Hello.

I have a question: why the below results are different? what is the meaning of each of the clustering? That is, how can I interpret the coefficients as well as the robust standard errors?

Actually, in my real dataset which requires double clustering in terms of SIC_TO(industry) and year, the number of clusters is small(below 20) when I use the second code so that it cannot generate F-stat which I should report in my paper.

How can I solve this problem?

CODE:

. use "https://ift.tt/29fKNF7", clear
. egen double_cluster=group(idcode year)

First Method: . reghdfe ln_wage age i.race, noa vce(cluster double_cluster)

Second Method: . reghdfe ln_wage age i.race, noa vce(cluster idcode year)

Results:

1) First Result:

. . reghdfe ln_wage age i.race, noa vce(cluster double_cluster)
(MWFE estimator converged in 1 iterations)

HDFE Linear regression Number of obs = 28,510
Absorbing 1 HDFE group F( 3, 28506) = 905.75
Statistics robust to heteroskedasticity Prob > F = 0.0000
R-squared = 0.0946
Adj R-squared = 0.0945
Within R-sq. = 0.0946
Number of clusters (double_cluster) = 28,510 Root MSE = 0.4549

(Std. Err. adjusted for 28510 clusters in double_cluster)
------------------------------------------------------------------------------
| Robust
ln_wage | Coef. Std. Err. t P>|t| [95% Conf. Interval]
-------------+----------------------------------------------------------------
age | .0196731 .0004233 46.48 0.000 .0188435 .0205028
|
race |
black | -.1377638 .0059505 -23.15 0.000 -.1494271 -.1261006
other | .0666999 .0284081 2.35 0.019 .0110187 .1223812
|
_cons | 1.141686 .012024 94.95 0.000 1.118119 1.165254
------------------------------------------------------------------------------

2) Second Result:

. . reghdfe ln_wage age i.race, noa vce(cluster idcode year)
(MWFE estimator converged in 1 iterations)

HDFE Linear regression Number of obs = 28,510
Absorbing 1 HDFE group F( 3, 14) = 99.06
Statistics robust to heteroskedasticity Prob > F = 0.0000
R-squared = 0.0946
Adj R-squared = 0.0945
Number of clusters (idcode) = 4,710 Within R-sq. = 0.0946
Number of clusters (year) = 15 Root MSE = 0.4549

(Std. Err. adjusted for 15 clusters in idcode year)
------------------------------------------------------------------------------
| Robust
ln_wage | Coef. Std. Err. t P>|t| [95% Conf. Interval]
-------------+----------------------------------------------------------------
age | .0196731 .0014594 13.48 0.000 .0165431 .0228032
|
race |
black | -.1377638 .0133762 -10.30 0.000 -.166453 -.1090747
other | .0666999 .0664563 1.00 0.333 -.0758347 .2092346
|
_cons | 1.141686 .0456635 25.00 0.000 1.043748 1.239625
------------------------------------------------------------------------------