14123_varnew

Upload: jesse-sanders

Post on 03-Jun-2018

219 views

Category:

Documents


0 download

TRANSCRIPT

  • 8/12/2019 14123_VARNew

    1/24

    Options, Futures, and Other Derivatives

    7thEdition, Copyright John C. Hull2008 1

    The Question Being Asked inVaR

    What loss level is such that we areX%confident it will not be exceeded inN

    business days?

  • 8/12/2019 14123_VARNew

    2/24

    Value at Risk

    The Value at Risk measures the potentialloss in value of a risky asset or portfolioover a defined period for a given confidenceinterval. Thus, if the VaR on an asset is $100 million at a one-week, 95% confidencelevel, there is a only a 5% chance that thevalue of the asset will drop more than $ 100

    million over any given week

    Options, Futures, and Other

    Derivatives, 7th Edition, Copyright John C. Hull 2008 2

  • 8/12/2019 14123_VARNew

    3/24

    Options, Futures, and Other Derivatives

    7thEdition, Copyright John C. Hull2008 3

    VaR and Regulatory Capital(Business Snapshot 20.1, page 452)

    Regulators base the capital they requirebanks to keep on VaR

    The market-risk capital is ktimes the 10-day 99% VaR where kis at least 3.0

  • 8/12/2019 14123_VARNew

    4/24

    Options, Futures, and Other Derivatives

    7thEdition, Copyright John C. Hull2008 4

    Advantages of VaR

    It captures an important aspect of risk

    in a single number

    It is easy to understand

    It asks the simple question: How bad canthings get?

  • 8/12/2019 14123_VARNew

    5/24

    Options, Futures, and Other Derivatives

    7thEdition, Copyright John C. Hull2008 5

    Time Horizon

    Instead of calculating the 10-day, 99% VaRdirectly analysts usually calculate a 1-day99% VaR and assume

    This is exactly true when portfolio changeson successive days come from independent

    identically distributed normal distributions

    day VaR1-day VaR-10 10

  • 8/12/2019 14123_VARNew

    6/24

    VAR of portfolio

    An investor has invested 70000 Rs inasset A and 30000 Rs in asset B. Daily

    VaR on asset A is 20000 Rs. and on

    asset B is 8000 Rs. Calculate the daily

    VaR for overall investment portfolio.

    Options, Futures, and Other

    Derivatives, 7th Edition, Copyright John C. Hull 2008 6

  • 8/12/2019 14123_VARNew

    7/24

    Variance-Covariance Method

    Steps:

    Calculate the value of Mean and Std Devfor the return data series.

    Portfolio Mean Return,:

    Options, Futures, and Other

    Derivatives, 7th Edition, Copyright John C. Hull 2008 7

  • 8/12/2019 14123_VARNew

    8/24

    Portfolio Std. Dev.:

    Options, Futures, and Other

    Derivatives, 7th Edition, Copyright John C. Hull 2008 8

  • 8/12/2019 14123_VARNew

    9/24

    Percentile value at risk,

    VAR=|P+ z| V

    Where, P= expected return , V = portfolio value , =volatility

    Options, Futures, and Other

    Derivatives, 7th Edition, Copyright John C. Hull 2008 9

  • 8/12/2019 14123_VARNew

    10/24

    An investor has invested 400,000 Rs inan portfolio based on Index XYZ.

    Calculate the 99 percentile, 10 days VaR

    for his portfolio by using Variance-

    Covariance method. Z value is 2.33 and

    Historical prices for index XYZ are given

    given as following

    Options, Futures, and Other

    Derivatives, 7th Edition, Copyright John C. Hull 2008 10

  • 8/12/2019 14123_VARNew

    11/24

    Date 4-1-12 5-1-12 6-1-12 7-1-12 8-1-12 9-1-12 10-1-12 11-1-12 12-1-12Price 4123 4823 4712 5612 4935 5832 5912 5712 5467

    Options, Futures, and Other

    Derivatives, 7th Edition, Copyright John C. Hull 2008 11

  • 8/12/2019 14123_VARNew

    12/24

    An investor has invested 20000 Rs inasset A and 80000 Rs in asset B. Daily

    VaR on asset A is 50000 Rs. and on

    asset B is 2000 Rs. Calculate the daily

    VaR for overall investment portfolio.

    Portfolio VaR = W1 * VaR(A) + W1 * VaR(B)

    Options, Futures, and Other

    Derivatives, 7th Edition, Copyright John C. Hull 2008 12

  • 8/12/2019 14123_VARNew

    13/24

    Options, Futures, and Other Derivatives

    7thEdition, Copyright John C. Hull2008 13

    Historical Simulation(See Tables 20.1 and 20.2, page 454-55))

    Historical simulations represent the simplestway of estimating the Value at Risk formany portfolios. In this approach, the VaRfor a portfolio is estimated by creating a

    hypothetical time series of returns on thatportfolio, obtained by running the portfoliothrough actual historical data andcomputing the changes that would have

    occurred in each period.

  • 8/12/2019 14123_VARNew

    14/24

    To run a historical simulation, we begin withtime series data on each market risk factor,

    just as we would for the variance-covariance approach. However, we do notuse the data to estimate variances and co-variances looking forward, since thechanges in the portfolio over time yield all

    the information you need to compute theValue at Risk

    Options, Futures, and Other

    Derivatives, 7th Edition, Copyright John C. Hull 2008 14

    Hi t i l i l ti V R

  • 8/12/2019 14123_VARNew

    15/24

    Historical simulation VaR

    Method-

    Historical simulation method includesfollowing Steps-

    Define current portfolio value=1000000

    Confidence level- 95% for internal purposeAnd 99% for credit rating and reportingpurpose

    Forecast horizon is 10 days so we will

    calculate 10 day- VaR

    10 Days-VaR= SQRT (10)*Daily VaR

    Options, Futures, and Other

    Derivatives, 7th Edition, Copyright John C. Hull 2008 15

  • 8/12/2019 14123_VARNew

    16/24

    Historical Observation Period-I am takingS&P CNX Nifty data from 1 Jan 2007 to 30Nov 2009

    Calculating daily return data Multiply this historical return data with

    current portfolio value to create hypotheticalportfolio

    Arrange this in descending order andplotting histogram of this data

    Calculate 95thand 99thpercentile values

    using hypothetical return data.Options, Futures, and Other

    Derivatives, 7th Edition, Copyright John C. Hull 2008 16

  • 8/12/2019 14123_VARNew

    17/24

    Options, Futures, and Other Derivatives

    7thEdition, Copyright John C. Hull2008 17

    Historical Simulation continued

    Suppose we use mdays of historical data Let v

    ibe the value of a variable on day i

    There are m1simulation trials

    The ith trial assumes that the value of themarket variable tomorrow (i.e., on day m+1)is

    1i

    i

    m

    v

    v

    v

  • 8/12/2019 14123_VARNew

    18/24

    Options, Futures, and Other Derivatives

    7thEdition, Copyright John C. Hull2008 18

    The Model-Building Approach

    The main alternative to historical simulationis to make assumptions about theprobability distributions of return on themarket variables and calculate theprobability distribution of the change in thevalue of the portfolio analytically

    This is known as the model building

    approach or the variance-covarianceapproach

  • 8/12/2019 14123_VARNew

    19/24

    Options, Futures, and Other Derivatives

    7thEdition, Copyright John C. Hull2008 19

    Daily Volatilities

    In option pricing we measure volatility peryear

    In VaR calculations we measure volatility

    per day

    252

    year

    day

  • 8/12/2019 14123_VARNew

    20/24

    Options, Futures, and Other Derivatives

    7thEdition, Copyright John C. Hull2008 20

    Daily Volatility continued

    Strictly speaking we should define dayasthe standard deviation of the continuouslycompounded return in one day

    In practice we assume that it is the standarddeviation of the percentage change in oneday

  • 8/12/2019 14123_VARNew

    21/24

    Options, Futures, and Other Derivatives

    7thEdition, Copyright John C. Hull2008 21

    Microsoft Example (page 456)

    We have a position worth $10 million inMicrosoft shares

    The volatility of Microsoft is 2% per day

    (about 32% per year) We useN=10 andX=99

  • 8/12/2019 14123_VARNew

    22/24

    Options, Futures, and Other Derivatives

    7thEdition, Copyright John C. Hull2008 22

    Microsoft Example continued

    The standard deviation of the change in theportfolio in 1 day is $200,000

    The standard deviation of the change in 10

    days is

    200 000 10 456, $632,

  • 8/12/2019 14123_VARNew

    23/24

    Options, Futures, and Other Derivatives

    7thEdition, Copyright John C. Hull2008 23

    Microsoft Example continued

    We assume that the expected change in thevalue of the portfolio is zero (This is OK forshort time periods)

    We assume that the change in the value ofthe portfolio is normally distributed

    SinceN(2.33)=0.01, the VaR is

    2 33 632 456 473 621. , $1, ,

  • 8/12/2019 14123_VARNew

    24/24

    Options, Futures, and Other Derivatives

    7thEdition, Copyright John C. Hull2008 24

    AT&T Example (page 457)

    Consider a position of $5 million in AT&T The daily volatility of AT&T is 1% (approx

    16% per year)

    The S.D per 10 days is

    The VaR is50 000 10 144, $158,

    158 114 2 33 405, . $368,