Minimized Sum of Squared Residuals: 1.01e+04
Standard error of residuals: 1.6546
Threshold estimator: 0.1104
95% conf. intv. of threshold: 0.0682 0.1695
LR Critical value to test gamma=gamma0: 7.3523
Threshold regression(Ordinary Std. Error):
----------------------------------------------------
| Coef Std t prob
----+-----------------------------------------------
1 | -0.2270 0.0292 -7.7700 0.0000
2 | -0.4019 0.0478 -8.4156 0.0000
3 | 14.8827 3.4636 4.2969 0.0000
4 | 13.3524 2.9892 4.4668 0.0000
----------------------------------------------------
Threshold regression(Robust Std. Error):
-----------------------------------------------------
| Coef Std_Robust t prob
----+------------------------------------------------
1 | -0.2270 0.1470 -1.5441 0.1227
2 | -0.4019 0.3592 -1.1191 0.2632
3 | 14.8827 13.6038 1.0940 0.2740
4 | 13.3524 12.3276 1.0831 0.2788
-----------------------------------------------------
Note: Critcal (Inverse CDF of LR stat): -2*ln(1-sqrt(1-alpha))
Ho: No threshold; Ha: Single threshold
Number of bootstrap:2000
F-stat & Prob: 3.3678 0.0585
F-critical value of 90% 95% 99%:
1
+---------------+
1 | 2.624169499 |
2 | 3.608841499 |
3 | 6.064772631 |
+---------------+
Thresholds in single model:
.1104458094
老师你好 ,请问为何ordinary回归的p值反而小于robust回归的p值呢?还有请问这个结果是显著的吗?是否代表存在门槛效应呢?