Root Mean Squared Error in xtreg

[Korbinian Hammer]

Dear all,

I want to compare Mean-Group estimators with pooled estimators obtained by xtreg. However, the mean group estimator give me the Rood Mean Squared Error while xtreg provides measures for R squared (overall, between, within). How can I get the RMSE for the FE estimator by xtreg?

Best,

Korbinian

[Clyde Schechter]

-xtreg- returns the root mean squared error in e(rmse).

xtreg whatever
local RMSE = e(rmse)

[Joe Korkey]

When I do this local RMSE = e(rmse) after the xtreg, it does not return anything. it just executes the command and I see nothing. How do I see the value?

[Joseph Coveney]

When I do this local RMSE = e(rmse) after the xtreg, it does not return anything. it just executes the command and I see nothing. How do I see the value?

That only assigns the value; in order to see it you'd have to follow that with something like the following.

display `RMSE'

I illustrate it below (at the "Here" comment).

.ÿ
.ÿversionÿ17.0

.ÿ
.ÿclearÿ*

.ÿ
.ÿ//ÿseedem
.ÿsetÿseedÿ1708559278

.ÿ
.ÿquietlyÿsysuseÿauto

.ÿ
.ÿsummarizeÿrep78,ÿmeanonly

.ÿquietlyÿreplaceÿrep78ÿ=ÿruniformint(r(min),ÿr(max))ÿifÿmi(rep78)

.ÿ
.ÿxtregÿpriceÿi.foreignÿc.mpg,ÿi(rep78)ÿfe

Fixed-effectsÿ(within)ÿregressionÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿNumberÿofÿobsÿÿÿÿÿ=ÿÿÿÿÿÿÿÿÿ74
Groupÿvariable:ÿrep78ÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿNumberÿofÿgroupsÿÿ=ÿÿÿÿÿÿÿÿÿÿ5

R-squared:ÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿObsÿperÿgroup:
ÿÿÿÿÿWithinÿÿ=ÿ0.2909ÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿminÿ=ÿÿÿÿÿÿÿÿÿÿ3
ÿÿÿÿÿBetweenÿ=ÿ0.2855ÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿavgÿ=ÿÿÿÿÿÿÿ14.8
ÿÿÿÿÿOverallÿ=ÿ0.2816ÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿmaxÿ=ÿÿÿÿÿÿÿÿÿ30

ÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿF(2,67)ÿÿÿÿÿÿÿÿÿÿÿ=ÿÿÿÿÿÿ13.75
corr(u_i,ÿXb)ÿ=ÿ-0.2240ÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿProbÿ>ÿFÿÿÿÿÿÿÿÿÿÿ=ÿÿÿÿÿ0.0000

------------------------------------------------------------------------------
ÿÿÿÿÿÿÿpriceÿ|ÿCoefficientÿÿStd.ÿerr.ÿÿÿÿÿÿtÿÿÿÿP>|t|ÿÿÿÿÿ[95%ÿconf.ÿinterval]
-------------+----------------------------------------------------------------
ÿÿÿÿÿforeignÿ|
ÿÿÿÿForeignÿÿ|ÿÿÿ1572.385ÿÿÿ785.2305ÿÿÿÿÿ2.00ÿÿÿ0.049ÿÿÿÿÿ5.057904ÿÿÿÿ3139.711
ÿÿÿÿÿÿÿÿÿmpgÿ|ÿÿ-315.8967ÿÿÿ61.23027ÿÿÿÿ-5.16ÿÿÿ0.000ÿÿÿÿ-438.1128ÿÿÿ-193.6806
ÿÿÿÿÿÿÿ_consÿ|ÿÿÿ12425.54ÿÿÿ1309.532ÿÿÿÿÿ9.49ÿÿÿ0.000ÿÿÿÿÿ9811.701ÿÿÿÿ15039.37
-------------+----------------------------------------------------------------
ÿÿÿÿÿsigma_uÿ|ÿÿ825.04818
ÿÿÿÿÿsigma_eÿ|ÿÿ2556.6422
ÿÿÿÿÿÿÿÿÿrhoÿ|ÿÿ.09431798ÿÿÿ(fractionÿofÿvarianceÿdueÿtoÿu_i)
------------------------------------------------------------------------------
Fÿtestÿthatÿallÿu_i=0:ÿF(4,ÿ67)ÿ=ÿ0.64ÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿÿProbÿ>ÿFÿ=ÿ0.6323

.ÿlocalÿRMSEÿ=ÿe(rmse)

.ÿ
.ÿ//ÿHere
.ÿdisplayÿinÿsmclÿasÿtextÿ`RMSE'
2556.6422

.ÿ
.ÿexit

endÿofÿdo-file


.

[Carlo Lazzaro]

Korbinian:
another approach might be:

se "https://www.stata-press.com/data/r17/nlswork.dta"
. xtreg ln_wage age, fe

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

R-squared:                                      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 | Coefficient  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

. di e(rmse)
.30349389

.