Xtreg, illustrate regression in graph?

[Joakim Jean]

Friends,

I have a panel data set, looking like:

Units Variable Year
Unit 1 5 2000
Unit 1 2 2001
Unit 2 7 2000
Unit 2 3 2001

with 200 unique "units", and 20 years.

I want to illustrate the value of "variable" over time. Xtline produces 200 lines, which is unreadable. twoway lfit/qfit produces a solid average (one line), however I want to use the Fixed effect estimated regression line. Is there any neat way of doing this? I appriciate specific code suggestions, thank you very much. / Joakim

[Carlo Lazzaro]

Joakim:
welcome to this forum.
Do you mean something along the lines of the following toy-example?

. use "http://www.stata-press.com/data/r15/nlswork.dta"
(National Longitudinal Survey.  Young Women 14-26 years of age in 1968)

. xtreg ln_wage age, fe

Fixed-effects (within) regression               Number of obs     =     28,510
Group variable: idcode                          Number of groups  =      4,710

R-sq:                                           Obs per group:
     within  = 0.1026                                         min =          1
     between = 0.0877                                         avg =        6.1
     overall = 0.0774                                         max =         15

                                                F(1,23799)        =    2720.20
corr(u_i, Xb)  = 0.0314                         Prob > F          =     0.0000

------------------------------------------------------------------------------
     ln_wage |      Coef.   Std. Err.      t    P>|t|     [95% Conf. Interval]
-------------+----------------------------------------------------------------
         age |   .0181349   .0003477    52.16   0.000     .0174534    .0188164
       _cons |   1.148214   .0102579   111.93   0.000     1.128107     1.16832
-------------+----------------------------------------------------------------
     sigma_u |  .40635023
     sigma_e |  .30349389
         rho |  .64192015   (fraction of variance due to u_i)
------------------------------------------------------------------------------
F test that all u_i=0: F(4709, 23799) = 8.81                 Prob > F = 0.0000

. predict Fixed_effect, u
(24 missing values generated)

. twoway (scatter Fixed_effect year)

[Joakim Jean]

Carlo:

Thank you very much for a quick respons. After trying derivations of your code I think I managed to get closer to what I want.

So to be more clear: I would like to get an average regression line, like the results from an xtline ln_wage age (by group/unit- one line per group) but combined to one single line in a graph.

I think in your example, I'm looking for something like:
. xtreg ln_wage age, fe r
. predict Fixed_effect
.twoway line Fixed_effect age

It seems to me this gives an illustration of the FE-regression. Does this seem reasonable to you? Best regards/ Joakim

[Carlo Lazzaro]

Joakim:
it may well be reasonabale, conditional on your research goal.