中介效应的四个条件（抱歉是英文，请自行翻译，来自Baron & Kenny, (1986) ）：
The predictor must significantly predict the outcome variable.
The predictor must significantly predict the mediator.
The mediator must significantly predict the outcome variable.
The predictor variable must predict the outcome variable less strongly in model 3 than in model 1.
这样一来（抱歉是英文，请自行翻译，来自本人学习笔记 ），
1.Each path should be significantly related: ->a  ->b  ->c (e.g., 0.4)
2.When “mediator” is considered, if the 0.4 becomes 0.15
0.15 (2.05) significant: there is mediating effect and mediator is partial mediator
But if 0.15 (1.02): mediator became perfect mediator.
Add "mediator" to the regression. Observe any change in path "c". Did it change? How much? If it were "perfect mediation", path "c" would drop to zero after having included "mediator." This usually doesn't happen however, and we must settle on a test for what is called "partial mediation" to see if the change from "c" to "c'" is big enough to claim partial mediation.
用sobel检验做检验的时候，可以进入以下网址输入相应数据：http://quantpsy.org/sobel/sobel.htm
我给你得到结果了，看我的图2。0.9以上的p值说明中介效应不成立

多谢多谢，不知道怎么给你给金币。但是我用另一个计算工具的出来的结果，指出我这个中介效应是存在的。很是不解，到底哪个是对的。

再请问以下，为什么高于0.96就是不显著了呢？判断依据是什么？或者原理是什么？谢谢了

你给的信息不够，要看从A到C的显著性变化，加入“中介变量”之前必须显著，加入之后显著性应该减弱

P值一般高于0.05就是不显著了