Risk Management辅导、VaR，ES留学生辅导、讲解R、R程序语言讲解 调试Matlab程序|辅导Web开发
- 首页 >> 其他 Quantitative Risk Management
Coursework
The objective of the coursework is to allow you a first hand appreciation of some of
the key issues in measuring risk. There are two parts, one involving analysis of a
portfolio having a single risk factor, the other involving analysis of a portfolio having
two risk factors.
1. Select, and acquire historical data for, a traded financial asset. This might, for
instance, be a commodity, a security, or a stock market index. Suppose that
you had invested 1 million pounds in this asset at the date given by the earliest
date in your data.
(a) Explain your choice of sample size.
(b) Using the data up to, but not including, 20th February 2019, calculate
the simple daily returns for your asset [use simple returns throughout this
coursework]. Examine and describe the key statistical features of your sample
of returns.
(c) Calculate VaR and ES for 20th February 2019 using a one day holding period,
and a confidence level of 95%, using the following methods:
i. Basic Historical Simulation
ii. Age-weighted Historical Simulation
iii. Hull-White
iv. Parametric, using the Normal distribution, without volatility adjustment
v. Parametric, using the Normal distribution, with volatility adjustment
vi. Parametric, using an appropriate distribution, without volatility adjustment
vii. Parametric, using an appropriate distribution, with volatility adjustment
You should present your results in a single table, and briefly provide a commentary
on the similarities and differences.
(d) Explain why it would be problematic to have used log returns to calculate
VaR and ES for any of the parametric methods in the previous question.
2. Acquire data for another asset and suppose that at at the start of the time series
you invested 1 million pounds in this asset as well. You now have a portfolio
which at the start of the data series was worth 2 million pounds. Suppose initially
that your portfolio is not actively managed, so that your holdings of each asset
remain unchanged.
(a) Using the data up to, but not including, 20th February 2019, calculate the
simple daily returns for each of the individual assets which constitute your
portfolio. Examine and describe the key statistical features of your sample
of returns.
(b) Calculate VaR and ES for 20th February 2019 using a one day holding period,
and a confidence level of 95%, using each of the following methods
i. Basic Historical Simulation
ii. Age-weighted Historical Simulationiii. Hull-White
iv. Parametric, using the Normal distribution, without volatility adjustment
v. Parametric, using the Normal distribution, with volatility adjustment
vi. Parametric, using an appropriate distribution, without volatility adjustment
vii. Parametric, using an appropriate distribution, with volatility adjustment
(c) Explain how you might have been able to reduce your risk exposure for 20th
February had you been able to adjust your portfolio on the 19th February.
The deadline for submission is as notified in the module outline. Please see Moodle
for further discussion of useful approaches to this topic, and hints about R code.
Coursework
The objective of the coursework is to allow you a first hand appreciation of some of
the key issues in measuring risk. There are two parts, one involving analysis of a
portfolio having a single risk factor, the other involving analysis of a portfolio having
two risk factors.
1. Select, and acquire historical data for, a traded financial asset. This might, for
instance, be a commodity, a security, or a stock market index. Suppose that
you had invested 1 million pounds in this asset at the date given by the earliest
date in your data.
(a) Explain your choice of sample size.
(b) Using the data up to, but not including, 20th February 2019, calculate
the simple daily returns for your asset [use simple returns throughout this
coursework]. Examine and describe the key statistical features of your sample
of returns.
(c) Calculate VaR and ES for 20th February 2019 using a one day holding period,
and a confidence level of 95%, using the following methods:
i. Basic Historical Simulation
ii. Age-weighted Historical Simulation
iii. Hull-White
iv. Parametric, using the Normal distribution, without volatility adjustment
v. Parametric, using the Normal distribution, with volatility adjustment
vi. Parametric, using an appropriate distribution, without volatility adjustment
vii. Parametric, using an appropriate distribution, with volatility adjustment
You should present your results in a single table, and briefly provide a commentary
on the similarities and differences.
(d) Explain why it would be problematic to have used log returns to calculate
VaR and ES for any of the parametric methods in the previous question.
2. Acquire data for another asset and suppose that at at the start of the time series
you invested 1 million pounds in this asset as well. You now have a portfolio
which at the start of the data series was worth 2 million pounds. Suppose initially
that your portfolio is not actively managed, so that your holdings of each asset
remain unchanged.
(a) Using the data up to, but not including, 20th February 2019, calculate the
simple daily returns for each of the individual assets which constitute your
portfolio. Examine and describe the key statistical features of your sample
of returns.
(b) Calculate VaR and ES for 20th February 2019 using a one day holding period,
and a confidence level of 95%, using each of the following methods
i. Basic Historical Simulation
ii. Age-weighted Historical Simulationiii. Hull-White
iv. Parametric, using the Normal distribution, without volatility adjustment
v. Parametric, using the Normal distribution, with volatility adjustment
vi. Parametric, using an appropriate distribution, without volatility adjustment
vii. Parametric, using an appropriate distribution, with volatility adjustment
(c) Explain how you might have been able to reduce your risk exposure for 20th
February had you been able to adjust your portfolio on the 19th February.
The deadline for submission is as notified in the module outline. Please see Moodle
for further discussion of useful approaches to this topic, and hints about R code.