Would anyone know why I don't get exact standard errors when running -ivreg2- command with -, small- option & -ivreghdfe- command with -, dof(none)- option? According to the link below, the output of -ivreghdfe- and -ivreg2- should coincide when using these options.
https://github.com/sergiocorreia/ivreghdfe/issues/16
https://github.com/sergiocorreia/ivreghdfe/issues/16
Code:
. sysuse auto, clear
(1978 Automobile Data)
. ivreg2 price (weight=length) i.turn headroom, cluster(turn) small
IV (2SLS) estimation
--------------------
Estimates efficient for homoskedasticity only
Statistics robust to heteroskedasticity and clustering on turn
Number of clusters (turn) = 18 Number of obs = 74
F( 19, 17) = 4.62
Prob > F = 0.0013
Total (centered) SS = 635065396.1 Centered R2 = 0.6202
Total (uncentered) SS = 3447834321 Uncentered R2 = 0.9300
Residual SS = 241186914.4 Root MSE = 2113
------------------------------------------------------------------------------
| Robust
price | Coef. Std. Err. t P>|t| [95% Conf. Interval]
-------------+----------------------------------------------------------------
weight | 4.509739 .8817875 5.11 0.000 2.64933 6.370148
|
turn |
32 | 4877.48 1054.52 4.63 0.000 2652.637 7102.323
33 | 5213.019 1126.867 4.63 0.000 2835.538 7590.499
34 | 5087.309 906.7419 5.61 0.000 3174.251 7000.367
35 | 4214.549 849.7413 4.96 0.000 2421.752 6007.347
36 | 5181.819 850.9116 6.09 0.000 3386.553 6977.085
37 | 4764.247 447.3317 10.65 0.000 3820.46 5708.034
38 | 5682.881 377.091 15.07 0.000 4887.289 6478.474
39 | 1884.571 525.563 3.59 0.002 775.73 2993.412
40 | 354.0945 211.4594 1.67 0.112 -92.04575 800.2347
41 | 1614.824 315.6847 5.12 0.000 948.7876 2280.86
42 | -875.8628 297.734 -2.94 0.009 -1504.027 -247.699
43 | 661.132 351.431 1.88 0.077 -80.32257 1402.587
44 | 128.3899 546.5868 0.23 0.817 -1024.807 1281.587
45 | 1254.095 716.2294 1.75 0.098 -257.0171 2765.207
46 | -1000.848 430.9085 -2.32 0.033 -1909.986 -91.71103
48 | -620.5562 1108.191 -0.56 0.583 -2958.635 1717.523
51 | -493.1664 1463.767 -0.34 0.740 -3581.445 2595.113
|
headroom | -292.5445 330.1702 -0.89 0.388 -989.1427 404.0537
_cons | -8813.063 2837.232 -3.11 0.006 -14799.1 -2827.027
------------------------------------------------------------------------------
Underidentification test (Kleibergen-Paap rk LM statistic): 6.323
Chi-sq(1) P-val = 0.0119
------------------------------------------------------------------------------
Weak identification test (Cragg-Donald Wald F statistic): 56.021
(Kleibergen-Paap rk Wald F statistic): 53.560
Stock-Yogo weak ID test critical values: 10% maximal IV size 16.38
15% maximal IV size 8.96
20% maximal IV size 6.66
25% maximal IV size 5.53
Source: Stock-Yogo (2005). Reproduced by permission.
NB: Critical values are for Cragg-Donald F statistic and i.i.d. errors.
------------------------------------------------------------------------------
Warning: estimated covariance matrix of moment conditions not of full rank.
overidentification statistic not reported, and standard errors and
model tests should be interpreted with caution.
Possible causes:
number of clusters insufficient to calculate robust covariance matrix
singleton dummy variable (dummy with one 1 and N-1 0s or vice versa)
partial option may address problem.
------------------------------------------------------------------------------
Instrumented: weight
Included instruments: 32.turn 33.turn 34.turn 35.turn 36.turn 37.turn 38.turn
39.turn 40.turn 41.turn 42.turn 43.turn 44.turn 45.turn
46.turn 48.turn 51.turn headroom
Excluded instruments: length
------------------------------------------------------------------------------
. ivreghdfe price (weight=length) headroom, absorb(turn) cluster(turn) dof(none)
(dropped 4 singleton observations)
(MWFE estimator converged in 1 iterations)
IV (2SLS) estimation
--------------------
Estimates efficient for homoskedasticity only
Statistics robust to heteroskedasticity and clustering on turn
Number of clusters (turn) = 14 Number of obs = 70
F( 2, 13) = 13.60
Prob > F = 0.0006
Total (centered) SS = 436283540.4 Centered R2 = 0.4472
Total (uncentered) SS = 436283540.4 Uncentered R2 = 0.4472
Residual SS = 241186914.4 Root MSE = 2113
------------------------------------------------------------------------------
| Robust
price | Coef. Std. Err. t P>|t| [95% Conf. Interval]
-------------+----------------------------------------------------------------
weight | 4.509739 .8645848 5.22 0.000 2.641917 6.377561
headroom | -292.5445 323.7289 -0.90 0.383 -991.9184 406.8293
------------------------------------------------------------------------------
Underidentification test (Kleibergen-Paap rk LM statistic): 6.323
Chi-sq(1) P-val = 0.0119
------------------------------------------------------------------------------
Weak identification test (Cragg-Donald Wald F statistic): 56.021
(Kleibergen-Paap rk Wald F statistic): 55.712
Stock-Yogo weak ID test critical values: 10% maximal IV size 16.38
15% maximal IV size 8.96
20% maximal IV size 6.66
25% maximal IV size 5.53
Source: Stock-Yogo (2005). Reproduced by permission.
NB: Critical values are for Cragg-Donald F statistic and i.i.d. errors.
------------------------------------------------------------------------------
Hansen J statistic (overidentification test of all instruments): 0.000
(equation exactly identified)
------------------------------------------------------------------------------
Instrumented: weight
Included instruments: headroom
Excluded instruments: length
Partialled-out: _cons
nb: total SS, model F and R2s are after partialling-out;
any small-sample adjustments include partialled-out
variables in regressor count K
------------------------------------------------------------------------------
Absorbed degrees of freedom:
-----------------------------------------------------+
Absorbed FE | Categories - Redundant = Num. Coefs |
-------------+---------------------------------------|
turn | 14 0 14 |
-----------------------------------------------------+
Comment