Annals of Statistics

Testing for monotone increasing hazard rate

Peter Hall and Ingrid Van Keilegom

Full-text: Open access


A test of the null hypothesis that a hazard rate is monotone nondecreasing, versus the alternative that it is not, is proposed. Both the test statistic and the means of calibrating it are new. Unlike previous approaches, neither is based on the assumption that the null distribution is exponential. Instead, empirical information is used to effectively identify and eliminate from further consideration parts of the line where the hazard rate is clearly increasing; and to confine subsequent attention only to those parts that remain. This produces a test with greater apparent power, without the excessive conservatism of exponential-based tests. Our approach to calibration borrows from ideas used in certain tests for unimodality of a density, in that a bandwidth is increased until a distribution with the desired properties is obtained. However, the test statistic does not involve any smoothing, and is, in fact, based directly on an assessment of convexity of the distribution function, using the conventional empirical distribution. The test is shown to have optimal power properties in difficult cases, where it is called upon to detect a small departure, in the form of a bump, from monotonicity. More general theoretical properties of the test and its numerical performance are explored.

Article information

Ann. Statist., Volume 33, Number 3 (2005), 1109-1137.

First available in Project Euclid: 1 July 2005

Permanent link to this document

Digital Object Identifier

Mathematical Reviews number (MathSciNet)

Zentralblatt MATH identifier

Primary: 62G09: Resampling methods 62G10: Hypothesis testing 62G20: Asymptotic properties 62N03: Testing

Bandwidth bootstrap convex function cumulative hazard rate kernel methods local alternative monotone function power survival analysis


Hall, Peter; Van Keilegom, Ingrid. Testing for monotone increasing hazard rate. Ann. Statist. 33 (2005), no. 3, 1109--1137. doi:10.1214/009053605000000039.

Export citation


  • Ahmad, I. A. (1975). A nonparametric test for the monotonicity of a failure rate function. Comm. Statist. 4 967–974.
  • Anderson, N. H., Hall, P. and Titterington, D. M. (1994). Two-sample test statistics for measuring discrepancies between two multivariate probability density functions using kernel-based density estimates. J. Multivariate Anal. 50 41–54.
  • Barlow, R. E. and Doksum, K. A. (1972). Isotonic tests for convex orderings. Proc. Fifth Berkeley Symp. Math. Statist. Probab. 1 293–323. Univ. California Press, Berkeley.
  • Bickel, P. J. (1969). Tests for monotone failure rate. II. Ann. Math. Statist. 40 1250–1260.
  • Bickel, P. J. and Doksum, K. A. (1969). Tests for monotone failure rate based on normalized spacings. Ann. Math. Statist. 40 1216–1235.
  • Bowman, A. W., Jones, M. C. and Gijbels, I. (1998). Testing monotonicity of regression. J. Comput. Graph. Statist. 7 489–500.
  • Cheng, M.-Y. and Hall, P. (1999). Mode testing in difficult cases. Ann. Statist. 27 1294–1315.
  • Cheng, M.-Y. and Hall, P. (2001). Methods for tracking support boundaries with corners. Unpublished manuscript.
  • Chung, K. L. (1974). A Course in Probability Theory, 2nd ed. Academic Press, New York.
  • Delecroix, M., Hall, P. and Roget, C. (2001). Powerful tests for single index models. Unpublished manuscript.
  • Gail, M. H. and Gastwirth, J. L. (1978). A scale-free goodness-of-fit test for the exponential distribution based on the Gini statistic. J. Roy. Statist. Soc. Ser. B 40 350–357.
  • Gail, M. H. and Gastwirth, J. L. (1978). A scale-free goodness-of-fit test for the exponential distribution based on the Lorenz curve. J. Amer. Statist. Assoc. 73 787–793.
  • Gijbels, I. and Heckman, N. (2004). Nonparametric testing for a monotone hazard function via normalized spacings. J. Nonparametr. Statist. 16 463–478.
  • Hall, P., Huang, L.-S., Gifford, J. A. and Gijbels, I. (2001). Nonparametric estimation of hazard rate under the constraint of monotonicity. J. Comput. Graph. Statist. 10 592–614.
  • Hartigan, J. A. and Hartigan, P. M. (1985). The dip test of unimodality. Ann. Statist. 13 70–84.
  • Klefsjö, B. (1983). Some tests against aging based on the total time on test transform. Comm. Statist. A–-Theory Methods 12 907–927.
  • Komlós, J., Major, P. and Tusnády, G. (1975). An approximation of partial sums of independent RV's, and the sample DF. I. Z. Wahrsch. Verw. Gebiete 32 111–131.
  • Lavergne, P. and Vuong, Q. (2000). Nonparametric significance testing. Econometric Theory 16 576–601.
  • Proschan, F. and Pyke, R. (1967). Tests for monotone failure rate. Proc. Fifth Berkeley Symp. Math. Statist. Probab. 3 293–312. Univ. California Press, Berkeley.
  • Silverman, B. W. (1981). Using kernel density estimates to investigate multimodality. J. Roy. Statist. Soc. Ser. B 43 97–99.