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

reachqi · 2019年11月18日

问一道题:NO.PZ2015120204000059

问题如下:

In completing her analysis, Maxwell considers her choice of simulation analysis over alternative approaches, such as decision trees and scenario analysis, to be justified. Although scenario analysis and decision trees both consider possible outcomes, neither can be used easily when correlated variables are present. Further, she notes that, compared with scenario analysis and decision trees, simulation is best suited for continuous risks, whether they be concurrent or sequential.

Maxwell’s justifications for her choice of simulation analysis are correct with respect to:

选项:

A.

correlated risks.
 

B.

continuous risks.
 

C.

both correlated risks and continuous risks.
 

解释:

C is correct. Correlated risks are difficult to model in decision trees. In addition, adjusting scenario analysis for correlated risks is subjective. Scenario analysis and decision trees are generally built around discrete outcomes in risky events, whereas simulations are better suited for continuous risks. Further, if the various risks to which an investment is exposed are correlated, simulations allow for explicitly modeling these correlations if they can be estimated. 

为什么correlation variables不能用于Decision Tree和Scenario Analysis? 能详细点解释吗?这部分学的不是很明白


1 个答案
已采纳答案

星星_品职助教 · 2019年11月18日

同学你好,

这道题是今年这一章下协会新加了一个case共7道题,所以课程也增加了一个课后题讲解,里面有这道题,可以看完讲解后也去听一下巩固。

这道题主要就是这三种方法的对比,其中决策树是一个“流程”,下一步的结果取决于上一步的“决策”的结果,例如老师上课讲的:先决定是建个大工厂还是小工厂,然后再分别分析如果是大厂/小厂后的销量情况。这种方法只是考虑了每次决策后的结果,并没有将决策之间的相关性考虑进去。

而情景分析其实是包含了相关性的,例如经济变差时,信用风险上升,这个时候抵押品价值又往往会下降。所以就可以设置一种情景:信用风险上升,和抵押品价值下降。这其实就将信用风险和抵押品价值这两个变量的相关关系考虑进去了,但是这种相关关系比较主观。

而simulation是模拟了无数种的情况,也就是把例如经济变差后的这两个变量的无数种可能都模拟了,自然也就包含了相关性,而且也不是主观人为“认定”相关性就一定是怎样的关系。

截取原版书上的对应知识点如下,加油~

Correlation across risks: If the various risks that an investment is exposed to are correlated, simulations allow for explicitly modeling these correlations
(assuming that you can estimate and forecast them). In scenario analysis, we can deal with correlations subjectively by creating scenarios that allow for them; the high (low) interest rate scenario will also include slower (higher) economic growth. Correlated risks are difficult to model in decision trees.