Abstract
This paper introduces a multivariate density estimator for truncated and censored data with special emphasis on extreme values based on survival analysis. A local constant density estimator is considered. We extend this estimator by means of tail flattening transformation, dimension reducing prior knowledge and a combination of both. The asymptotic theory is derived for the proposed estimators. It shows that the extensions might improve the performance of the density estimator when the transformation and the prior knowledge is not too far away from the true distribution. A simulation study shows that the density estimator based on tail flattening transformation and prior knowledge substantially outperforms the one without prior knowledge, and therefore confirms the asymptotic results. The proposed estimators are illustrated and compared in a data study of fire insurance claims.
Similar content being viewed by others
References
Andersen, P. K., Borgan, Ø., Gill, R. D., Keiding, N. (1993). Statistical models based on counting processes. Springer Series in Statistics. New York: Springer-Verlag.
Bagkavos D. (2008) Transformations in hazard rate estimation. Journal of Nonparametric Statistics 20(8): 721–738
Bagkavos, D. (2009). Local linear hazard rate estimation and bandwidth selection. The Annals of the Institute of Statistical Mathematics (in press).
Bagkavos D., Patil P.N. (2008) Local polynomial fitting in failure rate estimation. IEEE Transactions on Reliability 56: 126–163
Beran, R. (1981). Nonparametric regression with randomly censored survival data. Unpublished technical report, Berkeley: University of California.
Bolancé C., Guillén M., Nielsen J.P. (2003) Kernel density estimation of actuarial loss functions. Insurance: Mathematics and Economics 32: 19–36
Bolancé C., Guillén M., Nielsen J.P. (2008) Inverse beta transformation in kernel density estimation. Statistics and Probability Letters 78: 1757–1764
Bouaziz O., Lopez O. (2010) Conditional density estimation in a censored single-index regression model. Bernoulli 16(2): 514–542
Buch-Kromann T. (2009) Comparison of tail performance of the champernowne transformed kernel density estimator, the generalized pareto distribution and the g-and-h distribution. The Journal of Operational Risk 4(2): 43–67
Buch-Kromann T., Englund M., Gustafsson J., Nielsen J.P., Thuring F. (2007) Non-parametric estimation of operational risk losses adjusted for under-reporting. Scandinavian Actuarial Journal 4: 293–304
Buch-Kromann, T., Guillén, M., Linton, O., Nielsen, J. P. (2009). Multivariate density estimation using dimension reducing information and tail flattening transformations. Under revision to Insurance: Mathematics and Economics.
Buch-Larsen T., Nielsen J.P., Guillén M., Bolancé C. (2005) Kernel density estimation for heavy-tailed distributions using the Champernowne transformation. Statistics 39(6): 503–518
Clements A., Hurn S., Lindsay K. (2003) Mobius-like mappings and their use in kernel density estimation. Journal of the American Statistical Association 98(464): 993–1000
Dabrowska D.M. (1987) Nonparametric regression with censored survival time data. Scandinavian Journal of Statistics Theory and Applications 14(3): 181–197
Embrechts, P., Klüppelberg, C., Mikosch, T. (1997). Modelling extremal events. Applications of Mathematics (New York) (Vol. 33). Berlin: Springer.
Guillen M., Gustafsson J., Nielsen J.P., Pritchard P. (2007) Using external data in operational risk capital. The Geneva papers 32: 178–189
Gustafsson J. (2006) Modelling operational risk with kernel density estimation using the champernowne transformation. The ICFAI Journal of Risk & Insurance 3(4): 39–75
Gustafsson J., Nielsen J.P. (2008) A mixing model for operational risk. The Journal of Operational Risk 3(3): 25–37
Gustafsson J., Nielsen J.P., Pritchard P., Roberts D. (2006a) Quantifying operational risk guided by kernel smoothing and continuous credibility. The ICFAI Journal of Financial Risk Management 3(2): 23–47
Gustafsson J., Nielsen J.P., Pritchard P., Roberts D. (2006b) Quantifying operational risk guided by kernel smoothing and continuous credibility: a practioner’s view. The Journal of operational risk 1(1): 43–55
Hastie, T. J., Tibshirani, R. J. (1990). Generalized additive models. Monographs on statistics and applied probability (Vol. 43). London: Chapman & Hall Ltd.
Heuchenne C., Van Keilegom I. (2007a) Location estimation in nonparametric regression with censored data. Journal of Multivariate Analysis 98: 1558–1582
Heuchenne C., Van Keilegom I. (2007b) Nonlinear regression with censored data. Technometrics 49: 34–44
Jacobsen, M. (1982). Statistical analysis of counting processes. Lecture notes in statistics (Vol. 12). New York: Springer.
Koekemoer G., Swanepoel J.W.H. (2008a) A semi-parametric method for transforming data to normality. Statistics and Computing 18(3): 241–257
Koekemoer G., Swanepoel J.W.H. (2008b) Transformation kernel density estimation with applications. Journal of Computational and Graphical Statistics 17(3): 750–769
Li G., Doss H. (1995) An approach to nonparametric regression for life history data using local linear fitting. The Annals of Statistics 23(3): 787–823
Linton O., Nielsen J.P. (1995) A kernel method of estimating structured nonparametric regression based on marginal integration. Biometrika 82(1): 93–100
Linton O., Nielsen J.P., van de Geer S. (2003) Estimating multiplicative and additive hazard functions by kernel methods. The Annals of Statistics 31(2): 464–492 dedicated to the memory of Herbert E. Robbins.
Linton, O., Mammen, E., Nielsen, J. P., Van Keilegom, I. (2010). Nonparametric regression with filtered data. Bernoulli (to appear).
Mammen E., Nielsen J.P. (2007) A general approach to predictability issue in survival analysis with applications. Biometrika 94(4): 873–892
Martinussen, T., Scheike, T. H. (2006). Dynamic regression models for survival data. Statistics for biology and health. New York: Springer.
McKeague I.W., Utikal K.J. (1990) Inference for a nonlinear counting process regression model. The Annals of Statistics 18(3): 1172–1187
Nielsen J.P. (1998) Marker dependent kernel hazard estimation from local linear estimation. Scandinavian Actuarial Journal 2: 113–124
Nielsen J.P., Linton O. (1995) Kernel estimation in a nonparametric marker dependent hazard model. The Annals of Statistics 23(5): 1735–1748
Nielsen J.P., Tanggaard C. (2001) Boundary and bias correction in kernel hazard estimation. Scandinavian Journal of Statistics Theory and Applications 28(4): 675–698
Nielsen J.P., Jones C., Tanggaard C. (2009) Local linear density estimation for filtered survival data. Statistics 2(43): 167–186
Silverman, B. W. (1986). Density estimation for statistics and data analysis. Monographs on statistics and applied probability. London: Chapman & Hall.
Stone C.J. (1980) Optimal rates of convergence for nonparametric estimators. The Annals of Statistics 8(6): 1348–1360
Van Keilegom I., Akritas M.G. (1999) Transfer of tail information in censored regression models. The Annals of Statistics 27(5): 1745–1784
Van Keilegom I., Veraverbeke N. (2001) Hazard rate estimation in nonparametric regression with censored data. Annals of the Institute of Statistical Mathematics 53(4): 730–745
Van Keilegom I., Veraverbeke N. (2002) Density and hazard estimation in censored regression models. Bernoulli 8(5): 607–625
Wand M.P., Marron J.S., Ruppert D. (1991) Transformations in density estimation. Journal of the American Statistical Association 86(414): 343–361 with discussion and a rejoinder by the authors.
Yang L., Marron J.S. (1999) Iterated transformation-kernel density estimation. Journal of the American Statistical Association 94(446): 580–589
Author information
Authors and Affiliations
Corresponding author
About this article
Cite this article
Buch-Kromann, T., Nielsen, J.P. Multivariate density estimation using dimension reducing information and tail flattening transformations for truncated or censored data. Ann Inst Stat Math 64, 167–192 (2012). https://doi.org/10.1007/s10463-010-0313-6
Received:
Revised:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10463-010-0313-6