b*s
发帖数: 82482 | 1 这行的矿工们越玩越玄，搞得很多业内老总都不明白了。当年祥林嫂，不，祥林哥，搞
出那个倒霉的Gaussian copula function公式的时候，用这个公式是需要条件的，结果
一帮人，有意或者无意，都把这个东东当成法宝，到处乱套，结果全球形势一片大号，
不是小好，this time, it will be different……
然后，祥林哥就在2008年海龟了，牛人在哪里都牛……
才发现这楼里在吵这个。实际上社会大众对花街有意见，有一个很朴素的原因：其它的
行业多数都对社会做了正面贡献，但金融业界的很多业务对社会并没有贡献什么真正的
价值，基本就是用钱玩钱、投机赌博，还搞得这么大，挣的钱这么多，很不合理。前几
年Tech Crunch有一篇文章：Friends Don't Let Friends Go to Wall Street，说据统
计MIT每年有四分之一的学生毕业之后上了花街，去从事那些不能为社会创造价值的活
动，仅仅是因为这个行业挣钱多，这实际上是对社会人才和资源的极大浪费。要是这些
人才和资源能投入对社会更有益的工作，那么攻克癌症、解决能源危机神马的事业就会
更容易... 阅读全帖 |
|
E**********v
发帖数: 5509 | 2 这问题基本只要是model就有。Gaussian copula应用有一个assumption，就是两个随机
变量都要iid。这个基本实际生活中没法严格遵守。数学模型本来就是实际问题的
approximation。大部分情况下一个model能够work就不错了。目前的传统金融建模的理
论水平只能把肥尾不work的情况解释为noise。这是一个industry普遍存在的问题，
theory limit，no better alternative。跟fraud没啥关系。换个思路想想，不完美
有错误，是事实，但是总比啥都没有好吧。
我在学校的时候，有一个分支是搞复杂系统，颠覆传统自上而下用数学公式建模的方法
，而采用自下而上通过simulation衍生规则方式建模。但是这个理论其实是一个交叉学
科，它的发展heavily depends on计算机学科人工智能技术的发展。都这么多年过去了
，都还没见到啥成熟的应用。
街上现在最主要的问题是model governance。model还是要用要开发，但是应用之前的
validation和back testing很重要。其实银行里也都有严格规定，关... 阅读全帖 |
|
n********n
发帖数: 8336 | 3 8。2。2 希腊文(Greek)
希腊文是一种很美丽、丰富多采和和谐的语言，非常适合作为表达宗教哲学思想的工具
。有人这样比较希伯来文和希腊文：“闪族人的语言像一座石矿场，里头的巨石被希腊
人琢磨成一尊尊塑像。”希伯来人给我们宗教、希腊人给我们哲学和诗歌。
希腊文有二十四个字母。它是一种强烈的合成语言，这也是为什么一般人觉得这种语言
难学的原因。因为现代的英文(中文更甚)构造和希腊文截然不同。
希腊文的词汇非常丰富。希伯来文的词语不多，约少于一万；而希腊文则有二十万之多
。譬如，“爱”就用了agape(上帝的爱)，philia(友爱)，storge(家庭间的爱)，eros(
情爱)。英文的another(另一个)就用了allos(another of the same sort)和 heteros(
another of the different sort)。约十四：15 “父就另外赐给你们一位保惠师。。
”这一位保惠师是allos，是另一位像他一样的。还有，“new”(新)有时间上的“新”
(neos)和品质上的“新”(kainos)。弗四：24“并且穿上新人”用的是kai... 阅读全帖 |
|
f***e
发帖数: 332 | 4 David X. Li
From Wikipedia, the free encyclopedia
David X. Li is a quantitative analyst and a qualified actuary who pioneered
the use of Gaussian copula models for the pricing of collateralized debt
obligations (CDOs).[1][2]
Li grew up in rural China in the 1960s.[1] He received a master's degree in
economics from Nankai University before leaving China to earn an MBA from
Laval University in Quebec.[1] He then received a master's in actuarial
science and a PhD in statistics from the University o |
|
f***e
发帖数: 332 | 5 David X. Li（中文名是什么？）是Quant中的传奇，因为他发明的Gaussian copula公
式是CDS，CDO产生的基础。可以说是David X Li一手造就了今天波及全球摧毁华尔街的
金融危机。现在我们可敬的老李同志已经安然返回了祖国的怀抱，在北京出任中国国际
金融有限公司风险管理主管。现在华尔街发出了全球通缉令，有认识老李同志一定要记
得提醒他躲一躲风声。
David X. Li：http://en.wikipedia.org/wiki/David_X._Li
Wired杂志的原文 ：http://www.wired.com/techbiz/it/magazine/17-03/wp_quant
《连线》17-03期封面：导致华尔街灾难的模型
新浪财经讯 本期《连线杂志》介绍了近乎荒诞、且另美国和全球金融体系摇摇欲坠的
事件：所有全球金融精英人士对一个中国人构建的金融计量模型几乎像圣经一样顶礼膜
拜，但精英们忘却了模型的限制条件的警告，最终使它失效，他们也付出了可怕的代价。
人们此前总认为像David X. Li这样有数学天才者可能在某日会得到诺贝尔经济学
奖的眷顾， |
|
l******n
发帖数: 9344 | 6 这就不得不提到copula和一个国人大牛了。。。这是quant的话题呀 |
|
l******n
发帖数: 9344 | 7 这就不得不提到copula和一个国人大牛了。。。这是quant的话题呀 |
|
B*****k
发帖数: 18 | 8 David X. Li
Vice President
Global Credit Derivative Research, Salomon Smith
388 Greenwich Street 11th Floor
New York, NY 10013
United States
Tel: (212) 816-2679
Designations
ASA 1993
Academic Degrees
Ph.D.
李大牛08年回国，现在是中金的chief risk officer.
David X. Li (born in China in the 1960s as simplified Chinese: 李 祥林;
pinyin: Lǐ Xiánglín[1]) is a quantitative analyst and a qualified actuary
who in the early 2000s pioneered the use of Gaussian copula models for the
pricing of collateralized debt obliga |
|
s*******0
发帖数: 3461 | 9 呵呵 所以说 这个文章 瞎说啊
有很多人小朋友 又要忽悠进去了
保饿 分红 就是英试 分红了 之前 安联大众 旧有这样分红的
不知道为啥 第一人的称号给他
不过 也许 中子公司 保饿分红第一人的称号可以算是差不多
david li啊 大牛人 主要贡献 还是在金融工程了 就是 信贷风险控制的领域
第一个 在credit default risk 领域引进copulas 函数啊
貌似也是这次 次债危机的罪魁祸首 之一 呵呵
his model now is called a "recipe for disaster" |
|
s*******0
发帖数: 3461 | 10 p.s.
"To say David brought down the market is like blaming Einstein for Hiroshima"
呵呵 凡事出事 总要找个人 来 替罪啊 中外 皆如此
其实 具体的机理我也不是很明白
有懂得的人 说说
最近 就在看这个 高斯copula 呵呵 貌似看了 说 这个 只能考虑不同产品的静态的
相关系数 但是 相关系数 应该是动态变化的 所以 不是很合理 |
|
z*****l
发帖数: 3472 | 11 What is the conditional distribution of one uniform random variable given
another under a Clayton Copula |
|
e***t
发帖数: 14386 | 12 2. \Pseudo-likelihood Ratio test for model selection of semiparametric
copula-based
multivariate survival models under general censorship", with Xiaohong Chen,
Yanqin
Fan and Zhiliang Ying. Forthcoming in Journal of Econometrics.
3. \E±cient Estimation of Semiparametric Conditional Moment Models with
Possibly
Nonsmooth Residuals", with Xiaohong Chen. Available at SSRN:
http://ssrn.com/abstract=1267230. Forthcoming in Journal of Econometrics.
4. \Estimation of Nonparametric Conditional Moment Mod |
|
p**********n
发帖数: 1470 | 13 from wiki... 请自带避雷针
Another contribution of Dr. Chen to the financial industry and academia is
to develop the so-called Modeling without Programming techniques.
Specifically, Prof. Chen invented sophisticated techniques to implement
advanced algorithms and models in financial engineering, computational
finance and actuarial science, (such as Monte Carlo simulations, EVT,
Copulas, and MCMC) in Excel spreadsheets using Excel’s functions only.
These advanced models are normally implemented by serio |
|
c**i
发帖数: 6973 | 14 【 以下文字转载自 Taiwan 讨论区 】
发信人: choi (choi), 信区: Taiwan
标 题: Complete Idiot's Guide
发信站: BBS 未名空间站 (Mon Apr 27 15:24:07 2009)
to Current Financial Crisis; A Chinese Genius Named David Li.
The above is the title and subtitle of my posting.
(1) Sam Jones, Of Couples and Copulas. Financial Times (FT), Apr. 25, 2009.
http://www.ft.com/cms/s/2/912d85e8-2d75-11de-9eba-00144feabdc0.html
(a) Captions to the two photographs in the print edition:
(i) "Lovestruck Johnny Cash died a few months after his wife J |
|
|
j********9
发帖数: 162 | 16 Please disregard the questions.
The above questions doesn't make sense. I was confused by myself.
Now it is clear. |
|
y****d
发帖数: 432 | 17 包括以下书籍
★A course in probility theory
★An.Introduction.to.Copulas
★Aspects of Mathematical Finance (Yor, 2008, Springer)
★Computational.and.Mathematical.Modeling.in.the.Social.Sciences
★convergence of stochastic processes （ by Pollard ）
★Convex Optimization
★Discrete-Time.Markov.Jump.Linear.Systems
★EC5028.Mathematical.Finance
★Elementary Differential Equations-Boyce
★Introduction.to.Stochastic.Calculus.for.Finance.-.A.New.Didactic.Approach
★levy process in finance
★Markov Chains and Stochastic S... 阅读全帖 |
|
e**********n
发帖数: 359 | 18 Check out wikipedia, that's enough for this written test. |
|
K*****Y
发帖数: 629 | 19 Correlation, copula models. |
|
|
s**k
发帖数: 10 | 21 Modeling without Programming is a systematic approach developed by Lin Chen
to implement advanced algorithms and models in financial engineering,
computational finance and actuarial science in Excel spreadsheets using
Excel’s functions only, without VBA coding.
Such advanced models and methods include, but are not limited to, HJM model,
BGM model,Monte Carlo method, least-square MC, American option pricing,
extreme value theory, copula approach, default risk models. These models and
algorithms a |
|
i*******e
发帖数: 8 | 22 我就知道的是好像要解ode,pde方程了，至于在像CDO pricing model, copula model, credit model这些模型中用的多得是哪些方法呢，谢谢 |
|
b***k
发帖数: 2673 | 23 ☆─────────────────────────────────────☆
p838 (p838) 于 (Tue Mar 4 15:09:18 2008) 提到:
There are 3 chinese quants mentioned by Paul wilmott in Quantative Finance
Timeline.
who know them?
☆─────────────────────────────────────☆
bachelier (bachelier) 于 (Tue Mar 4 15:33:52 2008) 提到:
David Li: Copula model
Thomas Ho and Sang-Bin Lee: Ho-Lee model in interest rate
I never met them in person but I remember Sang-Bin Lee is not a Chinese (
Korean maybe).
☆─────────────────────────────────────☆ |
|
k**k
发帖数: 61 | 24 Guess these days the only trustworthy way is through Monte-Carlo for VaR.
The idea is simple: simulate 100 portfolio returns and take the 5th worse
case as your 95% VaR. But the key is HOW to simulate your returns based on
what you've already known for the assets in your portfolio. Basically, this
is done through
1. getting the marginal distribution of individual returns
right via fitting to some fat-tail distribution such as Pareto.
2. getting the cross-dependence right via copula such as T-cop |
|
k**k
发帖数: 61 | 25 Still follow my previous argument, if we assume individual asset return
follows the following relation
r(t) = c + sigma(t)*z(t)
where z(t) ~ N(0,1) and c is constant
and you will have different sets of c, sigma(t), z(t) for different assets
in or portfolio. With the above setup we can then use GARCH(1,1) to model
sigma(t) and T-copula to capture the cross dependence among differen z(t).
That way we can obtain a more realistic relation between the different r(t)
and hence our M |
|
c******s
发帖数: 90 | 26 Essentially the correlated bi-variate uniforms generated
by the second method can be viewed as a Gaussian copula with marginal
uniform distribution. You can calculate the spearman's rho, which
is given by that formula. |
|
K*****Y
发帖数: 629 | 27 Simulate marginal distribution for each of them separately, then simulate
the joint distribution using whatever Copula you choose. |
|
s******e
发帖数: 24 | 28 subprime crisis is not because of this gaussian copula.
The name of subprime crisis already explains the cause of this crisis:
investment in the subprime mortgage. |
|
|
|
d*******1
发帖数: 293 | 31 今天看了些copula的资料, 感觉主要还是用来算correlation的,就如计算非正泰分布的变量的之间的关系, 来计算VAR. 可是这个如何用来random sampling呢? |
|
|
|
t**i
发帖数: 7 | 34 10feb的risk magazine一篇文章提到regulator还propose不让complex product的earni
ngs发成bonus；
怎么cutting edge section又在讲pricing and hedging basket credit derivative i
n gaussian copula，这不是自相矛盾吗？真看不懂啊。也不知道risk magazine是为谁
服务的。 |
|
k**k
发帖数: 61 | 35 我之前提到已经有correlated return for individual stocks,这是用historical
price,然后假设individual stock return follows:
r(t) = u + sigma(t)*z(t) (z(t) ~ i.i.d)
利用GJR(1,1)model( 用于forcast每个stock的sigma(t) )，generalized pareto
distribution( 用于fit每个stock的empirical CDF of z(t) ),外加t-copula（用于
simulate joint distribution of不同stock之间的z(t) )最后得到。剩下就是如何利
用这组simulated return来优化portfolio weight．之前的步骤都能用matlab实现，就
是最后优化不清楚如何在matlab中实现.
不知道哪位能赐教？
solver |
|
m***s
发帖数: 605 | 36 see
Rockafellar, R.T. and Uryasev, S., 2000, Optimization of conditional value-a
t-risk. J. Risk, 2, 21-41.
Rockafellar, R.T. and Uryasev, S., 2002, Conditional value-at-risk for gener
al loss distributions. J. Bank. Finance, 26(7) 1443-1471.
But I thought you were doing parametric CVaR. You have marginal and t-copula
. Everytime, you change the weights, your parametric CVaR should be differen
t from the non-parametric CVaR, no? |
|
k**k
发帖数: 61 | 37 Just read a few paragraphs in the first article. Think this is the one I'm
looking for. Thanks a lot!
As to parametric vs. non-parametric, not sure your exact definitions. What I
did is to parameterize the marginal distribution of standard innovation z(t
) from their empirical CDF. Together with a t-copula, I can directly sample
from their empirical joint distribution. That way I can obtain a set of
simulated portfolio returns taking into account the non-normal joint
distribution of returns. Thi |
|
o******e
发帖数: 74 | 38 Thank you very much, pcasnik! Those are very good references! |
|
|
t*****e
发帖数: 38 | 40 约好2点， 1点55找了个没人的位置（很难找），等到2点15分，还没来电话。回到工作
岗位，突然打来了。没有道歉，直接开始。
1.what is your strongest area? math,statistics,然后从统计开始
2. give me 3 important result of prob theory. This was OK.
3. what is the prob that A
result after computation, any other way, I gave an intuitive way, any other
way, I said sorry, he said" I have a better way I thought you could have
used,I am a little bit disappointed"
4. How could you generate a normal from uniform? I said use sum... 阅读全帖 |
|
w*********m
发帖数: 196 | 41 1. X and aX+b
2. Copula? |
|
w*********m
发帖数: 196 | 42 correlation is the linear dependence between two random variables
Using copula we can create non-linear dependence of two random variables |
|
y****d
发帖数: 432 | 43 分享地址
http://www.filesonic.com/folder/318617
分2部分，包括以下书籍：
A course in probility theory
An.Introduction.to.Copulas
Aspects of Mathematical Finance (Yor, 2008, Springer)
Computational.and.Mathematical.Modeling.in.the.Social.Sciences
convergence of stochastic processes （ by Pollard ）
Convex Optimization
Discrete-Time.Markov.Jump.Linear.Systems
EC5028.Mathematical.Finance
Elementary Differential Equations-Boyce
Introduction.to.Stochastic.Calculus.for.Finance.-.A.New.Didactic.Approach
levy process in ... 阅读全帖 |
|
f*******y
发帖数: 988 | 44 我早说了，quant现在的趋势就是IT化
需要PhD才知道怎么hedge的product，
就算政府让你卖，成熟市场不会再有人买，
新兴市场的买了输钱会赖账
prop desk剥离之后赚钱要难很多，
没后台的话要搞点大bet的话leverage上不去
这种一招就是20个的职位，主要任务就是
从事well defined的daily routine
，下一步就是招50个码工来彻底电子化
当然了，这样的职位你想通过面试，
随机过程C++复分析组合数学Copula
什么乱七八糟的你也要会才行，呵呵 |
|
y****d
发帖数: 432 | 45 8.我珍藏的40部金融数学类书籍合集[新增下载链接！]
http://www.filesonic.com/folder/318617
新增Fileserve链接
http://www.fileserve.com/file/j3twCj3
内容如下
A course in probility theory
An.Introduction.to.Copulas
Aspects of Mathematical Finance (Yor, 2008, Springer)
Computational.and.Mathematical.Modeling.in.the.Social.Sciences
convergence of stochastic processes （ by Pollard ）
Convex Optimization
Discrete-Time.Markov.Jump.Linear.Systems
EC5028.Mathematical.Finance
Elementary Differential Equations-Boyce
Introduction.to.Stochas... 阅读全帖 |
|
T*****w
发帖数: 802 | 46 Two independent random variables uniformly distributed in [0,1]. How do you
transform them, so that they stay uniformly distributed in [0,1], but the
correlation between them becomes \rho.
不知道如何用copula的方法去解?
(另外：类似的题目是如果是两个 normally distributed z1, z2 ~N(0,1),（independently）
可以用 cholesky decomposition 的方法得到
x1=z1
x2=pz1 + sqrt(1-p^2) z2 |
|
c*****n
发帖数: 83 | 47 在论坛上有很多地方需要包子，
可惜我现在才有 0.1 个伪币。
别人发包子时，由于我自己手慢总是领不到。
照这样的速度，猴年马月才有 10 个伪币。
所以在此用自己多年收藏的书籍向有包子的大牛们交换。
一个包子一本书。
有意者请发站内邮箱，注明要那些书，并附上邮箱地址，我收到包子后就发书。
以下是书籍目录：
active portfolio management.pdf
Advanced Analytical Models.pdf
Advanced Modelling in Finance Using Excel and VBA.pdf
Advances in Behavioral Finance II (Richard H. Thaler).pdf
Advances in Behavioral Finance Volume II.pdf
An Introduction to Copulas.pdf
An Introduction to High-Frequency Finance.djvu
An Introduction to High-Frequency Finance.pdf
A... 阅读全帖 |
|
|
p******e
发帖数: 756 | 49 能给讲讲这个copula怎么用么,多次看到,大致理解就是multivariate dependency,但是
具体的怎么解释呢
thx~~ |
|
y****d
发帖数: 432 | 50 包括以下书籍
★A course in probility theory
★An.Introduction.to.Copulas
★Aspects of Mathematical Finance (Yor, 2008, Springer)
★Computational.and.Mathematical.Modeling.in.the.Social.Sciences
★convergence of stochastic processes （ by Pollard ）
★Convex Optimization
★Discrete-Time.Markov.Jump.Linear.Systems
★EC5028.Mathematical.Finance
★Elementary Differential Equations-Boyce
★Introduction.to.Stochastic.Calculus.for.Finance.-.A.New.Didactic.Approach
★levy process in finance
★Markov Chains and Stochastic S... 阅读全帖 |
|
