arlionn 发表于 2014-4-10 09:16 
bs, reps(500): ivreg2 ....... y* (count_totstd=iv_totstd), gmm2s robust cluster(reporter) idcluste ...
谢谢连老师。
我按您说的方法,加上 “idcluster(reporter_new) first”后,仍出现原来的错误。
于是,我将这部分删除,采取下面的方法,运行没有错,但是运行结果没有显示Anderson-Rubin Wald 检验值。不知是不是,因为bs的估计方法,不提供“Anderson-Rubin Wald”。
.
. bs, reps(500): ivreg2 y x1 y* (z= z1), gmm2s robust first
(running ivreg2 on estimation sample)
Bootstrap replications (500)
----+--- 1 ---+--- 2 ---+--- 3 ---+--- 4 ---+--- 5
.................................................. 50
.................................................. 100
.................................................. 150
.................................................. 200
.................................................. 250
.................................................. 300
.................................................. 350
.................................................. 400
.................................................. 450
.................................................. 500
2-Step GMM estimation
---------------------
Estimates efficient for arbitrary heteroskedasticity
Statistics robust to heteroskedasticity
Number of obs = 608
F( 26, 581) = .
Prob > F = 0.0000
Total (centered) SS = 507.5005318 Centered R2 = 0.5221
Total (uncentered) SS = 514.0870761 Uncentered R2 = 0.5283
Residual SS = 242.5199484 Root MSE = .6316
--------------------------------------------------------------------------------
| Observed Bootstrap Normal-based
vaxstd | Coef. Std. Err. z P>|z| [95% Conf. Interval]
---------------+----------------------------------------------------------------
index_5std | .3481919 .0474836 7.33 0.000 .2551258 .441258
patentppstd | .2790811 .0433641 6.44 0.000 .194089 .3640732
ulcemrogdpstd | -.0731036 .0370796 -1.97 0.049 -.1457782 -.000429
hdi2std | -.7363774 .0677417 -10.87 0.000 -.8691487 -.6036061
cprkrostd | .1921824 .0266811 7.20 0.000 .1398883 .2444765
pholineperstd | .3175728 .0743951 4.27 0.000 .1717611 .4633846
kaopenstd | .0366594 .045494 0.81 0.420 -.0525073 .125826
fdisppstd | -1.276395 .1286474 -9.92 0.000 -1.528539 -1.02425
institutionstd | .1742323 .0462876 3.76 0.000 .0835102 .2649543
ge_stdstd | -.1809017 .0507326 -3.57 0.000 -.2803359 -.0814676
naturalppstd | .4147439 .0350878 11.82 0.000 .345973 .4835148
year | -.0858614 .0116817 -7.35 0.000 -.1087571 -.0629657
yr2 | -.2452203 .1559818 -1.57 0.116 -.5509389 .0604984
yr3 | -.1422074 .1417747 -1.00 0.316 -.4200807 .1356658
yr4 | -.1523671 .1553619 -0.98 0.327 -.4568709 .1521367
yr5 | -.0803987 .153399 -0.52 0.600 -.3810553 .2202579
yr6 | -.8444466 .1388781 -6.08 0.000 -1.116643 -.5722505
yr7 | -.3012124 .1495642 -2.01 0.044 -.5943528 -.008072
yr8 | -.136197 .1393368 -0.98 0.328 -.409292 .136898
yr9 | -.0610204 .1491291 -0.41 0.682 -.3533081 .2312673
yr10 | -.0451324 .1385267 -0.33 0.745 -.3166397 .2263749
yr11 | -.6744716 .1345687 -5.01 0.000 -.9382214 -.4107219
yr12 | -.08162 .1342406 -0.61 0.543 -.3447267 .1814867
yr13 | -.4146444 .1383386 -3.00 0.003 -.685783 -.1435058
yr14 | -.5459585 .1440208 -3.79 0.000 -.8282341 -.263683
yr15 | -.0161639 .1492949 -0.11 0.914 -.3087764 .2764486
_cons | 172.1667 23.38363 7.36 0.000 126.3356 217.9978
--------------------------------------------------------------------------------
Underidentification test (Kleibergen-Paap rk LM statistic): 233.339
Chi-sq(1) P-val = 0.0000
------------------------------------------------------------------------------
Weak identification test (Cragg-Donald Wald F statistic): 9074.220
(Kleibergen-Paap rk Wald F statistic): 1.1e+04
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.
------------------------------------------------------------------------------
Sargan statistic (overidentification test of all instruments): 0.000
(equation exactly identified)
------------------------------------------------------------------------------
Instrumented: index_5std
Included instruments: patentppstd ulcemrogdpstd hdi2std cprkrostd pholineperstd
kaopenstd fdisppstd institutionstd ge_stdstd naturalppstd
year yr2 yr3 yr4 yr5 yr6 yr7 yr8 yr9 yr10 yr11 yr12 yr13
yr14 yr15
Excluded instruments: iv_index_5std
Dropped collinear: yr16 yr17
------------------------------------------------------------------------------
**********
另外,如果不采用BS方法,采用普通的2sls回归,则会出现下面的运行结果:
Weak-instrument-robust inference
Tests of joint significance of endogenous regressors B1 in main equation
Ho: B1=0 and orthogonality conditions are valid
Anderson-Rubin Wald test F(1,581)= 58.96 P-val=0.0000
Anderson-Rubin Wald test Chi-sq(1)= 61.70 P-val=0.0000
Stock-Wright LM S statistic Chi-sq(1)= 49.26 P-val=0.0000
)))
不知什么原因呢?
麻烦了,谢谢!