Credit Risk Modelling M.A. Fahrenwaldt Example sheet
1.Fort=0,…,T 1,j2S\{0}andk2S,letNtj denotethenumberof companies that are rated j at time t and followed until time t + 1 and let Ntjk denote the number of those companies that are rated k at time t + 1. A discrete-time, stationary Markov chain is fitted to the data (Ntj) and (Ntjk).
Show that the maximum likelihood estimator of the transition probability pjk is given by PT 1 Ntjk
t=0 pˆjk=PT 1N .
Copyright By PowCoder代写 加微信 powcoder
2. The matrix exponential of the Markov chain generator ⇤ 2 R(n+1)⇥(n+1) can be calculated using a number of software packages. One case where it can be calculated by simple matrix multiplication occurs when the generator is di- agonalizable, meaning that there exists an invertible matrix A 2 R(n+1)⇥(n+1) such that A 1⇤A = D where D = diag(d0, . . . , dn) is a diagonal matrix con- taining the eigenvalues of ⇤. Show that, in this case, the matrix of transition probabilities P (t) for the interval [0, t] may be written
P(t) = A diag ed0t,…,ednt A 1.
3. In Merton’s model the debt of a company consists of a single-zero coupon bond with face value B and maturity T. The asset value process (Vt)t 0 of a firm is modelled by the stochastic di↵erential equation
dVt =μVVtdt+ VVtdWt
where μV 2 R and V > 0 are the drift and asset volatility respectively. Default occurs if VT is less than B. Assuming V0 > B, show that the probability of default is an increasing function of the volatility V .
4. A bank uses a simple internal rating system in which there are only two ratings – A and B – as well as a default state D. You are given the information in the
following table. There are a few missing entries in the table.
first yeardefault so B 0.10 ? 0.20 Second yeardefault
Complete the table of transition probabilities and compute the probabilities that A-rated and B-rated obligors default over a two-year period.
5. Create graphs to show how the credit spread in Merton’s model varies with 二the relative debt lebel given by d = Bp0(t,T)/Vt. Experiment with di↵erent
values for the time to maturity of the debt T t and the asset volatility V .
6. This question will require the use of a computer package that contains the ma- trix exponential function. Estimate a generator matrix ⇤ for rating migrations by taking the average annual rating migration rates given in the table provided by Moody’s. Use ⇤ to derive the matrix of one-year transition probabilities P =P(1).
Now assume that the credit-migration model is embedded in a firm-value model. This is done by introducing an asset value process (Vt) for each firm
ABD A 0.80 0.15 ?
and thresholds
such that P(d ̃ < V d ̃ ) = p . As noted in the lectures, the migration
probabilities are invariant under simultaneous strictly increasing transforma-
tionsofV andthethresholdsd ̃. LetX =T(V )andd =T(d ̃)denotethe T kTTkk
transformed quantities. Find the values for the thresholds d0, . . . , dn+1 when XT ⇠N(0,1).
7. The Gompertz model is widely used by actuaries in mortality modelling. The distribution function is given by
F(t)=1 exp⇣ ab ebt 1 ⌘, a>0,b>0,t 0.
Caculate the hazard function and the cumulative hazard function of this dis-
tribution.
The Gompertz-Makeham model is an extension of the Gompertz model. If the hazard function of the Gompertz distribution is G(t) the Gompertz-Makeham distribution has hazard function GM(t) = G(t) + c for some constant c > 0. Calculate the distribution function of this model.
0=d ̃