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

Olivia Chen · 2020年10月01日

问一道题:NO.PZ2016062402000024 [ FRM I ]

问题如下:

You built a linear regression model to analyze annual salaries for a developed country. You incorporated two independent variables, age and experience, into your model. Upon reading the regression results, you notice that the coefficient of experience is negative, which appears to be counterintuitive. In addition, you discover that the coefficients have low t-statistics but the regression model has a high \(R^2\). What is the most likely cause of these results?

选项:

A.

Incorrect standard errors

B.

Heteroskedasticity

C.

Serial correlation

D.

Multicollinearity

解释:

Age and experience are likely to be highly correlated. Generally, multicollinearity manifests itself when standard errors for coefficients are high, even when the R2R^2 is high.

可以把四个答案都分别解释下吗?
1 个答案

小刘_品职助教 · 2020年10月02日

同学你好,

这题考点是违反回归假设有哪些常见的情况,对应的检验方法有哪些。

A 选项是凑选项的,说的是错误的标准误。就不是违反回归假设出现的问题。

B 选项是异方差。会使得F检验和T检验不可靠,检验异方差一般看散点图。

C是序列相关性,这个主要出现在时间序列数据当中。

D是多重共线性,单个系数的T检验的绝对值很低,但是R平方检验值很高时,就暗示着多重共线性的产生。