Abstract
In this article we propose an automatic selection of the bandwidth of the semirecursive kernel estimators of the hazard function for uncensored observations. We show that, using the selected bandwidth and a special stepsize, the proposed semirecursive estimators will be quite a bit better than the nonrecursive one in terms of estimation error and much better in terms of computational costs. We corroborated these theoretical results through simulation study and a real earthquake dataset.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Ahmad, I. A. 1976. Uniform strong convergence of the generalized failure rate estimated. Bulletin of Mathematical Statistics 17:77–84.
Altman, N., and C. Leger. 1995. Bandwidth selection for kernel distribution function estimation. Journal of Statistical Planning and Inference 46:195–214.
Bagkavos, D., and P. N. Patil. 2008. Local polynomial fitting in failure rate estimation. IEEE Transactions on Reliability 56:126–63.
Bagkavos, D. 2011. Local linear hazard rate estimation and bandwidth selection. Annals of the Institute of Statistical Mathematics 63:1019–46.
Bojanic, R., and E. Seneta. 1973. A unified theory of regularly varying sequences. Mathematische Zeitschrift 134:91–106.
Cheng, M. Y. 1997. Boundary aware estimators of integrated density derivative products. Journal of the Royal Statistical Society: Series B (Statistical Methodology) 59:191–203.
Delaigle, A., and I. Gijbels. 2004. Practical bandwidth selection in deconvolution kernel density estimation. Computational Statistics Data Analysis 45:249–67.
Galambos, J., and E. Seneta. 1973. Regularly varying sequences. Proceedings of the American Mathematical Society 41:110–16.
Mokkadem, A., and M. Pelletier. 2007. A companion for the Kiefer–Wolfowitz–Blum stochastic approximation algorithm. Annals Statistics 35:1749–72.
Mokkadem, A., M. Pelletier, and Y. Slaoui. 2009. The stochastic approximation method for the estimation of a multivariate probability density. Journal of Statistical Planning and Inference 139:2459–78.
Mïler, H. G., and J. L. Wang. 1994. Hazard rate estimation under random censoring with varying kernels and bandwidths. Biometrics 50:61–76.
Murthy, V. K. 1965. Estimation of jumps, reliability and hazard rate. Annals of Statistics 36:1032–40.
Quintela-del-Rio, A., and G. Estévez-Pérez. 2012. Nonparametric kernel distribution function estimation with kerdist: An R package for bandwidth choice and applications. Journal of Statistical Software 50:1–21.
Rebora, P., A. Salim, and M. Reilly. 2014. bshazard: A flexible tool for nonparametric smoothing of the hazard function. R Journal 6:114–1221.
Silverman, B. W. 1986. Density estimation for statistics and data analysis. London, UK: Chapman and Hall.
Slaoui, Y. 2013. Large and moderate principles for recursive kernel density estimators defined by stochastic approximation method. Serdica Mathematical Journal 39:53–82.
Slaoui, Y. 2014a. Bandwidth selection for recursive kernel density estimators defined by stochastic approximation method. Journal of Probability and Statistics 2014:739640. doi:10.1155/2014/739640.
Slaoui, Y. 2014b. The stochastic approximation method for the estimation of a distribution function. Mathematical Methods of Statistics 23:306–25.
Slaoui, Y. 2015. Plug-in bandwidth selector for recursive kernel regression estimators defined by stochastic approximation method. Statistica Neerlandica 69:483–509.
Slaoui, Y. 2016. Optimal bandwidth selection for semi-recursive kernel regression estimators. Statistics and its Interface 9:375–88.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Slaoui, Y. On the choice of smoothing parameters for semirecursive nonparametric hazard estimators. J Stat Theory Pract 10, 656–672 (2016). https://doi.org/10.1080/15598608.2016.1214853
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1080/15598608.2016.1214853