×

Dynamic survival models with varying coefficients for credit risks. (English) Zbl 1431.91410

Summary: Single event survival models predict the probability that an event will occur in the next period of time, given that the event has not happened before. In the context of credit risk, where one may wish to predict the probability of default on a loan account, such models have advantages over cross sectional models. The literature shows that the parameters of such models changed after compared with before the financial crisis of 2008. But there is also the possibility that the sensitivity of the probability of default, to say behavioural variables, changes over the life of an account. In this paper, we make two contributions. First, we parameterise discrete time survival models of credit card default using B-splines to represent the baseline relationship. These allow a far more flexible specification of the baseline hazard than has been adopted in the literature to date. This baseline relationship is crucial in discrete time survival models and typically has to be specified ex-ante. Second, we allow the estimates of the parameters of the hazard function to themselves be a function of duration time. This allows the relationship between covariates and the hazard to change over time. Using a large sample of credit card accounts we find that these specifications enhance the predictive accuracy of hazard models over specifications which adopt the type of baseline specification in the current literature and which assume constant parameters.

MSC:

91G40 Credit risk
62J12 Generalized linear models (logistic models)
62P05 Applications of statistics to actuarial sciences and financial mathematics

Software:

gamair; mgcv; R; SAS; SemiPar
PDFBibTeX XMLCite
Full Text: DOI Link

References:

[1] Allison, P. D., Survival analysis using SAS: A practical guide (2010), Cary, NC: SAS Institute Inc
[2] Altman, D. G.; Stavola, B. L.D.; Love, S. B.; Stepniewska, K. A., Review of survival analyses published in cancer journals, British Journal of Cancer, 72, 511-518 (1995)
[3] Andreeva, G., European generic scoring models using survival analysis, The Journal of Operational Research Society, 57, 1180-1187 (2006) · Zbl 1121.90072
[4] Banasik, J.; Crook, J. N.; Thomas, L. C., Not if but when will borrowers default, The Journal of Operational Research Society, 50, 1185-1190 (1999) · Zbl 1054.90531
[5] Bellotti, T.; Crook, J., Credit scoring with macroeconomic variables using survival models, The Journal of Operational Research Society, 60, 1699-1707 (2009) · Zbl 1196.91064
[6] Bellotti, T.; Crook, J., Forecasting and stress testing credit card default using dynamic models, International Journal of Forecasting, 29, 563-574 (2013)
[7] Bellotti, T.; Crook, J., Retail credit stress using discrete hazard models with macroeconomic factors, The Journal of Operational Research Society, 65, 340-350 (2014)
[8] Brown, E. R.; Ibrahim, J. G.; DeGruttola, V., A flexible b-spline model for multiple longitudinal biomarkers and survival, Biometrics, 61, 64-73 (2005) · Zbl 1077.62102
[9] Cameron, A. C.; Trivedi, P. K., Microeconometrics (2005), Oxford University Press
[10] Ciochetti, D.; Deng, Y.; Gao, B., The termination of commercial mortgage contracts through pre-payment and default: a proportional hazards approach with competing risks, Real Estate Economics, 30, 4, 595-633 (2002)
[11] Collett, D., Modelling survival data in medical research (1993), Chapman and Hall
[12] Cox, D. R., Regression models and life-tables (with discussion), Journal of Royal Statistic Society, Series B, 74, 187-220 (1972) · Zbl 0243.62041
[13] Crook, J.; Bellotti, T., Time varying and dynamic models for default risk in consumer loans, Journal of the Royal Statistical Society Series A (Statistics in Society), 173, 283-305 (2010)
[14] De Boor, C., A practical guide to splines (1978), Springer · Zbl 0406.41003
[15] Djeundje, V. A.B., Hierarchical and multidimensional smoothing with applications to longitudinal and mortality data (2011), Heriot-Watt University: Heriot-Watt University United Kingdom
[16] Djeundje, V. A.B., Systematic deviation in smooth mixed models for multi-level longitudinal data, Statistical Methodology, 32, 203-217 (2016) · Zbl 1487.62021
[17] Djeundje, V. A.B.; Crook, J., Accounting for heterogeneity and macroeconomic condition when estimating transition probabilities in a portfolio of credit card loans, European Journal of Operational Research, 271, 697-709 (2018)
[18] Efron, B., The efficiency of Cox’s likelihood function for censored data, Journal of the American Statistical Association, 76, 312-319 (1977)
[19] Eilers, P. H.C.; Marx, B. D., Flexible smoothing with B-splines and penalties, Statistical Science, 11, 89-121 (1996) · Zbl 0955.62562
[20] Eilers, P. H.C.; Marx, B. D., Generalized linear additive smooth structures, Journal of Computational and Graphical Statistics, 11, 758-783 (2002)
[21] Fan, J.; Zhang, W., Statistics and its interface, Statistics and its Interface, 1, 179-195 (2008)
[22] Ferguson, C. A.; Bowman, A. W.; Scott, E. M., Model comparison for a complex ecological system, Journal of Royal Statistical Society - A, 170, 691-711 (2007)
[23] Friedman, J. H.; Silverman, B. W., Flexible parsimonious smoothing and additive modelling, Technometrics, 31, 3-21 (1989) · Zbl 0672.65119
[24] Green, P. J.; Silverman, B. W., Nonparametric regression and generalized linear models (1995), Chapman and Hall
[25] Hastie, T.; Tibshirani, R., Varying-coefficient models, Statistical Methodology - B, 55, 757-796 (1993) · Zbl 0796.62060
[26] Hastie, T. J.; Tibshirani, R. J., Generalized additive models (1990), Chapman & Hall/CRC · Zbl 0747.62061
[27] Hougaard, P., Analysis of multivariate survival data (2012), Springer
[28] Hwang, R. C., A varying-coefficient default model, International Journal of Forecasting, 28, 675-688 (2012)
[29] Kauermann, G.; Tutz, G.; Brüderl, J., The survival of newly founded firms: a case-study into varying-coefficient models, Journal of Royal Statistical Society - A, 168, 145-158 (2005) · Zbl 1100.62102
[30] Leow, M.; Crook, J., Intensity models and transition probabilities for credit card loan, European Journal of Operational Research, 236, 685-694 (2014)
[31] Leow, M.; Crook, J., The stability of survival model parameter estimates for predicting the probability of default: Empirical evidence over the credit crisis, European Journal of Operational Research, 249, 457-464 (2015) · Zbl 1346.62107
[32] Leow, M., Mues, C., & Thomas, L. (2011). Competing risk survival model for mortgage loans with simulated distributions. In: Proceedings of the Credit Scoring and Credit Control III, Edinburgh.; Leow, M., Mues, C., & Thomas, L. (2011). Competing risk survival model for mortgage loans with simulated distributions. In: Proceedings of the Credit Scoring and Credit Control III, Edinburgh.
[33] Luo, S.; Kong, X.; Nie, T., Spline based survival model for credit risk modelling, European Journal of Operational Research, 253, 869-879 (2016) · Zbl 1346.91252
[34] Park, B. U.; Mammen, M.; Lee, Y. K.; Lee, E. R., Varying coefficient regression models: A review and new developments, International Statistical Review, 83, 36-64 (2015)
[35] Rue, H.; Martino, S.; Chopin, N., Approximate Bayesian inference for latent gaussian models using integrated nested laplace approximations (with discussion), Journal of the Royal Statistical Society, Series B, 71, 319-392 (2009) · Zbl 1248.62156
[36] Ruppert, D.; Carroll, R. J.; Wand, M. P., Semiparametric regression (2003), Cambridge University Press. · Zbl 1038.62042
[37] Stepanova, M.; Thomas, L. C., PHAB scores: Proportional hazards analysis behavioural scores, The Journal of the Operational Research Society, 52, 1007-1016 (2001) · Zbl 1181.91328
[38] Stepanova, M.; Thomas, L. C., Survival analysis for personal loan data, The Journal of the Operational Research Society, 50, 277-289 (2002) · Zbl 1163.91521
[39] Wood, S. N., Generalized additive models: An introduction with R (2006), Chapman & Hall/CRC · Zbl 1087.62082
[40] Wood, S. N. (2016). https://cran.r-project.org/web/packages/mgcv/mgcv.pdf; Wood, S. N. (2016). https://cran.r-project.org/web/packages/mgcv/mgcv.pdf
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.