签到
- 苹果/安卓/wp
- 苹果/安卓/wp
客户端
0.0

0.00

人大经济论坛 › 论坛 › 计量经济学与统计论坛五区 › 计量经济学与统计软件 › Stata专版 › 求助：stata GMM正交矩阵参数向量组如何估计200论坛币

CDA数据分析研究院

商业数据分析与大数据领航教育品牌



经管云课堂

经管/金融/财会/社科/名师公开课



学术培训

Stata 空间计量 SSCI Python

贵宾：通行论坛特权+数据库权限
+案例库+下载特权 VIP：论坛特权+更多下载次数
+ccerdata数据库+更高阅读权限+……

提升主题| 本版置顶| 关闭主题| 变更主题颜色| 抢沙发| 顶贴| 道具中心

楼主: byl0002

3271 13

求助：stata GMM正交矩阵参数向量组如何估计200论坛币 [推广有奖]

11楼

herbertzhao 发表于 2011-10-16 10:31:50 |只看作者 |坛友微信交流群

对了，你要是可以舍弃掉开头和结尾几年的数据，只是用1992q1到2008q4的数据的话，igmm就可以顺利得出converged的结果。如下：

. gmm (d2: {gamma}/(1-{gamma})*var1 + {beta}*(var2^({theta}*{gamma})*var3^({theta}*(1-{gamma})-1)*var4)-1) (d1: {beta}*(var2^({theta}*{gamma})*var3^({theta}*(1-{gamma})-1)*var5)-1) in 9/76, instruments(L.var3 L.var2 L.var4 L2.var3 L2.var2 L2.var4 const) derivative(d2/gamma = var1/(1-{gamma})+{gamma}*var1/(1-{gamma})^2+{beta}*var2^({theta}*{gamma})*{theta}*ln(var2)*var3^({theta}*(1-{gamma})-1)*var4-{beta}*var2^({theta}*{gamma})*var3^({theta}*(1-{gamma})-1)*{theta}*ln(var3)*var4) derivative(d2/theta = var3^({theta}-{theta}*{gamma}-1)*var2^({theta}*{gamma})*{beta}*var4*({gamma}*ln(var2)+ln(var3)-ln(var3)*{gamma})) derivative(d2/beta = var2^({theta}*{gamma})*var3^({theta}*(1-{gamma})-1)*var4) derivative(d1/theta = var3^({theta}-{theta}*{gamma}-1)*var2^({theta}*{gamma})*{beta}*var5*({gamma}*ln(var2)+ln(var3)-ln(var3)*{gamma})) derivative(d1/gamma = var3^({theta}-{theta}*{gamma}-1)*var2^({theta}*{gamma})*{beta}*{theta}*var5*(ln(var2)-ln(var3))) derivative(d1/beta = var2^({theta}*{gamma})*var3^({theta}*(1-{gamma})-1)*var5) winitial(identity) igmm
Step 1
Iteration 0: GMM criterion Q(b) = 13.140639
Iteration 1: GMM criterion Q(b) = 7.7166832
Iteration 2: GMM criterion Q(b) = 2.8734317
Iteration 3: GMM criterion Q(b) = 1.4045888
Iteration 4: GMM criterion Q(b) = .49684021
Iteration 5: GMM criterion Q(b) = .48986374
(中间省略一部分)
Iteration 216: GMM criterion Q(b) = .06870718
Iteration 217: GMM criterion Q(b) = .06869991
Iteration 218: GMM criterion Q(b) = .06869682
Iteration 219: GMM criterion Q(b) = .06865441
Iteration 220: GMM criterion Q(b) = .06865439 (backed up)
Iteration 221: GMM criterion Q(b) = .06865437 (backed up)
Iteration 222: GMM criterion Q(b) = .06865435 (backed up)
Iteration 223: GMM criterion Q(b) = .06865432 (backed up)
Iteration 224: GMM criterion Q(b) = .06865432 (backed up)
Iteration 225: GMM criterion Q(b) = .0686543 (backed up)
Iteration 226: GMM criterion Q(b) = .06865428 (backed up)
Iteration 227: GMM criterion Q(b) = .06865425 (backed up)
Iteration 228: GMM criterion Q(b) = .06865421 (backed up)
Iteration 229: GMM criterion Q(b) = .0686542 (backed up)
Iteration 230: GMM criterion Q(b) = .06865416 (backed up)
Iteration 231: GMM criterion Q(b) = .06865408 (backed up)
Iteration 232: GMM criterion Q(b) = .06865402 (backed up)
Iteration 233: GMM criterion Q(b) = .06865389
Iteration 234: GMM criterion Q(b) = .06865273
Iteration 235: GMM criterion Q(b) = .06865228
Iteration 236: GMM criterion Q(b) = .06864575
Iteration 237: GMM criterion Q(b) = .06864575 (backed up)
Step 2
Iteration 0: GMM criterion Q(b) = .772565
Iteration 1: GMM criterion Q(b) = .76588042
Iteration 2: GMM criterion Q(b) = .76536615
Iteration 3: GMM criterion Q(b) = .76502331
Iteration 4: GMM criterion Q(b) = .764702
Iteration 5: GMM criterion Q(b) = .76458672
Iteration 6: GMM criterion Q(b) = .76457052
Iteration 7: GMM criterion Q(b) = .76455907
Iteration 8: GMM criterion Q(b) = .76455127
Iteration 9: GMM criterion Q(b) = .76454617
Iteration 10: GMM criterion Q(b) = .76454305
Iteration 11: GMM criterion Q(b) = .76454111
Iteration 12: GMM criterion Q(b) = .76453995
Iteration 13: GMM criterion Q(b) = .76453925
Iteration 14: GMM criterion Q(b) = .76453884
Iteration 15: GMM criterion Q(b) = .7645386
Iteration 16: GMM criterion Q(b) = .76453845
Step 3
Iteration 0: GMM criterion Q(b) = .76558358
Iteration 1: GMM criterion Q(b) = .76253791
Iteration 2: GMM criterion Q(b) = .76250851
Iteration 3: GMM criterion Q(b) = .76248824
Iteration 4: GMM criterion Q(b) = .76247426
Iteration 5: GMM criterion Q(b) = .76247105
Iteration 6: GMM criterion Q(b) = .76246646
Iteration 7: GMM criterion Q(b) = .76246473
Iteration 8: GMM criterion Q(b) = .76246311
Iteration 9: GMM criterion Q(b) = .76246237
Iteration 10: GMM criterion Q(b) = .76246181
Iteration 11: GMM criterion Q(b) = .76246151
Iteration 12: GMM criterion Q(b) = .76246131
Iteration 13: GMM criterion Q(b) = .7624612
Step 4
Iteration 0: GMM criterion Q(b) = .76192997
Iteration 1: GMM criterion Q(b) = .76102659
Iteration 2: GMM criterion Q(b) = .76102288
Iteration 3: GMM criterion Q(b) = .76102155
Iteration 4: GMM criterion Q(b) = .76102087
Iteration 5: GMM criterion Q(b) = .76102061
Iteration 6: GMM criterion Q(b) = .76102047
Step 5
Iteration 0: GMM criterion Q(b) = .76049656
Iteration 1: GMM criterion Q(b) = .76006059
Iteration 2: GMM criterion Q(b) = .76005953
Iteration 3: GMM criterion Q(b) = .76005919
Iteration 4: GMM criterion Q(b) = .76005906
Step 6
Iteration 0: GMM criterion Q(b) = .75957112
Iteration 1: GMM criterion Q(b) = .75932708
Iteration 2: GMM criterion Q(b) = .75932664
Iteration 3: GMM criterion Q(b) = .75932651
Step 7
Iteration 0: GMM criterion Q(b) = .75890378
Iteration 1: GMM criterion Q(b) = .75876722
Iteration 2: GMM criterion Q(b) = .75876717
Step 8
Iteration 0: GMM criterion Q(b) = .75846541
Iteration 1: GMM criterion Q(b) = .75839066
Iteration 2: GMM criterion Q(b) = .75839056
Step 9
Iteration 0: GMM criterion Q(b) = .75815059
Iteration 1: GMM criterion Q(b) = .75810977
Iteration 2: GMM criterion Q(b) = .75810969
Step 10
Iteration 0: GMM criterion Q(b) = .75792487
Iteration 1: GMM criterion Q(b) = .75790265
Iteration 2: GMM criterion Q(b) = .7579026
Step 11
Iteration 0: GMM criterion Q(b) = .75776284
Iteration 1: GMM criterion Q(b) = .75775078
Iteration 2: GMM criterion Q(b) = .75775075
Step 12
Iteration 0: GMM criterion Q(b) = .75764622
Iteration 1: GMM criterion Q(b) = .75763969
Iteration 2: GMM criterion Q(b) = .75763967
Step 13
Iteration 0: GMM criterion Q(b) = .75756201
Iteration 1: GMM criterion Q(b) = .75755848
Iteration 2: GMM criterion Q(b) = .75755847
Step 14
Iteration 0: GMM criterion Q(b) = .75750101
Iteration 1: GMM criterion Q(b) = .75749911
Iteration 2: GMM criterion Q(b) = .75749911
Step 15
Iteration 0: GMM criterion Q(b) = .75745672
Iteration 1: GMM criterion Q(b) = .75745569
Iteration 2: GMM criterion Q(b) = .75745569
Step 16
Iteration 0: GMM criterion Q(b) = .75742448
Iteration 1: GMM criterion Q(b) = .75742393
Iteration 2: GMM criterion Q(b) = .75742393
Step 17
Iteration 0: GMM criterion Q(b) = .75740098
Iteration 1: GMM criterion Q(b) = .75740068
Iteration 2: GMM criterion Q(b) = .75740068
Step 18
Iteration 0: GMM criterion Q(b) = .75738382
Iteration 1: GMM criterion Q(b) = .75738366
Step 19
Iteration 0: GMM criterion Q(b) = .75736995
Iteration 1: GMM criterion Q(b) = .75736986
Step 20
Iteration 0: GMM criterion Q(b) = .75736164
Iteration 1: GMM criterion Q(b) = .7573616
Step 21
Iteration 0: GMM criterion Q(b) = .75735475
Iteration 1: GMM criterion Q(b) = .75735473
Step 22
Iteration 0: GMM criterion Q(b) = .7573501
Iteration 1: GMM criterion Q(b) = .75735009
Step 23
Iteration 0: GMM criterion Q(b) = .75734654
Iteration 1: GMM criterion Q(b) = .75734653
Step 24
Iteration 0: GMM criterion Q(b) = .75734401
Iteration 1: GMM criterion Q(b) = .75734401
Step 25
Iteration 0: GMM criterion Q(b) = .75734213
Iteration 1: GMM criterion Q(b) = .75734213
Step 26
Iteration 0: GMM criterion Q(b) = .75734077
Iteration 1: GMM criterion Q(b) = .75734077
Step 27
Iteration 0: GMM criterion Q(b) = .75733977
Iteration 1: GMM criterion Q(b) = .75733977
Step 28
Iteration 0: GMM criterion Q(b) = .75733905
Iteration 1: GMM criterion Q(b) = .75733905
Step 29
Iteration 0: GMM criterion Q(b) = .75733851
Iteration 1: GMM criterion Q(b) = .75733851
Step 30
Iteration 0: GMM criterion Q(b) = .75733812
Iteration 1: GMM criterion Q(b) = .75733812
Step 31
Iteration 0: GMM criterion Q(b) = .75733784
Iteration 1: GMM criterion Q(b) = .75733784
Step 32
Iteration 0: GMM criterion Q(b) = .75733763
Iteration 1: GMM criterion Q(b) = .75733763
Step 33
Iteration 0: GMM criterion Q(b) = .75733748
Iteration 1: GMM criterion Q(b) = .75733748
Step 34
Iteration 0: GMM criterion Q(b) = .75733737
Iteration 1: GMM criterion Q(b) = .75733737
iterative GMM weight matrix converged
iterative GMM parameter vector converged
GMM estimation
Number of parameters = 3
Number of moments = 16
Initial weight matrix: Identity Number of obs = 68
GMM weight matrix: Robust
------------------------------------------------------------------------------
| Robust
| Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
/gamma | .7694751 .0229652 33.51 0.000 .7244641 .8144862
/beta | -.0130816 .0445299 -0.29 0.769 -.1003586 .0741954
/theta | -22.30377 16.25333 -1.37 0.170 -54.15971 9.552167
------------------------------------------------------------------------------
Instruments for equation 1: L.var3 L.var2 L.var4 L2.var3 L2.var2 L2.var4 const _cons
Instruments for equation 2: L.var3 L.var2 L.var4 L2.var3 L2.var2 L2.var4 const _cons

复制代码

点我我有惊喜！！

回复

使用道具举报

12楼

herbertzhao 发表于 2011-10-16 10:34:11 |只看作者 |坛友微信交流群

哦，另外，我之前都explicitly的加了const作为Z的一部分。但是其实stata自己会加上_cons的，所以那个const可以不用。

好啦~顺利完成了~88

点我我有惊喜！！

回复

使用道具举报

13楼

herbertzhao 发表于 2011-10-16 10:35:05 |只看作者 |坛友微信交流群

对了，我当休闲娱乐做的。错了不负任何责任。而且再声明一次我不是搞宏观的。

点我我有惊喜！！

回复

使用道具举报

14楼

byl0002 发表于 2011-10-16 17:35:19 |只看作者 |坛友微信交流群

太谢谢你了，留个联系方式吧！给你点报酬，也交个朋友！

回复

使用道具举报

发帖

本版微信群

加好友,备注jltj
拉您入交流群

如有投资本站、合作意向或投放广告，请联系：13661292478（刘老师）

联系客服

邮箱：service@pinggu.org 投诉或不良信息处理：（010-68466864）

京ICP备16021002-2号京B2-20170662号京公网安备 11010802022788号论坛法律顾问：王进律师知识产权保护声明免责及隐私声明