1、随机效应模型情况下,如果有变量的参数不显著时,hausman检验有效不,以下是随机效应的结果:
Dependent Variable: LOG(EX?)
Method: Pooled EGLS (Cross-section random effects)
Date: 03/16/10 Time: 15:34
Sample: 1996 2008
Included observations: 13
Cross-sections included: 27
Total pool (balanced) observations: 351
Swamy and Arora estimator of component variances
Variable Coefficient Std. Error t-Statistic Prob.
C -33.66431 4.754878 -7.079952 0.0000
LOG(RJGDP?) 1.036394 0.183526 5.647111 0.0000
LOG(SCPCL?) 4.973280 0.453128 10.97544 0.0000
LOG(DIS?) -1.581683 0.408873 -3.868395 0.0001
D2? -1.003344 0.349901 -2.867509 0.0044
Random Effects (Cross)
JAPAN--C 1.500218
USA--C 4.249477
REPKOREA--C 0.094872
GERMANY--C 1.431548
UK--C 0.617836
SPAIN--C 1.246089
CANADA--C 2.044952
NERTHERLANDS--C -0.036543
FRANCE--C 0.414250
RUSSIAN--C 1.367327
POLAND--C 0.376017
PORTUGAL--C -0.488071
THAILAND--C 0.628750
MALAYSIA--C 0.471181
PHILIPPINES--C 0.284563
ITALY--C -1.062721
SWEDEN--C -1.563098
DENMARK--C -2.122384
AUSTRALIA--C -0.301839
INDONESIA--C 1.066160
ISRAEL--C -3.001967
SINGAPORE--C -1.338435
NEWZEALAND--C -1.401194
GREECE--C -1.796534
NORWAY--C -3.285261
MEXICO--C 0.889711
VIETNAM--C -0.284902
Effects Specification
S.D. Rho
Cross-section random 1.506125 0.7606
Idiosyncratic random 0.844925 0.2394
Weighted Statistics
R-squared 0.557616 Mean dependent var 0.411192
Adjusted R-squared 0.552502 S.D. dependent var 1.280519
S.E. of regression 0.856607 Sum squared resid 253.8862
F-statistic 109.0315 Durbin-Watson stat 0.647789
Prob(F-statistic) 0.000000
Unweighted Statistics
R-squared 0.295889 Mean dependent var 2.674569
Sum squared resid 1166.856 Durbin-Watson stat 0.140947
2、PANAL DATA中DW值与意义不


雷达卡



京公网安备 11010802022788号







