The authors investigate the borrower risk factors, delinquency rates, yield curves, and interest rates of long-term auto loans.
Estimating correlation parameters in credit portfolio models under time-varying and nonhomogeneous default probabilities
This paper proposes new maximum likelihood estimation methods that offer greater flexibility than current methods and can account for finite portfolio sizes, scarce default data and time varying, nonhomogeneous default probabilities.
This paper decomposes credit default swap spreads of euro area members into their risk premium and default risk elements and forecast one year probabilities of default.
The authors compare JLSMC DIM estimates with those produced by two other methods, finding that the JLSMC algorithm is accurate and efficient, producing results comparable with nested Monte Carlo with an order of magnitude less computational effort.