Estimating Loss Given Default from CDS Under Weak Identification

49 Pages Posted: 7 Sep 2017

See all articles by Lily Y. Liu

Lily Y. Liu

Duke University; Federal Reserve Banks - Federal Reserve Bank of Boston

Date Written: 2017-05-08

Abstract

This paper combines a term structure model of credit default swaps (CDS) with weak-identification robust methods to jointly estimate the probability of default and the loss given default of the underlying firm. The model is not globally identified because it forgoes parametric time series restrictions that have aided identification in previous studies, but that are also difficult to verify in the data. The empirical results show that informative (small) confidence sets for loss given default are estimated for half of the firm-months in the sample, and most of these are much lower than and do not include the conventional value of 0.60. This also implies that risk-neutral default probabilities, and hence risk premia on default probabilities, are underestimated when loss given default is exogenously fixed at the conventional value instead of estimated from the data.

JEL Classification: C13, C14, C58, G12, G13

Suggested Citation

Liu, Lily Y., Estimating Loss Given Default from CDS Under Weak Identification (2017-05-08). FRB Boston Risk and Policy Analysis Unit Paper No. RPA 17-1. Available at SSRN: https://ssrn.com/abstract=3033354

Lily Y. Liu (Contact Author)

Duke University ( email )

100 Fuqua Drive
Durham, NC 27708-0204
United States

Federal Reserve Banks - Federal Reserve Bank of Boston ( email )

600 Atlantic Avenue
Boston, MA 02210
United States

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
32
Abstract Views
238
PlumX Metrics