各位师兄师姐 各位达人 大家好 我用stata做了面板门限,我研究的是xx对yy的影响,
我认为当gdp小于一个门限值时,xx对yy的影响和gdp大于该门限值时 xx对yy的影响不同,问题的关键是这个不同在回归结果中如何看出?
xtptm yy jck fdi , rx(xx) thrvar(gdp) regime(2) iters(200) grid(30)
================ Single threshold regession: ===================
Minimized Sum of Squared Residuals: 8.41e+05
Standard error of residuals: 64.9969
Threshold estimator: 2.15e+04
95% conf. intv. of threshold: 2.15e+04 2.31e+04 这是什么意思
LR Critical value to test gamma=gamma0: 7.3523 这是什么意思
Threshold regression(Ordinary Std. Error):
----------------------------------------------------
| Coef Std t prob
----+-----------------------------------------------
1 | -234.0098 56.3942 -4.1495 0.0000
2 | -22.6750 313.2640 -0.0724 0.9424
3 | -16.8684 18.9967 -0.8880 0.3756
4 | 714.2660 100.1381 7.1328 0.0000
----------------------------------------------------
Threshold regression(Robust Std. Error):
-----------------------------------------------------
| Coef Std_Robust t prob
----+------------------------------------------------
1 | -234.0098 79.7452 -2.9345 0.0037
2 | -22.6750 353.9952 -0.0641 0.9490
3 | -16.8684 9.0919 -1.8553 0.0650
4 | 714.2660 201.4968 3.5448 0.0005
-----------------------------------------------------
Note: Critcal (Inverse CDF of LR stat): -2*ln(1-sqrt(1-alpha))
Ho: No threshold; Ha: Single threshold
Number of bootstrap: 200
F-stat & Prob: 56.7975 0.0000
F-critical value of 90% 95% 99%:
1
+---------------+
1 | 1.846513044 |
2 | 3.010170885 |
3 | 6.414076603 |
+---------------+
Thresholds in single model:
21548.9935
============ Double threshold regession: stage = 1
Minimized Sum of Squared Residuals: 7.97e+05
Standard error of residuals: 63.4313
Threshold estimate: 1.62e+04
95% conf. int. of threshold: 1.62e+04 2.00e+04
Two Thresholds: 1.62e+04 2.15e+04
Threshold regression(Ordinary Std. Err.):
----------------------------------------------------
| Coef Std t prob
----+-----------------------------------------------
1 | -246.2579 55.1602 -4.4644 0.0000
2 | -84.1014 306.2815 -0.2746 0.7839
3 | -18.3136 18.5443 -0.9876 0.3246
4 | 227.6340 76.1958 2.9875 0.0032
5 | 881.1814 109.9816 8.0121 0.0000
----------------------------------------------------
Threshold regression(Robust Std. Err.):
-----------------------------------------------------
| Coef Std_Robust t prob
----+------------------------------------------------
1 | -246.2579 79.7071 -3.0895 0.0023
2 | -84.1014 372.7654 -0.2256 0.8217
3 | -18.3136 9.6511 -1.8976 0.0592
4 | 227.6340 111.7706 2.0366 0.0430
5 | 881.1814 239.7495 3.6754 0.0003
-----------------------------------------------------
============ Double threshold regession: stage = 2
Minimized Sum of Squared Residuals: 7.97e+05
Standard error of residuals: 63.4313
Threshold estimate: 2.15e+04
95% conf. int. of threshold: 2.15e+04 2.31e+04
Two Thresholds: 1.62e+04 2.15e+04
Threshold regression(Ordinary Std. Err.):
----------------------------------------------------
| Coef Std t prob
----+-----------------------------------------------
1 | -246.2579 55.1602 -4.4644 0.0000
2 | -84.1014 306.2815 -0.2746 0.7839
3 | -18.3136 18.5443 -0.9876 0.3246
4 | 227.6340 76.1958 2.9875 0.0032
5 | 881.1814 109.9816 8.0121 0.0000
----------------------------------------------------
Threshold regression(Robust Std. Err.):
-----------------------------------------------------
| Coef Std_Robust t prob
----+------------------------------------------------
1 | -246.2579 79.7071 -3.0895 0.0023
2 | -84.1014 372.7654 -0.2256 0.8217
3 | -18.3136 9.6511 -1.8976 0.0592
4 | 227.6340 111.7706 2.0366 0.0430
5 | 881.1814 239.7495 3.6754 0.0003
-----------------------------------------------------
Thresholds in double model:
1
+---------------+
1 | 16200.90238 |
2 | 21548.9935 |
+---------------+
Ho: Single threshold; Ha: Double threshold
Number of bootstrap: 200
F-stat & Prob: 10.9448 0.0100 证明存在两个门限
F-critical value of 90% 95% 99%:
1
+---------------+
1 | 2.956565211 |
2 | 4.537797681 |
3 | 13.43303268 |
+---------------+
============== Descrpitive statistic in each regime: ===========
Descriptive statistics of y-X-THR at regime : 1
----------------------------------------------------------------
| Mean Std Min Max Count
----+-----------------------------------------------------------
1 | 180.7502 140.1279 14.0200 741.1700 206
2 | 0.3009 0.4108 0.0371 1.6805 206
3 | 0.0249 0.0338 0.0000 0.2011 206
4 | 0.3436 0.3572 0.0208 2.5931 206
5 | 6199.5355 3743.8472 393.0462 1.60e+04 206
----------------------------------------------------------------
Descriptive statistics of y-X-THR at regime : 2
----------------------------------------------------------------
| Mean Std Min Max Count
----+-----------------------------------------------------------
1 | 729.4475 214.8937 344.6700 1085.6500 12
2 | 0.6636 0.5303 0.0472 1.5668 12
3 | 0.1013 0.0581 0.0216 0.1828 12
4 | 0.2395 0.2441 0.0571 0.8024 12
5 | 1.85e+04 1611.2171 1.66e+04 2.13e+04 12
----------------------------------------------------------------
Descriptive statistics of y-X-THR at regime : 3
----------------------------------------------------------------
| Mean Std Min Max Count
----+-----------------------------------------------------------
1 | 1115.1707 252.3156 830.4800 1568.0000 14
2 | 0.8307 0.4279 0.2801 1.5484 14
3 | 0.1188 0.0479 0.0502 0.1827 14
4 | 0.2218 0.1478 0.0745 0.5199 14
5 | 2.87e+04 4641.7050 2.29e+04 3.79e+04 14
----------------------------------------------------------------
LR and Thresholds series are stored in Stata matrix: LR#
You can observe the scatter plot by: _matplot LR#, columns(1 2)
.
end of do-file
先谢谢大家!每位回帖的大人都会有金币补偿,最佳答案有500金币补偿!