CHAPTER #7
Value ate risk (VAR)
Historical Perspectives on VAR
VAR a widely used measure is credited by JPMorgan .The Chairman, Dennis Weatherstone, was
dissatisfied with the long-risk reports he received every day. These contained a huge amount of
detail on the Greek letters for different exposures, but very little that was really useful to top
management. He asked for something simple that focused on the bank’s total exposure over the next
24 hours measured across the bank’s entire trading portfolio. At first his subordinates said this was
impossible , but eventually they adapted the Markowitz portfolio theory to develop a VAR report.
Producing the report entailed a huge amount of work involving the collection of data daily on the
positions held by the bank around the world, the handling of different time zones, the estimation of
correlations and instabilities , and the development of computer systems. The work was completed
in about1990..
Historical Perspectives
The main benefit of the new system was that senior management had a better understanding of the
risks being taken by the bank and were better able to allocate capital within the bank. Other banks
had been working on similar approaches for aggregating risks and by 1993 VAR was established
as an important risk measure .
Banks usually keep the details about the models they develop internally a secret. However, in
1994 JPMorgan made a simplified version of their own system, which they called Risk Metrics.
Risk Metrics included variances and co variances for a very large number of different market
variables. This attracted a lot of attention and led to debates about the pros and cons of different
VaR models. Software firms started offering their own VaR models, some of which used
the database. After that ,VaR was rapidly adopted as a standard by financial institutions and some
nonfinancial corporations. The BIS Amendment, which was based on VaR was announced in 1996
and implemented in 1998. Later the Risk Metrics group within JPMorgan was turned off as a
separate company. This company developed Credit Metrics for handling credit risks in 1997 and
Corporate Metrics for handling the risks faced by non-financial corporations in 1999.
Value at risk
DEFINITION OF VAR
When using the value at risk measure, we are interested in making a statement
of the following form:
“We are X percent certain that we will not lose more than V dollars in time T.”
VAR
• The variable V is the VAR of the portfolio. It is a function of
two parameters: the time horizon, T, and the confidence
level, X percent.
• It is the loss level during a time period of length T that we
are X% certain will not be exceeded.
VAR:
• VAR can be calculated from either the probability distribution
of gains during time T or the probability distribution of losses
during time T. (In the former case, losses are negative gains; in
the latter case, gains are negative losses.)
• When the distribution of gains is used, VAR is equal to minus
the gain at the (100 − X) the percentile of the distribution. When
the distribution of losses is used .
VAR:
• VAR is equal to the loss at the X the percentile of the
distribution .For example, when T is five days and X = 97, VAR
is minus the third percentile of the distribution of gains in the
value of the portfolio over the next five days. Alternatively, it is
the 97th percentile of the distribution of losses in the value of the
portfolio over the next five days.
VAR and Capital
How much Amount of capital they should keep ?
VAR is used by regulators of financial institutions and by financial
institutions themselves to determine the amount of capital they should keep.
Regulators calculate the capital required for market risk as a multiple of the
VaR calculated using a 10-day Time horizon and a 99% confidence level.
They calculate capital for credit risk and operational risk.
VAR and Capital
Suppose that the VAR of a portfolio for a confidence level of 99.9% and a time
horizon of one year is $50 million. This means that in extreme the financial
institution will lose more than$50 million in a year. It also means that if it
keeps $50 million in capital it will have a 99.9% probability of not running out
of capital in the course of one year.
Suppose we are trying to design a risk measure that will equal the capital a
financial institution is required to keep. Is VAR (with an appropriate time
horizon and an appropriate confidence level) the best measure?
Artzner et al., have examined this question. They first proposed a number of
properties that such a risk measure should have.
VAR and Capital
These are:
• 1. Monotonicity: If a portfolio produces a worse result than another
portfolio for every state of the world, its risk measure should be greater.
• 2. Translation Invariance: If an amount of cash (K) is added to a portfolio,
its risk measure should go down by K.
• 3. Homogeneity: Changing the size of a portfolio by a factor while keeping
there relative amounts of different items in the portfolio the same, should
result in the risk measure being multiplied.
• 4. Subadditivity: The risk measure for two portfolios after they have been
merged should be no greater than the sum of their risk measures before they
were merged.
VAR and Capital
• The first condition is straightforward. If one portfolio always performs worse than
another portfolio, it clearly should be capital.
• The second condition is also reasonable. If we add an amount of cash equal to K to a
portfolio this provides a buffer against losses and should reduce the capital
requirement by K.
• The third condition is also reasonable. If we double the size of a portfolio,
presumably we should require twice as much capital.
• The fourth condition states that diversification helps reduce risks. When we aggregate
two portfolios, the total risk measure should either decrease or stay the same .VAR
satisfies the first three conditions. However, it does not always satisfy the fourth one.
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 can things get?”
Time Horizon
• An appropriate choice for the time horizon depends on the application. The
trading desks of banks calculate the profit and loss daily. When their
positions are fairly liquid and actively managed, it therefore makes sense to
calculate a VAR over a time horizon of one trading day. If the VAR turns out
to be unacceptable, the portfolio can be adjusted fairly quickly. Also, a VAR
with a longer time horizon might not be meaningful because of changes in
the composition of the portfolio.
Time Horizon
• For an investment portfolio held by a pension fund, a time horizon of one
month is often chosen. This is because the portfolio is traded less actively
and some of the instruments in the portfolio are less liquid. Also the
performance of pension fund portfolios is often monitored monthly.
Time Horizon
• Instead of calculating the 10-day, 99% VAR directly
analysts usually calculate a 1-day 99% VAR and
assume
10 - day VaR 10 1 - day VAR
• This is exactly true when portfolio changes on
successive days come from independent identically
distributed normal distributions
Time Horizon
• This formula is exactly true when the changes in the value of
the portfolio on successive days have independent identical
normal distributions with mean zero. In other cases, it is an
approximation.
1. The standard deviation of the sum on T independent identical
distributions is √T times the standard deviation of each
distribution.
2.The sum of independent normal distributions is normal.
The Historical Simulation Approach
• A method of calculating value-at-risk (VaR) that uses historical data to assess the
impact of market moves on a portfolio. A current portfolio is subjected to historically
recorded market movements; this is used to generate a distribution of returns on the
portfolio. This distribution can then be used to calculate the maximum loss with a
given likelihood that is, the VaR.
• Because historical simulation uses real data, it can capture unexpected events and
correlations that would not necessarily be predicted by a theoretical model.
The Historical Simulation Approach
• The main point here to remember is that the historical simulation does not
make any assumptions about the distributions of returns.
• the historical simulation uses an empirical return distribution to calculate
VAR. The simple assumption here is that the past returns give some
indication of what the future will be like and therefore an idea of possible
loss distributions. This can be a dangerous assumption.
The Historical Simulation Approach
• Create a database of the daily movements in all market variables.
• The first simulation trial assumes that the percentage changes in all market
variables are as on the first day
• The second simulation trial assumes that the percentage changes in all
market variables are as on the second day and so on
The Model-Building Approach
• An alternative to the historical simulation approach that is sometimes used
by portfolio managers is the model-building approach, sometimes also
referred to as the variance–covariance approach.
• This involves assuming a model for the joint distribution of changes in
market variables and using historical data to estimate the model parameters.
The Model-Building Approach
• The mean and standard deviation of the value of a portfolio can be calculated
from the mean and standard deviation of the returns on the underlying
products and the correlations between those returns.if, daily returns on the
investments are assumed to be multivariate normal, the probability
distribution for the change in the value of the portfolio over one day is also
normal. This makes it very easy to calculate value at risk.
Credit scoring models
• Credit-scoring models use data on observed borrower characteristics either to
calculate the probability of default or to sort borrowers into different default
risk classes. By selecting and combining different economic and financial
borrower characteristics, an FI manager may be able to:
1. Numerically establish which factors are important in explaining default risk.
2. Evaluate the relative degree or importance of these factors.
3. Improve the pricing of default risk.
4. Screen high-risk loan applicants.
5. Calculate any reserves needed to meet expected future loan losses
Altman’s Z-Score.
Altman developed a Z-score model for analyzing publicly traded
manufacturing firms in the United States. The indicator variable Z is an overall
measure of the borrower’s default risk classification. This classification, in
turn, depends on the values of various financial ratios of the borrower and the
weighted importance of these ratios based on the observed experience of
defaulting versus non defaulting borrowers derived from a discriminant
analysis model.
Altman’s Z-Score.
• Altman’s credit-scoring model takes the following form:
• Z = 1.2X1 1.4 X2 3.3X3 0.6X4 1.0 X5
Z-Score = 1.2A + 1.4B + 3.3C + 0.6D + 1.0E
Where
• X1 = Working capital/Total assets
• X2 = Retained earnings/ Total assets
• X3 = Earnings before interest and taxes/ Total assets
• X4 = Market value of equity/Book value of long-term debt or Total Liabilities
• X5 = Sales/ Total assets
Altman’s Z-Score
The higher the value of Z, the lower the borrower’s default risk classification.
Thus, low or negative Z values may be evidence that the borrower is a member
of a relatively high default risk class.
Example#2
• Let’s assume Bill’s Boats’ financial statements had the following figures:
• Sales: $1M
• EBIT: $500,000
• Total Assets: $2M
• Book Value of Total Liabilities: $1M
• Retained Earnings: $1M
• Market Value of Equity: $3M
• Working Capital: $500,000
Calculation:
• Bill’s Altman score would be calculated like this:
• Score = 1.2(.25) + 1.4(.5) + 3.3(.25) + 0.6(2) + 1.0(.5)
Score = (.375 + .7 + .825 + .12 + .5) = 2.52
• A = $500,000/ $2,000,000
• B = $1,000,000 / $2,000,000
• C = $500,000 / $2,000,000
• D = $2,000,000 / $1,000,000
• E = $1,000,000 / $2,000,000
• Bill’s Boats’ score is 2.52