Entity fixed effects regression using reghdfe
OTR 34
. reghdfe ln_gdppc ln_trade ln_labor , absorb(country1) vce(cluster country1)
(MWFE estimator converged in 1 iterations)
HDFE Linear regression Number of obs = 2,772
Absorbing 1 HDFE group F( 2, 125) = 87.57
Statistics robust to heteroskedasticity Prob > F = 0.0000
R-squared = 0.9943
Adj R-squared = 0.9940
Within R-sq. = 0.6267
Number of clusters (country1) = 126 Root MSE = 0.1099
(Std. err. adjusted for 126 clusters in country1)
------------------------------------------------------------------------------
| Robust
ln_gdppc | Coefficient std. err. t P>|t| [95% conf. interval]
-------------+----------------------------------------------------------------
ln_trade | .3603947 .0737076 4.89 0.000 .2145182 .5062712
ln_labor | .053167 .1608747 0.33 0.742 -.265224 .371558
_cons | -.9384681 1.075791 -0.87 0.385 -3.067592 1.190656
------------------------------------------------------------------------------
Absorbed degrees of freedom:
-----------------------------------------------------+
Absorbed FE | Categories - Redundant = Num. Coefs |
-------------+---------------------------------------|
country1 | 126 126 0 *|
-----------------------------------------------------+
* = FE nested within cluster; treated as redundant for DoF computation
Outcome Predictor(s)
Fixed effects option
Controlling for
correlation within
panels
Total number of
cases (rows)
Total number of entities (i)
If this number is < 0.05 then
your model is ok. This is an F-
test to see whether all the
coefficients in the model are
jointly different than zero.
Two-tail p-values test the
hypothesis that each coefficient is
different from 0 (according to its
t-value).
A value lower than 0.05 will reject
the null and conclude that the
predictor has a significant effect
on the outcome (95%
significance).
Beta coefficients indicate
the change in the output (y)
when the predictors change
one unit over time. In this
example, all the variables
are log-transformed, the
interpretation is: when the
predictor increases 1% over
time, the output (y) changes
% (elasticity).
R-squared shows the percent
of the variance in the outcome
explained by the model. The Adj
R-squared, accounts for the
number of variables and their
significant contribution to
explaining the variation in the
output variable.
NOTE: Use reghdfe when controlling for multiple fixed effects or when xtreg,fe cannot run due to the number
of panels.