[求助]关于随机效应和固定效应的选择问题以及异方差问题

10316

收藏 2008-02-28

1.问题1:在做HAUSMAN 检验时,结果接受原假设,按通常情况应选择随机效应,但是在做随机效应检验时,结果随机效应不明显,请问最终我应该选择哪一个模型.结果如下:. hausman fe reNote: the rank of the differenced variance matrix (13) does not equal the number of coefficients &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; being tested (14); be sure this is what you expect, or there may be problems computing the &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; test.&nbsp; Examine the output of your estimators for anything unexpected and possibly consider &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; scaling your variables so that the coefficients are on a similar scale.&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; ---- Coefficients ---- &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; |&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; (b)&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; (B)&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; (b-B)&nbsp;&nbsp;&nbsp;&nbsp; sqrt(diag(V_b-V_B)) &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; |&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; fe&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; re&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; Difference&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; S.E. -------------+---------------------------------------------------------------- &nbsp;&nbsp;&nbsp;&nbsp; revenue |&nbsp;&nbsp; -8.13e-12&nbsp;&nbsp;&nbsp; -5.15e-12&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; -2.98e-12&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 4.85e-12 &nbsp;compitition |&nbsp;&nbsp;&nbsp; .0029883&nbsp;&nbsp;&nbsp;&nbsp; .0015715&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; .0014169&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; .0010272 &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; fdi |&nbsp;&nbsp; -.0007191&nbsp;&nbsp;&nbsp; -.0019479&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; .0012288&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; .0025933 &nbsp;&nbsp;&nbsp;&nbsp; techgap |&nbsp;&nbsp; -.0016343&nbsp;&nbsp;&nbsp; -.0012345&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; -.0003998&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; .0009293 &nbsp;newproducts |&nbsp;&nbsp;&nbsp; .0044084&nbsp;&nbsp;&nbsp;&nbsp; .0008903&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; .0035181&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; .002783 _iinnxnewp~2 |&nbsp;&nbsp; -.0012093&nbsp;&nbsp;&nbsp; -.0035233&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; .002314&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; .0055937 _iinnxnewp~3 |&nbsp;&nbsp; -.0093128&nbsp;&nbsp;&nbsp;&nbsp; .0017929&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; -.0111058&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; .008412 _iinnxnewp~4 |&nbsp;&nbsp;&nbsp; .0060063&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; .005543&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; .0004633&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; .0073138 _iinnxtech~2 |&nbsp;&nbsp; -.0046144&nbsp;&nbsp;&nbsp; -.0022538&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; -.0023606&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; .0020646 _iinnxtech~3 |&nbsp;&nbsp;&nbsp; .0020085&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; .004613&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; -.0026045&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; .0025665 _iinnxtech~4 |&nbsp;&nbsp;&nbsp; .0031592&nbsp;&nbsp;&nbsp;&nbsp; .0015289&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; .0016303&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; .0023775 _Iinnovati~2 |&nbsp;&nbsp;&nbsp; .0034137&nbsp;&nbsp;&nbsp;&nbsp; .0020687&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; .001345&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; .0017113 _Iinnovati~3 |&nbsp;&nbsp;&nbsp; .0013863&nbsp;&nbsp;&nbsp;&nbsp; -.002063&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; .0034493&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; .0029152 _Iinnovati~4 |&nbsp;&nbsp;&nbsp; -.002214&nbsp;&nbsp;&nbsp; -.0011794&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; -.0010346&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; .0012532 ------------------------------------------------------------------------------ &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; b = consistent under Ho and Ha; obtained from xtreg &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; B = inconsistent under Ha, efficient under Ho; obtained from xtreg&nbsp;&nbsp;&nbsp; Test:&nbsp; Ho:&nbsp; difference in coefficients not systematic&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; chi2(13) = (b-B)'[(V_b-V_B)^(-1)](b-B) &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; =&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 14.69 &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; Prob&gt;chi2 =&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 0.3269 &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; (V_b-V_B is not positive definite). xttest0Breusch and Pagan Lagrangian multiplier test for random effects:&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; patent[industry,t] = Xb + u[industry] + e[industry,t]&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; Estimated results: &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; |&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; Var&nbsp;&nbsp;&nbsp;&nbsp; sd = sqrt(Var) &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; ---------+----------------------------- &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; patent |&nbsp;&nbsp; 1.39e-06&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; .0011792 &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; e |&nbsp;&nbsp; 8.95e-07&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; .0009461 &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; u |&nbsp;&nbsp; 2.12e-07&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; .00046&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; Test:&nbsp;&nbsp; Var(u) = 0 &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; chi2(1) =&nbsp;&nbsp;&nbsp;&nbsp; 2.77 &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; Prob &gt; chi2 =&nbsp;&nbsp;&nbsp;&nbsp; 0.09602.问题2:在考虑PANEL DATA 回归的异方差问题上,固定效应的异方差可以用XTTEST3来检验,随机效应的异方差应怎么检验,&nbsp; 随机效应模型<span style="; COLOR: red; FONT-FAMILY: &quot;Times New Roman&quot;; mso-bidi-; mso-font-kerning: 1.0pt; mso-ansi-language: EN-US; mso-fareast-language: ZH-CN; mso-bidi-language: AR-SA; mso-fareast-font-family: 宋体;">&nbsp;<span lang="EN-US" style="; FONT-FAMILY: &quot;Times New Roman&quot;; mso-bidi-; mso-font-kerning: 1.0pt; mso-ansi-language: EN-US; mso-fareast-language: ZH-CN; mso-bidi-language: AR-SA; mso-fareast-font-family: 宋体;">yit<span lang="EN-US" style="; FONT-FAMILY: &quot;Times New Roman&quot;; mso-bidi-; mso-font-kerning: 1.0pt; mso-ansi-language: EN-US; mso-fareast-language: ZH-CN; mso-bidi-language: AR-SA; mso-fareast-font-family: 宋体;"> = <span lang="EN-US" style="; FONT-FAMILY: Symbol; mso-bidi-; mso-ascii-font-family: 'Times New Roman'; mso-hansi-font-family: 'Times New Roman'; mso-bidi-font-family: 'Times New Roman'; mso-font-kerning: 1.0pt; mso-ansi-language: EN-US; mso-fareast-language: ZH-CN; mso-bidi-language: AR-SA; mso-fareast-font-family: 宋体; mso-char-type: symbol; mso-symbol-font-family: Symbol;">a<span lang="EN-US" style="; FONT-FAMILY: &quot;Times New Roman&quot;; mso-bidi-; mso-font-kerning: 1.0pt; mso-ansi-language: EN-US; mso-fareast-language: ZH-CN; mso-bidi-language: AR-SA; mso-fareast-font-family: 宋体;"> &nbsp;&nbsp;&nbsp;&nbsp;<span lang="EN-US" style="; FONT-FAMILY: &quot;Times New Roman&quot;; mso-bidi-; mso-font-kerning: 1.0pt; mso-ansi-language: EN-US; mso-fareast-language: ZH-CN; mso-bidi-language: AR-SA; mso-fareast-font-family: 宋体;">+ <span lang="EN-US" style="; FONT-FAMILY: Symbol; mso-bidi-; mso-ascii-font-family: 'Times New Roman'; mso-hansi-font-family: 'Times New Roman'; mso-bidi-font-family: 'Times New Roman'; mso-font-kerning: 1.0pt; mso-ansi-language: EN-US; mso-fareast-language: ZH-CN; mso-bidi-language: AR-SA; mso-fareast-font-family: 宋体; mso-char-type: symbol; mso-symbol-font-family: Symbol;">b<span lang="EN-US" style="; FONT-FAMILY: &quot;Times New Roman&quot;; mso-bidi-; mso-font-kerning: 1.0pt; mso-ansi-language: EN-US; mso-fareast-language: ZH-CN; mso-bidi-language: AR-SA; mso-fareast-font-family: 宋体;">1 <span lang="EN-US" style="; FONT-FAMILY: &quot;Times New Roman&quot;; mso-bidi-; mso-font-kerning: 1.0pt; mso-ansi-language: EN-US; mso-fareast-language: ZH-CN; mso-bidi-language: AR-SA; mso-fareast-font-family: 宋体;">xit <span lang="EN-US" style="; FONT-FAMILY: &quot;Times New Roman&quot;; mso-bidi-; mso-font-kerning: 1.0pt; mso-ansi-language: EN-US; mso-fareast-language: ZH-CN; mso-bidi-language: AR-SA; mso-fareast-font-family: 宋体;">+ <span lang="EN-US" style="; FONT-FAMILY: Symbol; mso-bidi-; mso-ascii-font-family: 'Times New Roman'; mso-hansi-font-family: 'Times New Roman'; mso-bidi-font-family: 'Times New Roman'; mso-font-kerning: 1.0pt; mso-ansi-language: EN-US; mso-fareast-language: ZH-CN; mso-bidi-language: AR-SA; mso-fareast-font-family: 宋体; mso-char-type: symbol; mso-symbol-font-family: Symbol;">e<span lang="EN-US" style="; FONT-FAMILY: &quot;Times New Roman&quot;; mso-bidi-; mso-font-kerning: 1.0pt; mso-ansi-language: EN-US; mso-fareast-language: ZH-CN; mso-bidi-language: AR-SA; mso-fareast-font-family: 宋体;">it<span lang="EN-US" style="; FONT-FAMILY: &quot;Times New Roman&quot;; mso-bidi-; mso-font-kerning: 1.0pt; mso-ansi-language: EN-US; mso-fareast-language: ZH-CN; mso-bidi-language: AR-SA; mso-fareast-font-family: 宋体;">&nbsp;&nbsp;<span lang="EN-US" style="; FONT-FAMILY: &quot;Times New Roman&quot;; mso-bidi-; mso-font-kerning: 1.0pt; mso-ansi-language: EN-US; mso-fareast-language: ZH-CN; mso-bidi-language: AR-SA; mso-fareast-font-family: 宋体;">&nbsp;<span lang="EN-US" style="; FONT-FAMILY: &quot;Times New Roman&quot;; mso-bidi-; mso-font-kerning: 1.0pt; mso-ansi-language: EN-US; mso-fareast-language: ZH-CN; mso-bidi-language: AR-SA; mso-fareast-font-family: 宋体;">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; <span lang="EN-US" style="; FONT-FAMILY: Symbol; mso-bidi-; mso-ascii-font-family: 'Times New Roman'; mso-hansi-font-family: 'Times New Roman'; mso-bidi-font-family: 'Times New Roman'; mso-font-kerning: 1.0pt; mso-ansi-language: EN-US; mso-fareast-language: ZH-CN; mso-bidi-language: AR-SA; mso-fareast-font-family: 宋体; mso-char-type: symbol; mso-symbol-font-family: Symbol;">e<span lang="EN-US" style="; FONT-FAMILY: &quot;Times New Roman&quot;; mso-bidi-; mso-font-kerning: 1.0pt; mso-ansi-language: EN-US; mso-fareast-language: ZH-CN; mso-bidi-language: AR-SA; mso-fareast-font-family: 宋体;">it<span lang="EN-US" style="; FONT-FAMILY: &quot;Times New Roman&quot;; mso-bidi-; mso-font-kerning: 1.0pt; mso-ansi-language: EN-US; mso-fareast-language: ZH-CN; mso-bidi-language: AR-SA; mso-fareast-font-family: 宋体;"> = ui + vt + wit&nbsp;&nbsp;&nbsp;&nbsp; <span lang="EN-US" style="; FONT-FAMILY: &quot;Times New Roman&quot;; mso-bidi-; mso-font-kerning: 1.0pt; mso-ansi-language: EN-US; mso-fareast-language: ZH-CN; mso-bidi-language: AR-SA; mso-fareast-font-family: 宋体;"><span lang="EN-US" style="; FONT-FAMILY: &quot;Times New Roman&quot;; mso-bidi-; mso-font-kerning: 1.0pt; mso-ansi-language: EN-US; mso-fareast-language: ZH-CN; mso-bidi-language: AR-SA; mso-fareast-font-family: 宋体;">这里要检验的是<span lang="EN-US" style="; FONT-FAMILY: Symbol; mso-bidi-; mso-ascii-font-family: 'Times New Roman'; mso-hansi-font-family: 'Times New Roman'; mso-bidi-font-family: 'Times New Roman'; mso-font-kerning: 1.0pt; mso-ansi-language: EN-US; mso-fareast-language: ZH-CN; mso-bidi-language: AR-SA; mso-fareast-font-family: 宋体; mso-char-type: symbol; mso-symbol-font-family: Symbol;">eit&nbsp;&nbsp;&nbsp;还是 wit&nbsp;&nbsp;&nbsp;&nbsp; ?<span lang="EN-US" style="; FONT-FAMILY: &quot;Times New Roman&quot;; mso-bidi-; mso-font-kerning: 1.0pt; mso-ansi-language: EN-US; mso-fareast-language: ZH-CN; mso-bidi-language: AR-SA; mso-fareast-font-family: 宋体;"><span lang="EN-US" style="; FONT-FAMILY: &quot;Times New Roman&quot;; mso-bidi-; mso-font-kerning: 1.0pt; mso-ansi-language: EN-US; mso-fareast-language: ZH-CN; mso-bidi-language: AR-SA; mso-fareast-font-family: 宋体;">如果要检验的是<span lang="EN-US" style="; FONT-FAMILY: Symbol; mso-bidi-; mso-ascii-font-family: 'Times New Roman'; mso-hansi-font-family: 'Times New Roman'; mso-bidi-font-family: 'Times New Roman'; mso-font-kerning: 1.0pt; mso-ansi-language: EN-US; mso-fareast-language: ZH-CN; mso-bidi-language: AR-SA; mso-fareast-font-family: 宋体; mso-char-type: symbol; mso-symbol-font-family: Symbol;">eit&nbsp;&nbsp;,是否可以用普通回归然后用WHITEST来检验?<span lang="EN-US" style="; FONT-FAMILY: &quot;Times New Roman&quot;; mso-bidi-; mso-font-kerning: 1.0pt; mso-ansi-language: EN-US; mso-fareast-language: ZH-CN; mso-bidi-language: AR-SA; mso-fareast-font-family: 宋体;"><span lang="EN-US" style="; FONT-FAMILY: &quot;Times New Roman&quot;; mso-bidi-; mso-font-kerning: 1.0pt; mso-ansi-language: EN-US; mso-fareast-language: ZH-CN; mso-bidi-language: AR-SA; mso-fareast-font-family: 宋体;">谢谢各位:)

[此贴子已经被作者于2008-2-28 20:51:07编辑过]

扫码加我拉你入群

请注明：姓名-公司-职位

以便审核进群资格，未注明则拒绝

全部回复

duncan_zheng

2008-3-6 15:17:00

难度

扫码加我拉你入群

请注明：姓名-公司-职位

以便审核进群资格，未注明则拒绝

xjtuchan

2008-12-12 17:12:00

是不是xttest1啊？

但是这个命令只能用于balanced panel data.对于unbalanced panel data就不知道怎么办了~

头大的很！

扫码加我拉你入群

请注明：姓名-公司-职位

以便审核进群资格，未注明则拒绝

wbzdwss

2009-1-4 15:25:00

(a)以F统计量比较混合最小二乘法与固定效应模型，原假设为不存在固定效应；(b)以Breusch和Pagan的拉格朗日乘子(LM)检验来比较混合最小二乘法与随机效应模型，原假设为不存在随机效应；(c)以Hausman(H)检验来比较固定效应模型与随机效应模型，原假设为随机效应的设定条件得到满足。若(a)(b)中的检验都不显著（即不能拒绝原假设），则选用混合最小二乘法；若(a)(b)中的检验至少有1个显著（即拒绝原假设），则进入检验(c)，若不显著，则选用随机效应模型，否则选用固定效应模型。

扫码加我拉你入群

请注明：姓名-公司-职位

以便审核进群资格，未注明则拒绝

565272151

2009-1-10 20:13:00

无论原假设成立与否，FE都是一致的，然而，在原假设成立时，RE比FE更有效。既然p值大于置信值a接受原假设，所以用RE较好。

扫码加我拉你入群

请注明：姓名-公司-职位

以便审核进群资格，未注明则拒绝

teresayou

2009-1-20 20:47:00

我的情况是

1. FE 回归结果最后一行如下

F test that all u_i=0: F(3118, 5764) = 0.92 Prob > F = 0.9945
因此OLS 优于FE

2. BREUSCH PAGAN LM 检验结果如下

Breusch and Pagan Lagrangian multiplier test for random effects

consumption_lag[hhid,t] = Xb + u[hhid] + e[hhid,t]

Estimated results:
  Var     sd = sqrt(Var)
  ---------+-----------------------------
  consump~g    1.42e+07       3770.974
  e     7356042       2712.202
u     1442900       1201.208

  Test:   Var(u) = 0
chi2(1) =   375.39
  Prob > chi2 =     0.0000

因此RE 由于OLS

3. 按4楼的建议进行HAUSMAN 检验, 结果如下

. hausman FE RE

Note: the rank of the differenced variance matrix (4) does not equal the number of
coefficients being tested (5); be sure this is what you expect, or there may be
problems computing the test. Examine the output of your estimators for anything
unexpected and possibly consider scaling your variables so that the coefficients
are on a similar scale.

---- Coefficients ----
(b) (B) (b-B) sqrt(diag(V_b-V_B))
FE RE Difference S.E.

income_lag     .3848475     .4055527       -.0207053         .003818
income_ins~g     .0661347    -.0134085        .0795432         .008158
insurance_~g    -149.3701    -14.11473       -135.2554        45.22008
hhsize_lag     119.9776     120.7448       -.7671836        15.90935
hhage_lag     7.107392     5.392909        1.714483        2.090247

b = consistent under Ho and Ha; obtained from xtreg
B = inconsistent under Ha, efficient under Ho; obtained from xtreg

Test: Ho: difference in coefficients not systematic

chi2(4) = (b-B)'[(V_b-V_B)^(-1)](b-B)
= 96.40
Prob>chi2 = 0.0000

H0 被拒绝, 应选FE.

但这是不是有点矛盾呢. 前两个实验结果显示 OLS 优于FE 以及 RE 优于OLS, 最后我却选了FE

多谢解答!

扫码加我拉你入群

请注明：姓名-公司-职位

以便审核进群资格，未注明则拒绝

点击查看更多内容…

扫码加我 拉你入群

扫码加我 拉你入群

扫码加我 拉你入群

扫码加我 拉你入群

扫码加我 拉你入群

扫码加我 拉你入群

扫码加我 拉你入群

扫码加我 拉你入群

扫码加我 拉你入群

扫码加我 拉你入群

扫码加我 拉你入群

分享

扫码加好友，拉您进群

扫码加我拉你入群

扫码加我拉你入群

扫码加我拉你入群

扫码加我拉你入群

扫码加我拉你入群

扫码加我拉你入群

扫码加我拉你入群

扫码加我拉你入群

扫码加我拉你入群

扫码加我拉你入群

扫码加我拉你入群