Recovering default risk from CDS spreads with a nonlinear filter

Alexander Guarin, Xiaoquan Liu, Wing Lon Ng

Research output: Journal PublicationArticlepeer-review

8 Citations (Scopus)


We propose a nonlinear filter to estimate the time-varying default risk from the term structure of credit default swap (CDS) spreads. Based on the numerical solution of the Fokker-Planck equation (FPE) using a meshfree interpolation method, the filter performs a joint estimation of the risk-neutral default intensity and CIR model parameters. As the FPE can account for nonlinear functions and non-Gaussian errors, the proposed framework provides outstanding flexibility and accuracy. We test the nonlinear filter on simulated spreads and apply it to daily CDS data of the Dow Jones Industrial Average component companies from 2005 to 2010 with supportive results.

Original languageEnglish
Pages (from-to)87-104
Number of pages18
JournalJournal of Economic Dynamics and Control
Issue number1
Publication statusPublished - Jan 2014
Externally publishedYes


  • CDS spreads
  • CIR model
  • Fokker-Planck equation
  • Meshfree methods
  • Radial basis function interpolation

ASJC Scopus subject areas

  • Economics and Econometrics
  • Control and Optimization
  • Applied Mathematics


Dive into the research topics of 'Recovering default risk from CDS spreads with a nonlinear filter'. Together they form a unique fingerprint.

Cite this