{[ promptMessage ]}

Bookmark it

{[ promptMessage ]}

KIC000065 - Dinan""-to-Default Model Model Default...

Info iconThis preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon
Calibration to an Actual Probability of Default Assume your model outputs a number- this number may be a probabtlltv, butthe probability depends on the distribution assumed in your model It is the case that the observed distributions for models do not match the actual distributions inmodels, so a calibration is needed. _ Need to map the output of the model to an actual probabilitv based on hf,;loric,,1 dat" Vou can use all kinds of ways to map the model output to an actual probability, but a simple way is a binned mapping where you interpolate or smooth between the bins. Moody's KMV uses an empirical mapping of distance- to- default to a probability lEDF = Expected Default Frequency) Example Mapping i-year PD
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
Background image of page 2
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: Dinan""-to-Default Model Model Default Probabilitv Output Output sa 0.03% ro 0.01% au 0.05% 0.015% zu 0.15% 0.075% sn 0.590 0.35% su 1.0% 0.8% ~ ,."" 1.5% au '.0% '.0% zu 10.Cl% ".0% W 15.tl% 3;.0% 40.ll'II. ;0.0% Reduced Form Models Reduced form models use market prices of debt or spreads to calculate the probability of default. Key differences between structural models:-Default occurs exogenously and not based on a default boundary-Probabilities are risk-neutral You can assume different forms for the probability of default over time.-Constant-A function of time with no random component-Random features with estimated parameters 7...
View Full Document

{[ snackBarMessage ]}