Estimating Mortgage Prepayment Rates Using the Gibbs-Sampling Approach

Che-Chun Lin ； Yu-Lieh Huang ； Chiuling Lu

《Advances in Financial Planning and Forecasting》 5期 (2012/12) Pp. 215-230

https://doi.org/10.6292/AFPF.2012.05.09

並列摘要

The main purpose of this paper is to use the Gibbs-sampling model method as an alternative technique to estimate mortgage payment rates. We use this method due to the face that available data on mortgage loans in many emerging markets, like Taiwan, are somewhat limited. The empirical results confirm that one advantage of this approach is that the coefficient estimate of each parameter exhibits its own exact posterior distribution rather than a mere point estimate. More than that, this approach allows for finite-sample inferences within the model estimates. We conclude, therefore, that the realized distributional form can be inferred from the statistical results. This significantly enhances the measurement of mortgage prepayment probabilities, particularly when the data are scant.

並列關鍵字

Mortgage Prepayment ； Gibbs-Sampling

參考文獻

Albert, J. H.,Chib, S.(1993).Bayesian analysis of binary and polychotomous response data.Journal of the American Statistical Association.88,669-679.

Albert, J. H.,Chib, S.(1993).Bayes inference via Gibbs sampling of autoregressive time series subject to Markov mean and variance shifts.Journal of Business & Economic Statistics.11,1-15.

Amemiya, T.(1985).Advanced econometrics.Cambridge, MA:Harvard University Press.

Betancourt, L.(1999).Using Markov chains to estimate losses from a portfolio of mortgage.Review of Quantitative Finance and Accounting.12,303-318.

Buser, S. A.,Hendershott, P. H.(1984).Pricing default free mortgages.Housing Finance Review.3,405-429.