The Annals of Statistics

Smooth goodness-of-fit tests for composite hypothesis in hazard based models

Edsel A. Peña

Full-text: Open access

Abstract

Consider a counting process $N(t), t\inT}$ with compensator process ${A(t),t\in T}$, where $A(t)=\int_0^t Y(s) ds, {Y(t), t\in T}$ is an observable predictable process, and $\lambda_0(\dot)$ is an unknown hazard rate function. A general procedure for extending Neyman’s smooth goodness­of­fit test for the composite null hypothesis $H_0: \lambda_0(\dot)\inC ={\lambda_0(\dot;\eta):\eta\in\Gamma\subseteq\Re^q}$ is proposed and developed. The extension is obtained by embedding $C$ in the class $A_ k$ whose members are of the form $\lambda_0(\dot;\eta)\exp{\theta^t\psi(\dot;\eta)}, (\eta,\theta) \in\Gamma\times\Re^k$, where $\psi(\dot;\eta)=(\psi_1(\dot;\eta,\ldots,\psi_k(\dot;\eta))^t$ is a vector of observable random processes satisfying certain regularity conditions. The tests are based on quadratic forms of the statistic $\int_0^\tau\psi(s;\hat{\eta})dM(s;\hat{\eta})$, where $M(t;\eta) = N(t) - \int_0^t Y(s)\lambda_0(s;\eta) ds$ and $\hat {\eta}$ is a restricted maximum likelihood estimator of $\eta$. Asymptotic properties of the test statistics are obtained under a sequence of local alternatives, and the asymptotic local powers of the tests are examined. The effect of estimating $\eta$ by $\hat{\eta}$ is ascertained, and the problem of choosing the $\lambda$­process is discussed. The procedure is illustrated by developing tests for testing that $\lambda_0(\dot)$ belongs to (i) the class of constant hazard rates and ii the class of Weibull hazard rates, with particular emphasis on the random censorship model. Simulation results concerning the achieved levels and powers of the tests are presented, and the procedures are applied to three data sets that have been considered in the literature.

Article information

Source
Ann. Statist., Volume 26, Number 5 (1998), 1935-1971.

Dates
First available in Project Euclid: 21 June 2002

Permanent link to this document
https://projecteuclid.org/euclid.aos/1024691364

Digital Object Identifier
doi:10.1214/aos/1024691364

Mathematical Reviews number (MathSciNet)
MR1673285

Zentralblatt MATH identifier
0934.62023

Subjects
Primary: 62F03 62N05: Reliability and life testing [See also 90B25]

Keywords
Censoring counting process generalized residual local asymptotic relative efficiency martingale central limit theorem multiplicative intensity model nuisance parameters and adaptiveness Neyman’s test score test test for exponentiality test for Weibull

Citation

Peña, Edsel A. Smooth goodness-of-fit tests for composite hypothesis in hazard based models. Ann. Statist. 26 (1998), no. 5, 1935--1971. doi:10.1214/aos/1024691364. https://projecteuclid.org/euclid.aos/1024691364


Export citation

References

  • AALEN, O. 1978. Nonparametric inference for a family of counting processes. Ann. Statist. 6 701 726. Z.
  • ABAN, I. and PENA, E. 1998. Properties of test statistics applied to residuals in failure time models, J. Statist. Plann. Inference. To appear. Z.
  • AKRITAS, M. 1988. Pearson-ty pe goodness-of-fit tests: the univariate case. J. Amer. Statist. Assoc. 83 222 230. Z.
  • ANDERSEN, P., BORGAN, O., GILL, R. and KEIDING, N. 1993. Statistical Models Based on Counting Processes. Springer, New York. Z.
  • ANDERSEN, P. and GILL, R. 1982. Cox's regression model for counting processes: a large sample study. Ann. Statist. 10 1100 1120. Z.
  • ANGUS, J. 1982. Goodness-of-fit tests for exponentiality based on a loss-of-memory ty pe functional equation. J. Statist. Plann. Inference 6 241 251. Z.
  • BALTAZAR ABAN, I. and PENA, E. 1995. Properties of hazard-based residuals and implications in model diagnostics. J. Amer. Statist. Assoc. 90 185 197. Z.
  • BARLOW, R., BARTHOLOMEW, D., BREMMER, J. and BRUNK, H. 1972. Statistical Inference Under Order Restrictions. Wiley, New York. Z.
  • BARLOW, W. and PRENTICE, R. 1988. Residuals for relative risk regression. Biometrika 75 65 74. Z.
  • BHAT, B. and NAGNUR, B. 1965. Locally most stringent tests and Lagrangian multiplier tests of linear hy potheses. Biometrika 52 459 468. Z.
  • BICKEL, P., KLAASEN, C., RITOV, Y. and WELLNER, J. 1993. Efficient and Adaptive Estimation for Semiparametric Models. Johns Hopkins Univ. Press. Z.
  • BICKEL, P. and RITOV, Y. 1992. Testing for goodness of fit: a new approach. In Nonparametric Z. Statistics and Related Topics A. K. Md. E. Saleh, ed. 51 57. North-Holland, Amsterdam. Z.
  • BILLINGSLEY, P. 1968. Convergence of Probability Measures. Wiley, New York.
  • BORGAN, O. 1984. Maximum likelihood estimation in parametric counting process models, with applications to censored failure time data. Scand. J. Statist. 11 1 16. Z.
  • CHEN, Y., HOLLANDER, M. and LANGBERG, N. 1982. Small-sample results for the Kaplan Meier estimator. J. Amer. Statist. Assoc. 77 141 144. Z. 2
  • CHERNOFF, H. and LEHMANN, E. 1954. The use of maximum likelihood estimates in tests for goodness of fit. Ann. Math. Statist. 25 579 586. Z.
  • CHOI, S., HALL, W. and SCHICK, A. 1996. Asy mptotically uniformly most powerful tests in parametric and semiparametric models. Ann. Statist. 24 841 861. Z. Z.
  • COX, D. 1972. Regression models and life tables with discussion. J. Roy al Statist. Soc. Ser. B 34 187 220. Z.
  • COX, D. and REID, N. 1987. Parameter orthogonality and approximate conditional inference Z. with discussion. J. Roy al Statist. Soc. Ser. B 49 1 39. Z.
  • COX, D. and SNELL, E. 1968. A general definition of residuals. J. Roy al Statist. Soc. Ser. B 30 248 275. Z.
  • DOKSUM, K. and YANDELL B. 1984. Tests for exponentiality. In Handbook of Statistics 4: Z. Nonparametric Methods P.R. Krishnaiah and P. K. Sen, eds. 579 611. North-Holland, Amsterdam. Z.
  • DURBIN, J. 1973. Distribution Theory for Tests Based on the Sample Distribution Function.
  • SIAM, Philadelphia. Z.
  • DURBIN, J. 1975. Kolmogorov Smirnov tests when parameters are estimated with applications to tests of exponentiality and tests on spacings. Biometrika 62 5 22. Z.
  • EUBANK, R. and HART, J. 1992. Testing goodness-of-fit regression via order selection criteria. Ann. Statist. 20 1412 1425. Z.
  • FAN, J. 1996. Test of significance based on wavelet thresholding and Ney man's truncation. J. Amer. Statist. Assoc. 91 674 688. Z.
  • FLEMING, T. and HARRINGTON, D. 1991. Counting Processes and Survival Analy sis. Wiley, New York. Z.
  • GATSONIS, C., HSIEH, H. and KORWAR, R. 1985. Simple nonparametric tests for a known standard survival based on censored data. Comm. Statist. Theory Methods 14 2137 2162. Z.
  • GRAY, R. and PIERCE, D. 1985. Goodness-of-fit for censored survival data. Ann. Statist. 13 552 563. Z.
  • HABIB, M. and THOMAS, D. 1986. Chi-squared goodness-of-fit tests for randomly censored data. Ann. Statist. 14 759 765. Z.
  • HJORT, N. 1990. Goodness-of-fit tests in models for life history data based on cumulative hazard rates. Ann. Statist. 18 1221 1258. Z. IMSL LIBRARY 1987. User's Manual: Stat Library Fortran Subroutines for Statistical Analy sis. IMSL, Houston. Z.
  • INGLOT, T., KALLENBERG, W. and LEDWINA, T. 1994. Power approximations to and power comparison of smooth goodness-of-fit tests. Scand. J. Statist. 21 131 145. Z.
  • KALLENBERG, W. and LEDWINA, T. 1995. Consistency and Monte Carlo simulation of a data driven version of smooth goodness-of-fit tests. Ann. Statist. 23 1594 1608. Z.
  • KHMALADZE, E. 1981. A martingale approach in the theory of goodness-of-fit tests. Teor. Z Veroy atnost. i Primenen. 26 246 265 English translation in Theory Probab. Appl. 26. 240 257. Z.
  • KHMALADZE, E. 1993. Goodness of fit problem and scanning innovation martingales. Ann. Statist. 21 798 829. Z.
  • KIM, J. 1993. Chi-square goodness-of-fit tests for randomly censored data. Ann. Statist. 21 1621 1639. Z.
  • KLEIN, J. and MOESCHBERGER, M. 1997. Survival Analy sis: Techniques for Censored and Truncated Data. Springer, New York. Z.
  • KOZIOL, J. and GREEN, S. 1976. A Cramer von Mises statistic for randomly censored data. ´ Biometrika 63 139 156. Z.
  • LAGAKOS, S. 1981. The graphical evaluation of explanatory variables in proportional hazard regression models. Biometrika 68 93 98.
  • LEDWINA, T. 1994. Data driven version of Ney man's smooth test of fit. J. Amer. Statist. Assoc. 89 1000 1005. Z.
  • LI, G. and DOSS, H. 1993. Generalized Pearson Fisher chi-square goodness-of-fit tests, with applications to models with life history data. Ann. Statist. 21 772 797. Z.
  • LOy NES, R. 1980. The empirical distribution function of residuals from generalised regression. Ann. Statist. 8 285 298. Z.
  • NEy MAN, J. 1937. ``Smooth test'' for goodness of fit. Skand. Aktuarietidskr. 20 149 199. Z.
  • NEy MAN, J. 1959. Optimal asy mptotic tests of composite statistical hy potheses. In Probability Z. and Statistics: The Harald Cramer Volume U. Grenander, ed. 213 234. Wiley, New ´ York. Z.
  • PENA, E. 1995. Residuals from ty pe censored samples. In Recent Advances in Life-Testing Z. and Reliability N. Balakrishnan, eds. 523 543. CRC Press, Boca Raton. Z.
  • PENA, E. 1996. Smooth goodness-of-fit tests for composite hy pothesis in hazard based models. Technical report, Dept. Mathematics and Statistics, Bowling Green State University. Z.
  • PENA, E. 1998. Smooth goodness-of-fit tests for the baseline hazard Cox's Proportional Hazards Model. J. Amer. Statist. Assoc. 93 673 692. Z.
  • PIERCE, D. 1982. The asy mptotic effect of substituting estimators for parameters in certain ty pes of statistics. Ann. Statist. 10 475 478. Z.
  • RANDLES, R. 1982. On the asy mptotic normality of statistics with estimated parameters. Ann. Statist. 10 462 474. Z.
  • RANDLES, R. 1984. On tests applied to residuals. J. Amer. Statist. Assoc. 79 349 354. Z.
  • RAO, K. and ROBSON, D. 1974. A chi-square statistic for goodness-of-fit tests within the exponential family. Comm. Statist. 3 1139 1153. Z.
  • RAy NER, J. and BEST, D. 1989. Smooth Tests of Goodness of Fit. Oxford Univ. Press. Z.
  • RAy NER, J. and BEST, D. 1990. Smooth tests of goodness of fit: an overview. Internat. Statist. Rev. 58 9 17. Z.
  • STEPHENS, M. 1976. Asy mptotic results for goodness-of-fit statistics with unknown parameters. Ann. Statist. 4 357 369. Z. Z.
  • STEPHENS, M. 1992. Introduction to Kolmogorov 1933. On the empirical determination of a Z distribution. In Breakthroughs in Statistics 2: Methodology and Distribution S. Kotz. and N. Johnson, eds. Springer, New York. Z.
  • THERNEAU, T., GRAMBSCH, P. and FLEMING, T. 1990. Martingale-based residuals for survival models. Biometrika 77 147 160. Z.
  • THOMAS, D. and PIERCE, D. 1979. Ney man's smooth goodness-of-fit test when the hy pothesis is composite. J. Amer. Statist. Assoc. 74 441 445. Z.
  • WOOLSON, R. and SEN, P. K. 1974. Asy mptotic comparison of a class of multivariate multiparameter tests. Comm. Statist. 3 813 828.
  • BOWLING GREEN, OHIO 43403 E-MAIL: pena@stochos.bgsu.edu