黃河泉 发表于 2019-4-26 08:08 
应该是!
黄老师,非常感谢您的回复,我缩减了样本,用命令thresholdtest y x1 x2 x3 , q(x1) trim_per(0.15) rep(200),得出来门槛检验结果是下面这样的,Bootstrap P-Value值是0.345,那这样是不是就说明没有门槛呢?trim_per()括号里面的赋值可以换其他的吗?盼复!
Test of Null of No Threshold Against Alternative of Threshold
Allowing Heteroskedastic Errors (White Corrected)
______________________________________________________________________
Number of Bootstrap Replications: 200
Trimming Percentage: .15
Threshold Estimate: 11.0821428
LM-test for no threshold: 30.0573352
Bootstrap P-Value: .345
______________________________________________________________________
.
. graph rename test1