Calibration of GARCH11 Model in QuantLib
Locked
 
|
Hi,
I am new in using QuantLib. Suppose I have the everyday close prices of S&P 500 index, next I have to convert these prices to yield rates. In common sense, daily yield is needed to calibrate GARCH11 Model. However, the comments in Garch11(a class) of QuantLib says, 'Volatilities are assumed to be expressed on an annual basis'. And I get confused. Which kind of yield should I put into the constructor of Garch11 in QuantLib? Hope someone could help me out, a simple piece of code is appreciated.
Thanks.
Zhehui Qian ------------------------------------------------------------------------------ HPCC Systems Open Source Big Data Platform from LexisNexis Risk Solutions Find What Matters Most in Your Big Data with HPCC Systems Open Source. Fast. Scalable. Simple. Ideal for Dirty Data. Leverages Graph Analysis for Fast Processing & Easy Data Exploration http://p.sf.net/sfu/hpccsystems _______________________________________________ QuantLib-users mailing list [hidden email] https://lists.sourceforge.net/lists/listinfo/quantlib-users |
|
|
That means the input yield should be annualized. Otherwise the output is not volatility at all (when we talk about volatility it is always on annual basis) Regards, Cheng 发件人: 钱哲辉 [mailto:[hidden email]] Hi, I am new in using QuantLib. Suppose I have the everyday close prices of S&P 500 index, next I have to convert these prices to yield rates. In common sense, daily yield is needed to calibrate GARCH11 Model. However, the comments in Garch11(a class) of QuantLib says, 'Volatilities are assumed to be expressed on an annual basis'. And I get confused. Which kind of yield should I put into the constructor of Garch11 in QuantLib? Hope someone could help me out, a simple piece of code is appreciated. Thanks. Zhehui Qian ------------------------------------------------------------------------------ HPCC Systems Open Source Big Data Platform from LexisNexis Risk Solutions Find What Matters Most in Your Big Data with HPCC Systems Open Source. Fast. Scalable. Simple. Ideal for Dirty Data. Leverages Graph Analysis for Fast Processing & Easy Data Exploration http://p.sf.net/sfu/hpccsystems _______________________________________________ QuantLib-users mailing list [hidden email] https://lists.sourceforge.net/lists/listinfo/quantlib-users |
|
|
Hi
Cheng,
Thank you for
your answer! However, I'm quite sure there is volatility on daily basis and this
kind of volatility appears in many cases. For example, we can put daily returns,
like ln(S2/S1), into the GARCH model in Matlab to calibrate the parameters.
Thanks again.
Regards,
Zhehui
发件人： [hidden email]
发送时间： 2014-06-23 15:32
收件人： [hidden email]; [hidden email]
主题： 答复: [Quantlib-users] Calibration of GARCH11 Model in
QuantLib That
means the input yield should be annualized. Otherwise the output is not
volatility at all (when we talk about volatility it is always on annual
basis) Regards, Cheng 发件人: 钱哲辉
[mailto:[hidden email]] Hi, I am new in using QuantLib. Suppose I have the everyday close prices of S&P 500 index, next I have to convert these prices to yield rates. In common sense, daily yield is needed to calibrate GARCH11 Model. However, the comments in Garch11(a class) of QuantLib says, 'Volatilities are assumed to be expressed on an annual basis'. And I get confused. Which kind of yield should I put into the constructor of Garch11 in QuantLib? Hope someone could help me out, a simple piece of code is appreciated. Thanks. Zhehui Qian ------------------------------------------------------------------------------ HPCC Systems Open Source Big Data Platform from LexisNexis Risk Solutions Find What Matters Most in Your Big Data with HPCC Systems Open Source. Fast. Scalable. Simple. Ideal for Dirty Data. Leverages Graph Analysis for Fast Processing & Easy Data Exploration http://p.sf.net/sfu/hpccsystems _______________________________________________ QuantLib-users mailing list [hidden email] https://lists.sourceforge.net/lists/listinfo/quantlib-users |
|
|
In reply to this post by cheng li
Hi Cheng,
Thank you for your answer! However, I'm quite sure there is volatility on daily basis and this kind of volatility appears in many cases. For example, we can put daily returns, like ln(S2/S1), into the GARCH model in Matlab to calibrate the parameters. Thanks again. Regards, Zhehui |
|
|
In reply to this post by qzhhugh
Hi zhihui， Yes, what you say is true. There is no definite reason to define volatility on annual basis. However if you input daily return without annual adjustments, you should be aware that your output vol is also annualized at all. Regards, Cheng 发件人: 钱哲辉 [mailto:[hidden email]] Hi Cheng, Thank you for your answer! However, I'm quite sure there is volatility on daily basis and this kind of volatility appears in many cases. For example, we can put daily returns, like ln(S2/S1), into the GARCH model in Matlab to calibrate the parameters. Thanks again. Regards, Zhehui 发件人： [hidden email] 发送时间： 2014-06-23 15:32 收件人： [hidden email]; [hidden email] 主题： 答复: [Quantlib-users] Calibration of GARCH11 Model in QuantLib That means the input yield should be annualized. Otherwise the output is not volatility at all (when we talk about volatility it is always on annual basis) Regards, Cheng 发件人: 钱哲辉 [[hidden email]] Hi, I am new in using QuantLib. Suppose I have the everyday close prices of S&P 500 index, next I have to convert these prices to yield rates. In common sense, daily yield is needed to calibrate GARCH11 Model. However, the comments in Garch11(a class) of QuantLib says, 'Volatilities are assumed to be expressed on an annual basis'. And I get confused. Which kind of yield should I put into the constructor of Garch11 in QuantLib? Hope someone could help me out, a simple piece of code is appreciated. Thanks. Zhehui Qian ------------------------------------------------------------------------------ HPCC Systems Open Source Big Data Platform from LexisNexis Risk Solutions Find What Matters Most in Your Big Data with HPCC Systems Open Source. Fast. Scalable. Simple. Ideal for Dirty Data. Leverages Graph Analysis for Fast Processing & Easy Data Exploration http://p.sf.net/sfu/hpccsystems _______________________________________________ QuantLib-users mailing list [hidden email] https://lists.sourceforge.net/lists/listinfo/quantlib-users |
Re: Calibration of GARCH11 Model in QuantLib
|
|
In reply to this post by qzhhugh
Hi Zhehui, You can rescale your returns to whatever time horizon you please and get the results for the same time horizon. The comment you are referring to is left there unchanged because i simply overlooked it. Hope this helps. Regards, Slava Mazur From: 钱哲辉 [mailto:[hidden email]] Hi, I am new in using QuantLib. Suppose I have the everyday close prices of S&P 500 index, next I have to convert these prices to yield rates. In common sense, daily yield is needed to calibrate GARCH11 Model. However, the comments in Garch11(a class) of QuantLib says, 'Volatilities are assumed to be expressed on an annual basis'. And I get confused. Which kind of yield should I put into the constructor of Garch11 in QuantLib? Hope someone could help me out, a simple piece of code is appreciated. Thanks. Zhehui Qian ------------------------------------------------------------------------------ HPCC Systems Open Source Big Data Platform from LexisNexis Risk Solutions Find What Matters Most in Your Big Data with HPCC Systems Open Source. Fast. Scalable. Simple. Ideal for Dirty Data. Leverages Graph Analysis for Fast Processing & Easy Data Exploration http://p.sf.net/sfu/hpccsystems _______________________________________________ QuantLib-users mailing list [hidden email] https://lists.sourceforge.net/lists/listinfo/quantlib-users |
| Free forum by Nabble | Edit this page |