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

izzyli · 2023年10月12日

咨询一个问题

NO.PZ2023040502000004

问题如下:

Mike collects values for ROE, CEO tenure and ESG rating for a sample of40 companies from the large-cap security universe. He performs a multipleregression with ROE (in percent) as the dependent variable and ESG rating, CEOtenure (in years) as the independent variables. He also wants to check on therelationship between these variables and the dividend growth rate (divgr).

Which of the followingwould violate the assumptions of multiple regression analysis?

1. ROE is lesscorrelated with the dividend growth rate in firms whose CEO has been in officemore than 15 years, and

2. CEO tenure is a normallydistributed random variable.

选项:

A.

The assumption about CEO tenure distribution only

B.

The assumption about the ROE/dividend growthcorrelation only

C.

The assumptions about both the ROE/dividend growthcorrelation and CEO tenure distribution

解释:

Multiple linear regression assumes that therelationship between the dependent variable and each of the independentvariables is linear. He believes that this is not true for dividend growthbecause he believes the relationship may be different in firms with along-standing CEO. Multiple linear regression also assumes that the independentvariables are not random. He states that he believes CEO tenure is a randomvariable.

帮忙解释一下第一个假设为何不对。谢谢

1 个答案
已采纳答案

星星_品职助教 · 2023年10月13日

同学你好,

第一个假设为“ ROE is less correlated with the dividend growth rate in firms whose CEO has been in office more than 15 years”。这个违背的是Y和X必须是线性关系。

线性关系意味着Y和X是固定的关系,不能随时变化。第一个假设中的“less correlated....with....more than 15 years”说的是这个关系是随着年限而变化的,一会强一会弱,所以不对。

  • 1

    回答
  • 0

    关注
  • 1143

    浏览
相关问题