Institute of Mathematical Statistics Collections

Smooth and non-smooth estimates of a monotone hazard

Piet Groeneboom and Geurt Jongbloed

Full-text: Open access


We discuss a number of estimates of the hazard under the assumption that the hazard is monotone on an interval $[0,a]$. The usual isotonic least squares estimators of the hazard are inconsistent at the boundary points $0$ and $a$. We use penalization to obtain uniformly consistent estimators. Moreover, we determine the optimal penalization constants, extending related work in this direction by [ Statist. Sinica 3 (1993) 501–515; Ann. Statist. 27 (1999) 338–360]. Two methods of obtaining smooth monotone estimates based on a non-smooth monotone estimator are discussed. One is based on kernel smoothing, the other on penalization.

Chapter information

Banerjee, M., Bunea, F., Huang, J., Koltchinskii, V., and Maathuis, M. H., eds., From Probability to Statistics and Back: High-Dimensional Models and Processes -- A Festschrift in Honor of Jon A. Wellner, (Beachwood, Ohio, USA: Institute of Mathematical Statistics, 2013) , 174-196

First available in Project Euclid: 8 March 2013

Permanent link to this document

Digital Object Identifier

Primary: 62G05: Estimation 62G05: Estimation
Secondary: 62E20: Asymptotic distribution theory

failure rate isotonic regression asymptotics penalized estimators smoothing spiking behavior

Copyright © 2010, Institute of Mathematical Statistics


Groeneboom, Piet; Jongbloed, Geurt. Smooth and non-smooth estimates of a monotone hazard. From Probability to Statistics and Back: High-Dimensional Models and Processes -- A Festschrift in Honor of Jon A. Wellner, 174--196, Institute of Mathematical Statistics, Beachwood, Ohio, USA, 2013. doi:10.1214/12-IMSCOLL913.

Export citation


  • [1] Chernoff, H. (1964). Estimation of the Mode. Ann. Inst. Statist. Math. 16 31–41.
  • [2] Durot, C. (2008). Testing convexity or concavity of a cumulated hazard rate. IEEE Trans. Rel. 57 465–473.
  • [3] van Es, A. J., Jongbloed, G. and van Zuijlen, M. C. A. (1998). Isotonic inverse estimators for nonparametric deconvolution. Ann. Statist. 26 2395–2406.
  • [4] Groeneboom, P. (1983). The concave majorant of Brownian motion. Ann. Probab. 11 1016–1027.
  • [5] Groeneboom, P. (1989). Brownian motion with a parabolic drift and Airy functions. Probab. Theory Related Fields 81 79–109.
  • [6] Groeneboom, P. and Jongbloed, G. (1995). Isotonic estimation and rates of convergence in Wicksell’s problem. Ann. Statist. 23 1518–1542.
  • [7] Groeneboom, P. and Jongbloed, G. (2003). Density estimation in the uniform deconvolution model. Stat. Neerl. 57 136–157.
  • [8] Groeneboom, P. and Jongbloed, G. (2010). Generalized continuous isotonic regression. Statist. Probab. Lett. 80 248–253.
  • [9] Groeneboom, P. and Jongbloed, G. (2012). Testing monotonicity of a hazard: asymptotic distribution theory. Bernoulli. To appear.
  • [10] Groeneboom, P. and Jongbloed, G. (2012). Isotonic $L_2$-projection test for local monotonicity of a hazard. J. Statist. Plann. Inference 142 1644–1658.
  • [11] Groeneboom, P. and Wellner, J. A. (2001). Computing Chernoff’s distribution. J. Comput. Graph. Statist. 10 388–400.
  • [12] Gijbels, I. and Heckman, N. (2004). Nonparametric testing for a monotone hazard function via normalized spacings. J. Nonparametr. Stat. 16 463–478.
  • [13] Hall, P. and Keilegom, I. van (2005). Testing for monotone increasing hazard rate. Ann. Statist. 33 1109–1137.
  • [14] Kiefer, J. and Wolfowitz, J. (1976). Asymptotically minimax estimation of concave and convex distribution functions. Zeitschrift für Wahrscheinlichkeitstheorie und verwandte Gebiete 32 111–131.
  • [15] Kim, J. and Pollard, D. (1990). Cube root asymptotics. Ann. Statist. 18 191–219.
  • [16] Neumeyer, N. (2007). A note on uniform consistency of monotone function estimators. Statist. Probab. Lett. 77 693–703.
  • [17] Pal, J. K. (2008). Spiking problem in monotone regression: Penalized residual sum of squares. Statist. Probab. Lett. 78 1548–1556.
  • [18] Pal, J. K. (2009). End-point estimation for decreasing densities: asymptotic behaviour of the penalized likelihood ratio. Scand. J. Stat. 36 764–781.
  • [19] Pal, J. K. and Woodroofe, M. (2006). On the distance between cumulative sum diagram and its greatest convex minorant for unequally spaced design points. Scand. J. Stat. 33 279–291.
  • [20] Pal, J. K. and Woodroofe, M. (2007). Large sample properties of shape restricted regression estimators with smoothness adjustments. Statist. Sinica 17 1601–1616.
  • [21] Prakasa Rao, B. L. S. (1970). Estimation for distributions with monotone failure rate. The Annals of Mathematical Statistics 41 507–519.
  • [22] Proschan, F. and Pyke, R. (1967). Tests for monotone failure rate. Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability 3 293–312.
  • [23] Rice, J. and Rosenblatt, M. (1976). Estimation of the log survivor function and hazard function. Sankhya A 38 60–78.
  • [24] Robertson, T., Wright, F. and Dykstra, R. (1972). Order Restricted Statistical Inference. John Wiley & Sons, New York.
  • [25] Singpurwalla, N. D. and Wong, M. Y. (1983). Estimation of the failure rate—A survey of nonparametric methods, Part 1: Non-Bayesian methods. Comm. Statist. Theory Methods 12 559–588.
  • [26] Tantiyaswasdikul, C. and Woodroofe, M. B. (1994). Isotonic smoothing splines under sequential designs. J. Statist. Plann. Inference 38 75–88.
  • [27] Woodroofe, M. and Sun, J. (1993). A penalized likelihood estimate of $f(0+)$ when $f$ is nonincreasing. Statist. Sinica 3 501–515.
  • [28] Woodroofe, M. and Sun, J. (1999). Testing uniformity versus a monotone density. Ann. Statist. 27 338–360.