Distribution of FE

[Linda Pasi]

Hello everyone.

I am trying to get the distribution of firm fixed effects (acquirer FE) when I also have in the regression year FE. Does anyone know how to get them isolated? So far I only know how to use the following code, but I think it includes both acquirer and year FE.

year_and_cusipgroup is a concat of year and cusip_group, which is a group variable for cusip, my company id.

xtset year_and_cusipgroup
xtreg car, fe i(year_and_cusipgroup)
predict year_and_cusipgroup_1, u

[Carlo Lazzaro]

Linda:
have you taken a look at the community-contributed command -reghdfe-?

[Linda Pasi]

Dear Carlo,

First of all, thank you for your response. I had a look at it now, but I still don't understand how to use both fixed effects in a reghdfe and get the distribution and statistics of only one FE.

I tried this code but STATA gave back "invalid options: predict(cusip_group) r(9)".

Do you have any extra recommendations?

reghdfe car, absorb(cusip_group year) predict(cusip_group)

Thanks!

[Linda Pasi]

I also tried this other code, by reading to the description of reghdfe.

reghdfe car, absorb(cusip_group year, savefe)

I attach the results I obtained. I am not sure how to interpret it...I apologise as I am still a beginner with STATA.

[Carlo Lazzaro]

Linda:
I fail to get what you're after.
That said, from the results you posted (for the future please do not share scrrenshots but use CODE delimiters instead. Thanks), being the within R-sq=0, I doubt that you have evidence of a group-wise fixed effect.
If, for any reason, you want to save the fes, you can tweak the following code, that was retrieved from the help file of the community-contributed command -reghdfe-:

use "http://www.stata-press.com/data/r16/nlswork.dta"
. reghdfe ln_w grade age ttl_exp tenure not_smsa south , absorb(FE1=idcode FE2=year)
(dropped 550 singleton observations)
(converged in 9 iterations)
note: grade omitted because of collinearity
(converged in 9 iterations)

HDFE Linear regression                            Number of obs   =     27,541
Absorbing 2 HDFE groups                           F(   5,  23375) =     261.99
                                                  Prob > F        =     0.0000
                                                  R-squared       =     0.6762
                                                  Adj R-squared   =     0.6185
                                                  Within R-sq.    =     0.0531
                                                  Root MSE        =     0.2939

------------------------------------------------------------------------------
     ln_wage |      Coef.   Std. Err.      t    P>|t|     [95% Conf. Interval]
-------------+----------------------------------------------------------------
       grade |          0  (omitted)
         age |   .0114497   .0099824     1.15   0.251    -.0081165    .0310159
     ttl_exp |   .0323758   .0015046    21.52   0.000     .0294266     .035325
      tenure |   .0104689   .0009264    11.30   0.000     .0086531    .0122847
    not_smsa |  -.0914148   .0096386    -9.48   0.000    -.1103071   -.0725225
       south |  -.0640471   .0110539    -5.79   0.000    -.0857134   -.0423808
-------------+----------------------------------------------------------------
    Absorbed |    F(4160, 23375) =      5.501   0.000             (Joint test)
------------------------------------------------------------------------------

Absorbed degrees of freedom:
---------------------------------------------------------------+
 Absorbed FE |  Num. Coefs.  =   Categories  -   Redundant     |
-------------+-------------------------------------------------|
      idcode |         4147            4147              0     |
        year |           14              15              1     |
---------------------------------------------------------------+

. sum FE1 FE2

    Variable |        Obs        Mean    Std. Dev.       Min        Max
-------------+---------------------------------------------------------
         FE1 |     27,541    5.66e-17    .3169373  -1.378648   1.946491
         FE2 |     27,541   -5.86e-18    .1045295  -.1716042   .1583403

.

[Linda Pasi]

Dear Carlo,

I think I solved the issue. Thank you very much for your help!

Kind regards,
Linda Pasi

[Carlo Lazzaro]

Linda:
happy with reading that you've solved the issue.
This forum encourages sharing the solution the original posters found out themselves, as others stumbling upon the same problem could greatly benefit from them.

[Linda Pasi]

Dear Carlo,

Of course.

I used this code to obtain the distribution and summary statistics of the different FE:

cusip_group is a group variable of my company id.

reghdfe y, absorb (cusip_group year, savefe)
summarize _hdfe1_, detail

[Carlo Lazzaro]

Linda:
thanks for sharing.

[Linda Pasi]

Dear Carlo,

I am also struggling with a loop. I created a new post here: https://www.statalist.org/forums/for...lready-defined.

If you have time to look quickly at it, maybe you could give me some advice?

Thanks in advance.

Kind regards,
Linda