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

🌻🎀LINDA🎀🌻 · 2022年11月17日

不是不需要假设来分析极值吗?

NO.PZ2016070202000008

问题如下:

A CRO is concerned that existing internal risk models of a firm, which are governed mainly by the central limit theorem, are not adequate in addressing potential random extreme losses of the firm. The CRO then recommends the use of extreme value theory (EVT). Which of the following statements regarding extreme value theory (EVT) is incorrect?

选项:

A.

In contrast to conventional approaches for estimating VAR, EVT considers only the tail behavior of the distribution.

B.

Conventional approaches for estimating VAR that assume that the distribution of returns follows a unique distribution for the entire range of values may fail to properly account for the fat tails of the distribution of returns.

C.

EVT attempts to find the optimal point beyond which all values belong to the tail and then models the distribution of the tail separately.

D.

By smoothing the tail of the distribution, EVT effectively ignores extreme events and losses that can generally be labeled outliers.

解释:

D is correct. EVT uses only information in the tail, so statement Conventional approaches such as delta-normal VAR assume a fixed probability density function (p.d.f.) for the entire distribution, which may understate the extent of fat tails, so statement B is correct. The first step in EVT is to choose a cutoff point for the tail, and then to estimate the parameters of the tail distribution, so statement C is correct. Finally, EVT does not ignore extreme events (as long as they are in the sample).

为什么文中提到好几次tail?如果没有分布的话

1 个答案

pzqa27 · 2022年11月17日

嗨,爱思考的PZer你好:


极值理论是把我们收益或者叫损失形成分布的尾巴割下来研究,但是它不限制损失和收益形成哪种分布,可以是高斯,泊松,泊努力的任意一种,也可以不服从这仨分布,但是它肯定可以形成一种分布,我们只是不限制这种分布的种类而已。

----------------------------------------------
虽然现在很辛苦,但努力过的感觉真的很好,加油!

  • 1

    回答
  • 0

    关注
  • 228

    浏览
相关问题

NO.PZ2016070202000008 问题如下 A CRO is concernethexisting internrisk mols of a firm, whiare governemainly the centrlimit theorem, are not aquate in aressing potentiranm extreme losses of the firm. The CRO then recommen the use of extreme value theory (EVT). Whiof the following statements regarng extreme value theory (EVT) is incorrect? A.In contrast to conventionapproaches for estimating VAR, EVT consirs only the tail behavior of the stribution. B.Conventionapproaches for estimating Vthassume ththe stribution of returns follows a unique stribution for the entire range of values mfail to properly account for the ftails of the stribution of returns. C.EVT attempts to finthe optimpoint beyonwhiall values belong to the tail anthen mols the stribution of the tail separately. smoothing the tail of the stribution, EVT effectively ignores extreme events anlosses thcgenerally labeleoutliers. is correct. EVT uses only information in the tail, so statement Conventionapproaches sulta-normVassume a fixeprobability nsity function (p.f.) for the entire stribution, whimunrstate the extent of ftails, so statement B is correct. The first step in EVT is to choose a cutoff point for the tail, anthen to estimate the parameters of the tail stribution, so statement C is correct. Finally, EVT es not ignore extreme events (long they are in the sample). 如题

2024-03-01 23:17 1 · 回答

NO.PZ2016070202000008问题如下 A CRO is concernethexisting internrisk mols of a firm, whiare governemainly the centrlimit theorem, are not aquate in aressing potentiranm extreme losses of the firm. The CRO then recommen the use of extreme value theory (EVT). Whiof the following statements regarng extreme value theory (EVT) is incorrect? A.In contrast to conventionapproaches for estimating VAR, EVT consirs only the tail behavior of the stribution.B.Conventionapproaches for estimating Vthassume ththe stribution of returns follows a unique stribution for the entire range of values mfail to properly account for the ftails of the stribution of returns.C.EVT attempts to finthe optimpoint beyonwhiall values belong to the tail anthen mols the stribution of the tail separately.smoothing the tail of the stribution, EVT effectively ignores extreme events anlosses thcgenerally labeleoutliers.is correct. EVT uses only information in the tail, so statement Conventionapproaches sulta-normVassume a fixeprobability nsity function (p.f.) for the entire stribution, whimunrstate the extent of ftails, so statement B is correct. The first step in EVT is to choose a cutoff point for the tail, anthen to estimate the parameters of the tail stribution, so statement C is correct. Finally, EVT es not ignore extreme events (long they are in the sample).句smoothing the tail说的是什么事情?

2022-04-04 01:06 1 · 回答

NO.PZ2016070202000008 老师C是不是描述的是广义极值分布的模型

2022-03-04 21:19 1 · 回答

lta-normal是什么意思啊

2020-12-27 10:19 1 · 回答