Bayesian Forecasting of Prepayment Rates for Individual Pools of Mortgages

31 Pages Posted: 20 Mar 2008 Last revised: 22 May 2012

Ivilina Popova

Texas State University - San Marcos

Elmira Popova

University of Texas at Austin

Edward George

University of Pennsylvania - Statistics Department

Date Written: January 22, 2008

Abstract

This paper proposes a novel approach for modeling prepayment rates of individual pools of mortgages. The model incorporates the empirical evidence that prepayment is past dependent via Bayesian methodology. There are many factors that influence the prepayment behavior and for many of them there is no available (or impossible to gather) information. We implement this issue by creating a Bayesian mixture model and construct a Markov Chain Monte Carlo algorithm to estimate the parameters. We assess the model on a data set from the Bloomberg Database. Our results show that the burnout effect is a significant variable for explaining normal prepayment activities. This result does not hold when prepayment is triggered by non-pool dependent events. We show how to use the new model to compute prices for Mortgage Backed Securities. Monte Carlo simulation is the traditional method for obtaining such prices and the proposed model can be easily incorporated within simulation pricing framework. Prices for standard Pass-Throughs are obtained using simulation.

Keywords: Mortgage Prepayment Rates, Mortgage Backed Securities Pricing, Gibbs Sampling

JEL Classification: G0, G21, C5, C11, C15

Suggested Citation

Popova, Ivilina and Popova, Elmira and George, Edward, Bayesian Forecasting of Prepayment Rates for Individual Pools of Mortgages (January 22, 2008). Available at SSRN: https://ssrn.com/abstract=900011 or http://dx.doi.org/10.2139/ssrn.900011

Ivilina Popova (Contact Author)

Texas State University - San Marcos ( email )

601 University Drive
San Marcos, TX 78666-4616
United States

HOME PAGE: http://www.business.txstate.edu/users/ip12/

Elmira Popova

University of Texas at Austin ( email )

Austin, TX 78712
United States

Edward George

University of Pennsylvania - Statistics Department ( email )

Wharton School
Philadelphia, PA 19104
United States

Paper statistics

Downloads
306
Rank
79,482
Abstract Views
1,973