Improving Parametric Mortgage Prepayment Models with Non-parametric Kernel Regression

Michael LaCour-Little (), Michael Marschoun () and Clark L. Maxam ()
Additional contact information
Michael LaCour-Little: Washington University in St. Louis and Wells Fargo Home Mortgage in Clayton, MO 63105
Michael Marschoun: PMI Mortgage Insurance Co., San Francisco, CA 94111
Clark L. Maxam: Montana State University, Bozeman, MT 59717

Journal of Real Estate Research, 2002, vol. 24, issue 3, pages 299-328

Abstract: Developing a good prepayment model is a central task in the valuation of mortgages and mortgage-backed securities but conventional parametric models often have bad out-of-sample predictive ability. A likely explanation is the highly non-linear nature of the prepayment function. Non-parametric techniques are much better at detecting non-linearity and multivariate interaction. This article discusses how non-parametric kernel regression may be applied to loan level event histories to produce a better parametric model. By utilizing a parsimonious specification, a model can be produced that practitioners can use in valuation routines based on Monte Carlo interest rate simulation.

JEL-codes: L85 (search for similar items in EconPapers)
Date: 2002
View list of references

Downloads: (external link)
http://aux.zicklin.baruch.cuny.edu/jrer/papers/pdf/past/vol24n03/05.299_328.pdf Full text (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: http://EconPapers.repec.org/RePEc:jre:issued:v:24:n:3:2002:p:299-328

Ordering information: This journal article can be ordered from
Diane Quarles American Real Estate Society Manager of Member Services Clemson University Box 341323 Clemson, SC 29634-1323
http://aux.zicklin.b ... u/jrer/about/get.htm

Access Statistics for this article

Journal of Real Estate Research is edited by Dr. Ko Wang

More articles in Journal of Real Estate Research from American Real Estate Society
Address: American Real Estate Society Clemson University School of Business & Behavioral Science Department of Finance 401 Sirrine Hall Clemson, SC 29634-1323
Series data maintained by JRER Graduate Assistant/Webmaster ().