The Annals of Statistics

Efficient estimation in the bivariate censoring model and repairing NPMLE

Mark J. van der Laan

Full-text: Open access


The NPMLE in the bivariate censoring model is not consistent for continuous data. The problem is caused by the singly censored observations. In this paper we prove that if we observe the censoring times or if the censoring times are discrete, then a NPMLE based on a slightly reduced data set, in particular, we interval censor the singly censored observations, is asymptotically efficient for this reduced data and moreover if we let the width of the interval converge to zero slowly enough, then the NPMLE is also asymptotically efficient for the original data. We are able to determine a lower bound for the rate at which the bandwidth should converge to zero. Simulation results show that the estimator for small bandwidths has a very goodperformance. The efficiency proof uses a general identity which holds for NPMLE of a linear parameter in convex models. If we neither observe the censoring times nor the censoring times are discrete, then we conjecture that our estimator based on simulated censoring times is also asymptotically efficient.

Article information

Ann. Statist., Volume 24, Number 2 (1996), 596-627.

First available in Project Euclid: 24 September 2002

Permanent link to this document

Digital Object Identifier

Mathematical Reviews number (MathSciNet)

Zentralblatt MATH identifier

Primary: 62G07: Density estimation
Secondary: 62F12: Asymptotic properties of estimators

Bivariate censorship self-consistency equations efficiency


van der Laan, Mark J. Efficient estimation in the bivariate censoring model and repairing NPMLE. Ann. Statist. 24 (1996), no. 2, 596--627. doi:10.1214/aos/1032894454.

Export citation


  • BAKKER, D. M. 1990. Two nonparametric estimators of the survival function of bivariate right censored observations. Report BS-R9035, Centrum Wisk. Inform., Amsterdam. Z.
  • BICKEL, P. J. and FREEDMAN, D. A. 1981. Some asy mptotic theory for the bootstrap. Ann. Statist. 9 1196 1217. Z.
  • BICKEL, P. J., KLAASSEN, A. J., RITOV, Y. and WELLNER, J. A. 1993. Efficient and Adaptive Estimation for Semi-Parametric Models. Johns Hopkins Univ. Press. Z.
  • BURKE, M. D. 1988. Estimation of a bivariate survival function under random censorship. Biometrika 75 379 382. Z.
  • DABROWSKA, D. M. 1988. Kaplan Meier estimate on the plane. Ann. Statist. 16 1475 1489. Z.
  • DABROWSKA, D. M. 1989. Kaplan Meier estimate on the plane: weak convergence, LIL, and the bootstrap. J. Multivariate Anal. 29 308 325. Z.
  • DEMPSTER, A. P., LAIRD, N. M. and RUBIN, D. B. 1977. Maximum likelihood from incomplete data via the EM-algorithm. J. Roy. Statist. Soc. Ser. B 39 1 38. Z.
  • EFRON, B. 1967. The two sample problem with censored data. Proc. Fifth Berkeley Sy mp. Math. Statist. Probab. 831 853. Univ. California Press, Berkeley. Z.
  • EINMAHL, J. H. H. 1987. Multivariate Empirical Processes. CWI Tract 32. Centrum Wisk. Inform., Amsterdam. Z.
  • GILL, R. D. 1989. Nonand semi-parametric maximum likelihood estimators and the von Mises Z. method Part 1. Scand. J. Statist. 16 97 128. Z.
  • GILL, R. D. 1992. Multivariate survival analysis. Theory Probab. Appl. 37 18 31 and 284 301. Z. English translation. Z.
  • GILL, R. D. 1994. Lectures on survival analysis. Ecole d'Ete de Probabilites de Saint Flour ´ ´ XXII. Lecture Notes in Math. 1581 115 241. Springer, Berlin. Z.
  • GILL, R. D., VAN DER LAAN, M. J. and WELLNER, J. A. 1993. Inefficient estimators of the bivariate survival function for three models. Ann. Inst. H. Poincare Probab. Statist.. ´ 31 547 597. Z.
  • HEITJAN, D. F. and RUBIN, D. B. 1991. Ignorability and coarse data. Ann. Statist. 19 2244 2253. Z. HOFFMANN-JøRGENSEN, J. 1984. Stochastic processes on Polish spaces. Unpublished manuscript. Z.
  • NEUHAUS, G. 1971. On weak convergence of stochastic processes with multidimensional time parameter. Ann. Math. Statist. 42 1285 1295. Z.
  • PARTHASARATHY, K. R. 1967. Probability Measures on Metric Spaces. Academic Press, New York. Z.
  • POLLARD, D. 1990. Empirical Processes: Theory and Applications. IMS, Hay ward, CA. Z.
  • PRENTICE, R. L. and CAI, J. 1992a. Covariance and survivor function estimation using censored multivariate failure time data. Biometrika 79 495 512. Z.
  • PRENTICE, R. L. and CAI, J. 1992b. Marginal and conditional models for the analysis of Z multivariate failure time data. In Survival Analy sis State of the Art Klein, J. P. and. Goel, P. K., eds.. Kluwer, Dordrecht. Z.
  • PRUITT, R. C. 1991a. On negative mass assigned by the bivariate Kaplan Meier estimator. Ann. Statist. 19 443 453. Z.
  • PRUITT, R. C. 1991b. Strong consistency of self-consistent estimators: general theory and an application to bivariate survival analysis. Technical Report 543, Univ. Minnesota. Z.
  • PRUITT, R. C. 1993. Small sample comparisons of six bivariate survival curve estimators. J. Statist. Comput. Simulation. 45 147 167. Z.
  • TSAI, W-Y., LEURGANS, S. and CROWLEY, J. 1986. Nonparametric estimation of a bivariate survival function in the presence of censoring. Ann. Statist. 14 1351 1365. Z.
  • TURNBULL, B. W. 1976. The empirical distribution with arbitrarily grouped censored and truncated data. J. Roy. Statist. Soc. Ser. B 38 290 295. Z.
  • VAN DER LAAN, M. J. 1990. Dabrowska's multivariate product limit estimator and the deltamethod. Master's dissertation, Dept. Mathematics, Univ. Utrecht, The Netherlands. Z.
  • VAN DER LAAN, M. J. 1993. General identity for linear parameters in convex models with Z. application to efficiency of the NP MLE. Preprint 765, Dept. Mathematics, Univ. Utrecht, The Netherlands.
  • VAN DER LAAN, M. J. 1994. Modified EM-estimator of the bivariate survival function. 3 213 243. Math. Methods Statist.. Z.
  • VAN DER LAAN, M. J. 1995. Efficiency of the NPMLE in a general class of missing data models. Unpublished manuscript. Z.
  • VAN DER LAAN, M. J. 1996. Efficient and inefficient estimation in semiparametric models. Technical Report, CWI, Amsterdam. Z.
  • VAN DER VAART, A. W. 1988. Statistical estimation in large parameter spaces. CWI Tract 44. Centrum Wisk. Inform. Amsterdam. Z.
  • VAN DER VAART, A. W. AND WELLNER, J. A. 1995. Weak Convergence and Empirical Processes.
  • IMS, Hay ward, CA.