Scenario Analysis and
Stress Testing
Chapter 22
Risk Management and Financial Institutions 4e, Chapter 22, Copyright John C. Hull 2015
Stress Testing
Key
Questions
How do we generate the scenarios?
How do we evaluate the scenarios?
What do we do with the results?
Risk Management and Financial Institutions 4e, Chapter 22, Copyright John C. Hull 2015
Generating the scenarios
Stress
individual variables
Choose particularly days when there were
big market movements and stress all
variables by the amount they moved on
those days
Form a stress testing committee of senior
management and ask it to generate the
scenarios
Risk Management and Financial Institutions 4e, Chapter 22, Copyright John C. Hull 2015
Core vs Peripheral Variables
If
scenario generated involves only a few
core variables, regress other peripheral
variables on the core variables to determine
their movements. (Kupiec, 1999)
Ideally the relationship between peripheral
and core variables should be estimated for
stressed market conditions (Kim and
Finger, 2000)
Risk Management and Financial Institutions 4e, Chapter 22, Copyright John C. Hull 2015
Making Scenarios Complete
Often
an adverse scenario has an
immediate effect on the value of a portfolio
and a knock on effect
Examples
Credit crisis of 2007
LTCM
Risk Management and Financial Institutions 4e, Chapter 22, Copyright John C. Hull 2015
Reverse Stress Testing
Use
an algorithm to search for scenarios
where large losses occur
Can be a useful input to the stress testing
committee.
Risk Management and Financial Institutions 4e, Chapter 22, Copyright John C. Hull 2015
What are the Incentives of a
Financial Institution?
If
the stress testing committee comes
up with extreme scenarios more
regulatory capital is likely to be required
The stress testing committee may
therefore has an incentive to water
down the scenarios they consider
Risk Management and Financial Institutions 4e, Chapter 22, Copyright John C. Hull 2015
Scenarios Chosen by Regulators
A part of US, UK, and EU regulation
CCAR for largest US banks considers recession
scenarios similar to 1973-75, 1981-81, and 2007-2009
and banks must submit capital management plan
DFAST for medium sized banks involves similar
scenarios but no capital management plans are
required
If banks fail the tests they have to raise more capital
Regulators have to make sure banks do not game the
system (See Business Snapshot 22.2)
Risk Management and Financial Institutions 4e, Chapter 22, Copyright John C. Hull 2015
What to do with the Results?
Should
managers place more reliance on
stress testing results or VaR results
One idea is to ask the stress testing
committee to assign probabilities to
scenarios (e.g. 0.05% or 0.2% or 0.5%)
The stress scenarios can then be
integrated with the historical simulation
scenarios to produce a composite VaR
Risk Management and Financial Institutions 4e, Chapter 22, Copyright John C. Hull 2015
Example from Chapter 13
Scenario
Loss ($000s)
Probability
Cumul. Probability
s5
850.000
0.00050
0.00050
s4
750.000
0.00050
0.00100
v494
477.814
0.00198
0.00298
s3
450.000
0.00200
0.00498
v339
345.435
0.00198
0.00696
s2
300.000
0.00200
0.00896
v349
282,204
0.00198
0.01094
v329
277.041
0.00198
0.01292
v487
253.385
0.00198
0.01490
s1
235.000
0.00500
0.01990
v227
217.974
0.00198
0.02188
v131
205.256
0.00198
0.02386
v238
201.389
0.00198
0.02584
Risk Management and Financial Institutions 4e, Chapter 22, Copyright John C. Hull 2015
10
Subjective vs Objective
Probabilities
Objective probabilities are calculated from data
Subjective probabilities is based on a individuals
judgment.
Objective probabilities are inevitably backward
looking
The procedure just described is a way of
combining subjective and objective probabilities.
Risk Management and Financial Institutions 4e, Chapter 22, Copyright John C. Hull 2015
11
