如果x和u都是互相关联的然后这违反了一项 regression。 应用了OLS的公式的结果不符合的估计,即使在样本大小的方法无穷的估计参数的平均值将不平等的人口估计数。 要
解决此问题可以适用TSLS也称为四步骤。 这是一两个步骤的过程。 第一,OLS regression x的z和获取预测x说x^。 第二,苏丹生命线行动的回归y xˆ
I am not really good in mandarin. 我的华语不是很好。 This is how I can explain in English though. 我用英语解释会比较好。
If x and u are correlated then this violates an assumption of the regression. Applying OLS to the equation results in inconsistent estimates, that is, even as the sample size approaches infinity the estimates of the parameters on average will not equal the population estimates. To
remedy this problem one can apply TSLS, also called IV procedure. It is a two step procedure. First, OLS regression x on z and get predictions for x, say x^. Second, OLS regression y on xˆ
Hope this helps. 希望这对你有帮助。