天涯归宿 发表于 2018-6-1 17:27
楼主,你做的结果的接图有没有啊?
LM回归 判断使用哪种空间模型
先设定矩阵pweight.dta(如moran前几步)
spregsarxt s segin edu gdp tech pop, wmfile(pweight.dta) nc(31) lmspac
==============================================================================
*** Binary (0/1) Weight Matrix: 341x341 - NC=31 NT=11 (Non Normalized)
==============================================================================
initial: log likelihood = 56.876941
rescale: log likelihood = 56.876941
rescale eq: log likelihood = 56.876941
Iteration 0: log likelihood = 56.876941
Iteration 1: log likelihood = 60.853957
Iteration 2: log likelihood = 60.88959
Iteration 3: log likelihood = 60.889613
Iteration 4: log likelihood = 60.889613
==============================================================================
* MLE Spatial Lag Panel Normal Model (SAR)
==============================================================================
s = segin + edu + gdp + tech + pop
------------------------------------------------------------------------------
Sample Size = 341 | Cross Sections Number = 31
Wald Test = 805.4746 | P-Value > Chi2(5) = 0.0000
F-Test = 161.0949 | P-Value > F(5 , 305) = 0.0000
(Buse 1973) R2 = 0.7063 | Raw Moments R2 = 0.9579
(Buse 1973) R2 Adj = 0.6726 | Raw Moments R2 Adj = 0.9530
Root MSE (Sigma) = 0.1390 | Log Likelihood Function = 60.8896
------------------------------------------------------------------------------
- R2h= 0.3260 R2h Adj= 0.2486 F-Test = 32.40 P-Value > F(5 , 305) 0.0000
- R2v= 0.3123 R2v Adj= 0.2334 F-Test = 30.43 P-Value > F(5 , 305) 0.0000
------------------------------------------------------------------------------
s | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
s |
segin | .0186811 .1423101 0.13 0.896 -.2602416 .2976038
edu | .0147365 .0028604 5.15 0.000 .0091302 .0203427
gdp | -.0005648 .0301892 -0.02 0.985 -.0597345 .0586049
tech | .0164845 .0020312 8.12 0.000 .0125035 .0204654
pop | .0000213 7.97e-06 2.67 0.008 5.64e-06 .0000369
_cons | .392449 .2580654 1.52 0.128 -.1133499 .898248
-------------+----------------------------------------------------------------
/Rho | -.0280663 .0101534 -2.76 0.006 -.0479667 -.0081659
/Sigma | .2075909 .0081441 25.49 0.000 .1916287 .2235531
------------------------------------------------------------------------------
LR Test SAR vs. OLS (Rho=0): 7.6409 P-Value > Chi2(1) 0.0057
Acceptable Range for Rho: -0.5991 < Rho < 0.1586
------------------------------------------------------------------------------
==============================================================================
*** Spatial Panel Aautocorrelation Tests
==============================================================================
Ho: Error has No Spatial AutoCorrelation
Ha: Error has Spatial AutoCorrelation
- GLOBAL Moran MI = 0.2037 P-Value > Z( 6.412) 0.0000
- GLOBAL Geary GC = 0.8827 P-Value > Z(-2.584) 0.0098
- GLOBAL Getis-Ords GO = -1.0907 P-Value > Z(-6.412) 0.0000
------------------------------------------------------------------------------
- Moran MI Error Test = 1.5220 P-Value > Z(47.325) 0.1280
------------------------------------------------------------------------------
- LM Error (Burridge) = 31.2441 P-Value > Chi2(1) 0.0000
- LM Error (Robust) = 28.1051 P-Value > Chi2(1) 0.0000
------------------------------------------------------------------------------
Ho: Spatial Lagged Dependent Variable has No Spatial AutoCorrelation
Ha: Spatial Lagged Dependent Variable has Spatial AutoCorrelation
- LM Lag (Anselin) = 3.2034 P-Value > Chi2(1) 0.0735
- LM Lag (Robust) = 0.0644 P-Value > Chi2(1) 0.7997
------------------------------------------------------------------------------
Ho: No General Spatial AutoCorrelation
Ha: General Spatial AutoCorrelation
- LM SAC (LMErr+LMLag_R) = 31.3085 P-Value > Chi2(2) 0.0000
- LM SAC (LMLag+LMErr_R) = 31.3085 P-Value > Chi2(2) 0.0000
------------------------------------------------------------------------------