Abstract
This paper examines borrower’s mortgage loan termination behaviors (default and prepayment) by applying a nonparametric spatial model to a traditional loan hazard model. In this spatial hazard model, all of the parameters are allowed, but not forced, to vary across space. This means that borrowers in different locations are allowed to act differently with respect to changes in the termination incentives (e.g., changes in interest rates). Using a sample of 30-year fixed-rate subprime mortgage loans for home purchase, this study finds spatial variation in a borrower’s responsiveness to interest rate change and housing equity change in their decision to terminate a loan. The results further show that the nonparametric model offers improvements in the estimation of the loan termination probabilities.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
