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

funfunxiong · 2021年08月08日

怎么理解下面这句话?太抽象了。

NO.PZ2018122701000058

问题如下:

Which of the following statements about correlation and copula are correct?

I.Copula enables the structures of correlation between variables to be calculated separately from their marginal distributions.

II.Transformation of variables does not change their correlation structure.

III.Correlation can be a useful measure of the relationship between variables drawn from a distribution without a defined variance.

IV.Correlation s a good measure of dependence when the measured variables are distributed as multivariate elliptical.

选项:

A.

I and IV only

B.

II, III, and IV only

C.

I and III only

D.

II and IV only

解释:

A is correct.

考点 Copula Functions

解析

"I" is true. Using the copula approach, we can calculate the structures of correlation between variables separately from the marginal distributions. "IV" is also true. Correlation is a good measure of dependence when the measured variables are distributed as multivariate elliptical.

"II" is false. The correlation between transformed variables will not always be the same as the correlation between those same variables before transformation. Data transformation can sometimes alter the correlation estimate. "III" is also false. Correlation is not defined unless variances are finite.

Using the copula approach, we can calculate the structures of correlation between variables separately from the marginal distributions

1 个答案

品职答疑小助手雍 · 2021年08月08日

嗨,爱思考的PZer你好:


就是刚才我说的第一步,如何做mapping,其实就是各个分布通过marginal (一点一点累计直到100%)mapping到标准正态,然后建立关联。

这也就相当于把各个分布的marginal distribution建立起了关联。

copula这部分因为没办法考计算,只能考一些理解,备考准备中我是建议放在了解即可的范畴的哈,毕竟就算考顶多1,2道题的选项里会出现。巴塞尔协议的几大条线才是重中之重~

----------------------------------------------
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
  • 549

    浏览
相关问题

NO.PZ2018122701000058 问题如下 Whiof the following statements about correlation ancopula are correct? I.Copula enables the structures of correlation between variables to calculateseparately from their marginal stributions. II.Transformation of variables es not change their correlation structure. III.Correlation ca useful measure of the relationship between variables awn from a stribution without a fined variance. IV.Correlation s a goomeasure of pennce when the measurevariables are stributemultivariate elliptical. I anIV only II, III, anIV only I anIII only II anIV only A is correct. 考点 : Copula Functions 解析 : \"I\" is true. Using the copula approach, we can calculate the structures of correlation between variables separately from the marginstributions. \"IV\" is also true. Correlation is a goomeasure of pennwhen the measurevariables are stributemultivariate elliptical. \"II\" is false. The correlation between transformevariables will not always the same the correlation between those same variables before transformation. ta transformation csometimes alter the correlation estimate. \"III\" is also false. Correlation is not fined unless variances are finite. 如题

2024-03-05 03:59 1 · 回答

NO.PZ2018122701000058问题如下 Whiof the following statements about correlation ancopula are correct? I.Copula enables the structures of correlation between variables to calculateseparately from their marginal stributions. II.Transformation of variables es not change their correlation structure. III.Correlation ca useful measure of the relationship between variables awn from a stribution without a fined variance. IV.Correlation s a goomeasure of pennce when the measurevariables are stributemultivariate elliptical. I anIV only II, III, anIV only I anIII only II anIV only A is correct. 考点 : Copula Functions 解析 : \"I\" is true. Using the copula approach, we can calculate the structures of correlation between variables separately from the marginstributions. \"IV\" is also true. Correlation is a goomeasure of pennwhen the measurevariables are stributemultivariate elliptical. \"II\" is false. The correlation between transformevariables will not always the same the correlation between those same variables before transformation. ta transformation csometimes alter the correlation estimate. \"III\" is also false. Correlation is not fined unless variances are finite. 我认为除了A都是对的,答案恰恰相反。A肯定不对啊。COPULA是求联合概率的,怎么是求单独的呢?其他为什么错误呢?

2023-08-04 03:17 1 · 回答

NO.PZ2018122701000058 问题如下 Whiof the following statements about correlation ancopula are correct? I.Copula enables the structures of correlation between variables to calculateseparately from their marginal stributions. II.Transformation of variables es not change their correlation structure. III.Correlation ca useful measure of the relationship between variables awn from a stribution without a fined variance. IV.Correlation s a goomeasure of pennce when the measurevariables are stributemultivariate elliptical. I anIV only II, III, anIV only I anIII only II anIV only A is correct. 考点 : Copula Functions 解析 : \"I\" is true. Using the copula approach, we can calculate the structures of correlation between variables separately from the marginstributions. \"IV\" is also true. Correlation is a goomeasure of pennwhen the measurevariables are stributemultivariate elliptical. \"II\" is false. The correlation between transformevariables will not always the same the correlation between those same variables before transformation. ta transformation csometimes alter the correlation estimate. \"III\" is also false. Correlation is not fined unless variances are finite. I和III不是很明白,ICopula enables the structures of correlation between variables to calculateseparately from their marginstributions.是翻译成“Copula根据变量的边缘分布分别计算变量之间的相关性的结构”吗?这个具体的逻辑没太明白,变量的边缘分布,是指高斯copula中的G1(u1)吗III.Correlation ca useful measure of the relationship between variables awn from a stribution without a finevariance.这里的awn from a stribution without a finevariance.请问指的是什么?谢谢!

2023-02-14 16:51 2 · 回答

NO.PZ2018122701000058问题如下 Whiof the following statements about correlation ancopula are correct? I.Copula enables the structures of correlation between variables to calculateseparately from their marginal stributions. II.Transformation of variables es not change their correlation structure. III.Correlation ca useful measure of the relationship between variables awn from a stribution without a fined variance. IV.Correlation s a goomeasure of pennce when the measurevariables are stributemultivariate elliptical. I anIV only II, III, anIV only I anIII only II anIV only A is correct. 考点 : Copula Functions 解析 : \"I\" is true. Using the copula approach, we can calculate the structures of correlation between variables separately from the marginstributions. \"IV\" is also true. Correlation is a goomeasure of pennwhen the measurevariables are stributemultivariate elliptical. \"II\" is false. The correlation between transformevariables will not always the same the correlation between those same variables before transformation. ta transformation csometimes alter the correlation estimate. \"III\" is also false. Correlation is not fined unless variances are finite. 相关性的两个变量需要有前提吗。

2022-07-18 21:40 1 · 回答

NO.PZ2018122701000058

2021-11-08 17:12 1 · 回答