bootstrap standard errors - panel data - repeated time values within panel error

[Kyle Smith]

I am trying to bootstrap standard errors on a panel data set. There are no firm-year duplicates in the panel.

I have searched for an answer for this throughout the forum and have not found it. Although many people seem to have this problem.

clear
input firmid year y x
1 1 7 3
1 2 5 8
1 3 6 4
1 4 9 4
1 5 6 3
1 7 7 2
2 1 4 7
2 2 5 8
2 3 4 6
2 4 9 4
2 5 4 6
2 6 8 4
end

duplicates drop firmid year, force
sort firmid year
xtset firmid year

reg y x
bootstrap, cluster(firmid) r(50) idcluster(firmid_cl) seed(123): reg y x

I get the

repeated time values within panel
the most likely cause for this error is misspecifying the cluster(), idcluster(), or group() option
r(451);

Error everytime.

Is the solution as simple as:

clear
input firmid year y x
1 1 7 3
1 2 5 8
1 3 6 4
1 4 9 4
1 5 6 3
1 7 7 2
2 1 4 7
2 2 5 8
2 3 4 6
2 4 9 4
2 5 4 6
2 6 8 4
end

duplicates drop firmid year, force
sort firmid year
xtset firmid year

reg y x
xtset, clear
xtset firmid
bootstrap, cluster(firmid) r(50) idcluster(firmid_cl) seed(123): reg y x

Thanks for the help.

[Joseph Coveney]

Wouldn't you want to be using an estimation command tailored to panel data? Perhaps something like

set seed `=strreverse("1585475")'
xtreg y c.(year x), i(firmid) fe vce(bootstrap, reps(1000) nodots)

Using the vce(bootstrap) option with a command that's designed with panel data in mind handles clustering seamlessly.

[Carlo Lazzaro]

Kyle:
as an aside to Joseph's helpful advice, I do not think you estimated a panel data regression in your first code.
Looking at the following toy-example, regression coefficient are not the same if you use -regress- or -xtreg-:

. use "https://www.stata-press.com/data/r16/nlswork.dta"
(National Longitudinal Survey.  Young Women 14-26 years of age in 1968)

. reg ln_wage c.age##c.age, vce(cluster idcode)

Linear regression                               Number of obs     =     28,510
                                                F(2, 4709)        =     701.39
                                                Prob > F          =     0.0000
                                                R-squared         =     0.0882
                                                Root MSE          =     .45654

                             (Std. Err. adjusted for 4,710 clusters in idcode)
------------------------------------------------------------------------------
             |               Robust
     ln_wage |      Coef.   Std. Err.      t    P>|t|     [95% Conf. Interval]
-------------+----------------------------------------------------------------
         age |   .0855891   .0046943    18.23   0.000     .0763861    .0947922
             |
 c.age#c.age |  -.0010982   .0000798   -13.76   0.000    -.0012547   -.0009417
             |
       _cons |   .1647917   .0655679     2.51   0.012      .036248    .2933354
------------------------------------------------------------------------------

. xtreg ln_wage c.age##c.age, vce(cluster idcode)

Random-effects GLS regression                   Number of obs     =     28,510
Group variable: idcode                          Number of groups  =      4,710

R-sq:                                           Obs per group:
     within  = 0.1087                                         min =          1
     between = 0.1015                                         avg =        6.1
     overall = 0.0870                                         max =         15

                                                Wald chi2(2)      =    1258.33
corr(u_i, X)   = 0 (assumed)                    Prob > chi2       =     0.0000

                             (Std. Err. adjusted for 4,710 clusters in idcode)
------------------------------------------------------------------------------
             |               Robust
     ln_wage |      Coef.   Std. Err.      z    P>|z|     [95% Conf. Interval]
-------------+----------------------------------------------------------------
         age |   .0590339   .0041049    14.38   0.000     .0509884    .0670795
             |
 c.age#c.age |  -.0006758   .0000688    -9.83   0.000    -.0008107    -.000541
             |
       _cons |   .5479714   .0587198     9.33   0.000     .4328826    .6630601
-------------+----------------------------------------------------------------
     sigma_u |   .3654049
     sigma_e |  .30245467
         rho |  .59342665   (fraction of variance due to u_i)
------------------------------------------------------------------------------

. xtreg ln_wage c.age##c.age, fe vce(cluster idcode)

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

R-sq:                                           Obs per group:
     within  = 0.1087                                         min =          1
     between = 0.1006                                         avg =        6.1
     overall = 0.0865                                         max =         15

                                                F(2,4709)         =     507.42
corr(u_i, Xb)  = 0.0440                         Prob > F          =     0.0000

                             (Std. Err. adjusted for 4,710 clusters in idcode)
------------------------------------------------------------------------------
             |               Robust
     ln_wage |      Coef.   Std. Err.      t    P>|t|     [95% Conf. Interval]
-------------+----------------------------------------------------------------
         age |   .0539076    .004307    12.52   0.000     .0454638    .0623515
             |
 c.age#c.age |  -.0005973    .000072    -8.30   0.000    -.0007384   -.0004562
             |
       _cons |    .639913   .0624195    10.25   0.000     .5175415    .7622845
-------------+----------------------------------------------------------------
     sigma_u |   .4039153
     sigma_e |  .30245467
         rho |  .64073314   (fraction of variance due to u_i)
------------------------------------------------------------------------------

.

In addition, if your were intended to estimate a fixed effect panel data regression with -regress- instead of -xtreg,fe- (an approach that I would not recommend, though), your code should have beeb something like:

regress y x i.firmid_cl. vce(cluster firmid_cl)

[Joseph Coveney]

. . . I do not think you estimated a panel data regression in your first code.
Looking at the following toy-example, regression coefficient are not the same if you use -regress- or -xtreg-:

So, I guess that that means that the OP's use here, in the context of clustered bootstrapping, of

xtgee . . ., . . . corr(independent) . . .

which is the equivalent of regress (or more accurately, of glm for the default normal linear model), wasn't really accomplishing what he wanted?

[Carlo Lazzaro]

Joseph:
it's difficult to say (for me, at least) without further details form the OP.