Volatility

Chapter 10

Risk Management and Financial Institutions 3e, Chapter 10, Copyright John 1C. Hull 2012
 Definition of Volatility
Suppose that Si is the value of a variable on
day i. The volatility per day is the standard
deviation of ln(Si /Si-1)
Normally days when markets are closed are
ignored in volatility calculations (see Business
Snapshot 10.1, page 207)
The volatility per year is 252 times the daily
volatility
Variance rate is the square of volatility

Risk Management and Financial Institutions 3e, Chapter 10, Copyright John C.
2 Hull 2012
 Implied Volatilities
Of the variables needed to price an option
the one that cannot be observed directly is
volatility
We can therefore imply volatilities from
market prices and vice versa

Risk Management and Financial Institutions 3e, Chapter 10, Copyright John C.
3 Hull 2012
VIX Index: A Measure of the Implied
Volatility of the S&P 500 (Figure 10.1, page
208)

Risk Management and Financial Institutions 3e, Chapter 10, Copyright John C.
4 Hull 2012
 Are Daily Changes in Exchange Rates
Normally Distributed? Table 10.1, page 209

Real World (%) Normal Model (%)

>1 SD 25.04 31.73
>2SD 5.27 4.55
>3SD 1.34 0.27
>4SD 0.29 0.01
>5SD 0.08 0.00
>6SD 0.03 0.00

Risk Management and Financial Institutions 3e, Chapter 10, Copyright John C.
5 Hull 2012
 Heavy Tails
Daily exchange rate changes are not normally
distributed
The distribution has heavier tails than the normal
distribution
It is more peaked than the normal distribution
This means that small changes and large
changes are more likely than the normal
distribution would suggest
Many market variables have this property,
known as excess kurtosis
Risk Management and Financial Institutions 3e, Chapter 10, Copyright John C.
6 Hull 2012
 Normal and Heavy-Tailed
Distribution

Risk Management and Financial Institutions 3e, Chapter 10, Copyright John C.
7 Hull 2012
 Alternatives to Normal Distributions:
The Power Law (See page 211)

Prob(v > x) = Kx-

This seems to fit the behavior of the

returns on many market variables better
than the normal distribution

Risk Management and Financial Institutions 3e, Chapter 10, Copyright John C.
8 Hull 2012
 Log-Log Test for Exchange Rate
Data

Risk Management and Financial Institutions 3e, Chapter 10, Copyright John C.
9 Hull 2012


Volatility

2
n
m1
(
u
ui1n
m

n
i
1
u

i)
Standard Approach to Estimating

2
Define n as the volatility per day between

m
day n-1 and day n, as estimated at end of day
n-1
Define S as the value of market variable at
i
end of day i
Define u = ln(S /S )
i i i-1

Risk Management and Financial Institutions 3e, Chapter 10, Copyright John C.
10Hull 2012



1
u
m
Simplifications Usually Made in
Risk Management
Define

Assume

Replace

This gives
m
221n
ni i
ui as (SiSi-1)/Si-1
that the mean value of ui is zero
m-1 by m

Risk Management and Financial Institutions 3e, Chapter 10, Copyright John C.
11Hull 2012


h
e

u
r
w1
22
n
m
m
i
1
ii
1
i
n
i
Weighting Scheme
Instead of assigning equal weights to the
observations we can set

Risk Management and Financial Institutions 3e, Chapter 10, Copyright John C.
12Hull 2012






V
r
w
h

e
1u
2
n
m m
L
i
ii
ARCH(m) Model

1

2
i
n
i
1
In an ARCH(m) model we also assign
some weight to the long-run variance rate,
VL:

Risk Management and Financial Institutions 3e, Chapter 10, Copyright John C.
13Hull 2012
 EWMA Model
In

(1

)u2
2
nn
2
1n
1
an exponentially weighted moving
average model, the weights assigned to
(page 216)

the u2 decline exponentially as we move

back through time
This leads to

Risk Management and Financial Institutions 3e, Chapter 10, Copyright John C.
14Hull 2012
 Attractions of EWMA
Relatively little data needs to be stored
We need only remember the current
estimate of the variance rate and the most
recent observation on the market variable
Tracks volatility changes
RiskMetrics uses = 0.94 for daily
volatility forecasting

Risk Management and Financial Institutions 3e, Chapter 10, Copyright John C.
15Hull 2012


V


u


GARCH (1,1), page 218

2
2
nLn
2
1n
1
In GARCH (1,1) we assign some weight to
the long-run average variance rate

Since weights must sum to 1

Risk Management and Financial Institutions 3e, Chapter 10, Copyright John C.
16Hull 2012





u

2
nV
L


1


2
2
n
1
n1
GARCH (1,1) continued
Setting VL the GARCH (1,1) model is

and

Risk Management and Financial Institutions 3e, Chapter 10, Copyright John C.
17Hull 2012
 Example
Suppose

The

0...0213u086
2121
2nnn
long-run variance rate is 0.0002 so
that the long-run volatility per day is 1.4%

Risk Management and Financial Institutions 3e, Chapter 10, Copyright John C.
18Hull 2012
 Suppose

0..2013.010.8602560.236
Example continued
that the current estimate of the
volatility is 1.6% per day and the most
recent percentage change in the market
variable is 1%.
The new variance rate is

The new volatility is 1.53% per day

Risk Management and Financial Institutions 3e, Chapter 10, Copyright John C.
19Hull 2012
 GARCH (p,q)

u p
nii
1j
22 n
iq
j
1
2
n
j
Risk Management and Financial Institutions 3e, Chapter 10, Copyright John C.
20Hull 2012
 Other Models
Many other GARCH models have been
proposed
For example, we can design a GARCH
models so that the weight given to ui2
depends on whether ui is positive or
negative

Risk Management and Financial Institutions 3e, Chapter 10, Copyright John C.
21Hull 2012
 Variance Targeting
One way of implementing GARCH(1,1)
that increases stability is by using variance
targeting
We set the long-run average volatility
equal to the sample variance
Only two other parameters then have to
be estimated

Risk Management and Financial Institutions 3e, Chapter 10, Copyright John C.
22Hull 2012
 Maximum Likelihood Methods

In maximum likelihood methods we

choose parameters that maximize the
likelihood of the observations occurring

Risk Management and Financial Institutions 3e, Chapter 10, Copyright John C.
23Hull 2012
 Example 1 (page 220)
We

happens?

p(1)
observe that a certain event happens
one time in ten trials. What is our estimate
of the proportion of the time, p, that it

The probability of the outcome is

We maximize this to obtain a maximum

likelihood estimate: p = 0.1
9
Risk Management and Financial Institutions 3e, Chapter 10, Copyright John C.
24Hull 2012
 M
ag
o
v
x
iT
m
z
e
:h
:
is
re
s
2
lv
1
nv
e
x
p
(1)u

u
2
v
Example 2 (page 220-221)

n
ii
1
n

1i
n2
i
2
i1
2
i
Estimate the variance of observations
from a normal distribution with mean zero

Risk Management and Financial Institutions 3e, Chapter 10, Copyright John C.
25Hull 2012
 Application to GARCH (1,1)

ln(v)
ni1ii2
We choose parameters that maximize

u
Risk Management and Financial Institutions 3e, Chapter 10, Copyright John C.
26Hull 2012
 Calculations for Yen Exchange
Rate Data (Table 10.4, page 222)

Day Si ui vi =i2 -ln vi-ui2/vi

1 0.007728
2 0.007779 0.006599
3 0.007746 -0.004242 0.00004355 9.6283
4 0.007816 0.009037 0.00004198 8.1329
5 0.007837 0.002687 0.00004455 9.8568
.
2423 0.008495 0.000144 0.00008417 9.3824
22,063.5833

Risk Management and Financial Institutions 3e, Chapter 10, Copyright John C.
27Hull 2012
 Daily Volatility of Yen: 1988-1997

Risk Management and Financial Institutions 3e, Chapter 10, Copyright John C.
28Hull 2012
 [
2nt]
E
(L
V )t(
Forecasting Future Volatility
(Equation 10.14, page 226)

2nV
L)
A few lines of algebra shows that

To estimate the volatility for an option

lasting T days we must integrate this from
0 to T

Risk Management and Financial Institutions 3e, Chapter 10, Copyright John C.
29Hull 2012
Forecasting Future Volatility cont

The volatility per year for an option

lasting T days is
1 e aT

(T ) 252 VL V (0) VL
aT
where
1
a ln

Risk Management and Financial Institutions 3e, Chapter 10, Copyright John C.
30Hull 2012
 Volatility Term Structures
(Equation 10.16, page 228)

The GARCH (1,1) model allows us to

predict volatility term structures
changes
When (0) changes by (0), GARCH
(1,1) 1predicts
e aT
0) (T) changes by
(that
(0)
aT (T )

Risk Management and Financial Institutions 3e, Chapter 10, Copyright John C.
31Hull 2012