Académique Documents
Professionnel Documents
Culture Documents
Dirk Tasche
Lloyds TSB Bank
Corporate Markets Rating Systems
dirk.tasche@gmx.net
Theopinions expressed in this presentation are those of the author and do not
necessarily reflect views of Lloyds TSB Bank.
i
Outline
ii
What is special about the Vasicek distribution? (1)
1
What is special about the Vasicek distribution? (2)
Examples of densities
3.0
Mean 0.25 , Stddev 0.137
2.5
2.0
Density value
Vasicek
Beta
1.5 Kumaraswamy
1.0
0.5
0.0
0% 25% 50% 75% 100%
Loss percentage
2
What is special about the Vasicek distribution? (3)
Examples of densities
4
Density value
3 Vasicek
Beta
Kumaraswamy
2
0
0% 25% 50% 75% 100%
Loss percentage
3
What is special about the Vasicek distribution? (4)
Observations:
When fitted to the same mean and standard deviation, the Va-
sicek, beta, and Kumaraswamy densities do not differ much.
4
What is special about the Vasicek distribution? (5)
5
What is special about the Vasicek distribution? (6)
6
What is special about the Vasicek distribution? (7)
7
Properties of the Vasicek distribution (1)
Consequences:
1
1%
(x)t
Distribution function: Fp,%(x) = P[X x] = %
8
Properties of the Vasicek distribution (2)
Moments
9
Properties of the Vasicek distribution (3)
Special cases:
E[X] = P[Y t] = p
(10.1)
var[X] = E[X 2] E[X]2 = P[Y1 t, Y2 t] p2
m
1
% is unique solution of 2(t, t; %) = m
P
x2
i
i=1
10
Properties of the Vasicek distribution (4)
Estimate and by
m m
1 X 1
1(xi), 2 = 1(xi)2 2
X
= (11.2)
m i=1 m i=1
11
Properties of the Vasicek distribution (5)
Quantile-based estimators
12
Properties of the Vasicek distribution (6)
13
Properties of the Vasicek distribution (7)
Sample size 5 10
Est. p SD SE Est. p SD SE
DMM 0.1017 0.0455 0.0455 0.1000 0.0312 0.0312
MLE 0.1009 0.0446 0.0446 0.0996 0.0308 0.0308
QBE 0.1220 0.0603 0.0642 0.1012 0.0399 0.0399
14
Properties of the Vasicek distribution (8)
Sample size 5 10
Est. % SD SE Est. % SD SE
DMM 0.2091 0.1306 0.1368 0.2242 0.1004 0.1036
MLE 0.1972 0.1071 0.1194 0.2223 0.0785 0.0832
QBE 0.2964 0.2025 0.2076 0.2081 0.1469 0.1526
15
Properties of the Vasicek distribution (9)
Comments on the simulation study
Estimation of p:
Estimation of %:
16
Modelling default rates (1)
17
Modelling default rates (2)
Binomial approach
n independent borrowers
1, if Di occurs
Default indicator: 1Di =
0, otherwise
n
1 X
Default rate: DR = 1D
n i=1 i
18
Modelling default rates (3)
k
h
k
i
n P D
X (n P D)`
Poisson approximation: P DR n e
`=0
`!
19
Modelling default rates (4)
20
Modelling default rates (5)
General observations on the binomial approach
1 P D (1 P D)
E[DR] = P D, var[DR] = n
21
Modelling default rates (6)
Vasicek approach: correlated binomial distribution
22
Modelling default rates (7)
Observations on the Vasicek approach
1 P D P D 2 + n1 (t, t; %)
E[DR] = P D, var[DR] = n n 2
Binomial
Corr Binomial
0.00
24
Modelling default rates (9)
Corr binomial
Vasicek
2
0
25
Modelling default rates (10)
Corr binomial
2
Vasicek
0
26
Modelling default rates (11)
Vasicek approach: Calculating the default rate distribution
Corr binomial
Vasicekfit
2
Vasicek
0
29
Related topics (not covered)
Multi-factor models.
...
30