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

丁洁Amy · 2021年04月05日

关于第二个场景的探讨

NO.PZ2015120204000026

问题如下:

An analyst is addressing the following research topics: how investment fund characteristics affect fund total returns and whether stock and bond market returns explain the returns of a portfolio of utility shares run by the firm.

To explore the first topic, he uses the average annualized rate of return(in percent) of 555 large-cap US equity funds over the past five years. The independent variables are fund expense ratio, portfolio turnover, the natural logarithm of fund size, fund age, and three dummy variables.For the second topic, he establish whether bond market returns (proxied by returns of long-term US Treasuries) and stock market returns(proxied by returns of the S&P 500 Index) explain the returns of a portfolio of utility stocks being recommended to clients.

Whether he should have estimated the models using a probit or logit model instead of using a traditional regression analysis?

选项:

A.

Both should be estimated with probit or logit models.

B.

Neither should be estimated with probit or logit models.

C.

Only the first analysis should be done with probit or logit models.

解释:

Probit and logit models are used for models with qualitative dependent variables, such as models in which the dependent variable can have one of two discrete outcomes (i.e., 0 or 1). The analysis in the two exhibits are explaining security returns, which are continuous (not 0 or 1)variables.

老师好,


我当时的想法是第一个不需要用probit and logit model,但是第二个我觉得是需要的。因为问的是X是否能解释Y,不外乎就是是或者不是。所以我理解的是这是个qualitative 的变量。请老师帮忙分析下,谢谢。

2 个答案
已采纳答案

星星_品职助教 · 2021年04月06日

同学你好,

是否用probit or logit model取决于Y变量本身是什么。场景2的Y变量是“returns”,这是个连续的变量,所以不能使用probit or logit models.

不能从“X是否能解释Y”的角度去思考。因为所有的回归模型其实都是在研究“X是否能解释Y”。例如场景1,研究的也是“fund expense ratio, portfolio turnover, the natural logarithm of fund size, fund age, and three dummy variables”这些变量能否解释Y(这个解释关系是否显著,解释力度强不强,X变化1单位,Y随之变化几单位)等问题

KK😯 · 2021年05月30日

是否用probit or logit model取决于Y变量本身是什么。场景2的Y变量是“returns”,这是个连续的变量,所以不能使用probit or logit models. 不能从“X是否能解释Y”的角度去思考。因为所有的回归模型其实都是在研究“X是否能解释Y”。例如场景1,研究的也是“fund expense ratio, portfolio turnover, the natural logarithm of fund size, fund age, and three dummy variables”这些变量能否解释Y(这个解释关系是否显著,解释力度强不强,X变化1单位,Y随之变化几单位)等问题