开发者:上海品职教育科技有限公司 隐私政策详情

应用版本:4.2.11(IOS)|3.2.5(安卓)APP下载

TZXคิดถึง · 2023年05月01日

请问我的理解有什么问题?

NO.PZ2023040502000025

问题如下:

Given the information in Exhibit 1, Hamilton’s conclusion that multicollinearity is not a problem, is most likely based on the observation that the:


选项:

A.

correlation between the S&P 500 and SPREAD is low.

B.

model F-value is high and the p-values for the S&P 500 and SPREAD are low.

C.

model R2 is relatively low.

解释:

Multicollinearity occurs when two or more independent variables (or combinations of independent variables) are highly (but not perfectly) correlated. Correlation between independent variables may be a reasonable indication of multicollinearity in cases in which the regression contains only two independent variables. In Hamilton’s regression model, the correlation between the SPREAD and the S&P 500 variables is only 0.30.

根据定义法,当F检验通过,但是t检验通不过,R^2特别高的时候,证明存在多重共线性,上述条件不满足任何一个都无法证明多重共线性。

所以是不是A、C也可以作为判断标准?

还是说本题就是不严谨,就想考察相关系数法的判断?

1 个答案
已采纳答案

星星_品职助教 · 2023年05月01日

同学你好,

如果只看一个指标,那么correlation自己就可以直接得出结论。所以A选项是本题“most likely”的选项。

多重共线性的另一个判断标准是F、t、R-squared三个指标一起看。B和C选项都只看了其中的一部分,不够全面,并不是本题最优的选择。合适的方式是把B、C两项结合起来综合考虑。

  • 1

    回答
  • 0

    关注
  • 259

    浏览
相关问题

NO.PZ2023040502000025问题如下 Given the information in Exhibit 1, Hamilton’sconclusion thmulticollinearity is not a problem, is most likely baseon theobservation ththe: A.correlation between the S P 500 anSPREis low.B.mol F-value is high anthe p-values for the S P500 anSPREare low.C.mol R2 is relatively low. Multicollinearity occurs when two or more inpenntvariables (or combinations of inpennt variables) are highly (but not perfectly)correlate Correlation between inpennt variables ma reasonableincation of multicollinearity in cases in whithe regression contains onlytwo inpennt variables. In Hamilton’s regression mol, the correlationbetween the SPREanthe S P 500 variables is only 0.30. ​这个相对大和相对小也没有判断标准吧,我感觉A和C是不是不太好选

2024-06-20 08:39 1 · 回答

NO.PZ2023040502000025 问题如下 Given the information in Exhibit 1, Hamilton’sconclusion thmulticollinearity is not a problem, is most likely baseon theobservation ththe: A.correlation between the S P 500 anSPREis low. B.mol F-value is high anthe p-values for the S P500 anSPREare low. C.mol R2 is relatively low. Multicollinearity occurs when two or more inpenntvariables (or combinations of inpennt variables) are highly (but not perfectly)correlate Correlation between inpennt variables ma reasonableincation of multicollinearity in cases in whithe regression contains onlytwo inpennt variables. In Hamilton’s regression mol, the correlationbetween the SPREanthe S P 500 variables is only 0.30. R-square小,VIF小,小的VIF没有多重共线性啊。。。

2023-08-26 10:27 1 · 回答