cluster robust errors of the dependent
> variable on set of predictors for two groups (premie_cat=0 and
> premie_cat==2)
>
> oaxaca c_lnallhccx2  c_tpcat2- c_tpcat6 c_bpdx2 c_chdx2 c_asthbrdx2
> c_cnsdx2 c_motordx2 c_physdevdx2 c_nddx2 c_chrnic1 c_period if
> premie_cat==0|premie_cat==2, by(premie_cat) weight(0 1) cluster(pcn)
>
>
> Blinder-Oaxaca decomposition                      Number of obs   =     137972
>
>           1: premie_cat = 0
>           2: premie_cat = 2
>
>                                 (Std. Err. adjusted for 68994 clusters in pcn)
> -------------------------------------------------------------------------------
>              |               Robust
> c_lnallhccx2 |      Coef.   Std. Err.      z    P>|z|     [95% Conf. Interval]
> --------------+----------------------------------------------------------------
> Differential  |
> Prediction_1 |   4.73e-10   6.22e-10     0.76   0.447    -7.46e-10    1.69e-09
> Prediction_2 |   1.19e-08   9.81e-09     1.21   0.227    -7.36e-09    3.11e-08
>   Difference |  -1.14e-08   9.83e-09    -1.16   0.247    -3.07e-08    7.88e-09
> --------------+----------------------------------------------------------------
> Decomposition |
>    Explained |          0  (omitted)
>  Unexplained |  -1.14e-08   9.83e-09    -1.16   0.247    -3.07e-08    7.88e-09
> -------------------------------------------------------------------------------
>
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/