Lifetime Data Analysis

, Volume 1, Issue 2, pp 131–144 | Cite as

Gaussian models for degradation processes-part I: Methods for the analysis of biomarker data

  • Kjell A. Doksum
  • Sharon-Lise T. Normand


We present two stochastic models that describe the relationship between biomarker process values at random time points, event times, and a vector of covariates. In both models the biomarker processes are degradation processes that represent the decay of systems over time. In the first model the biomarker process is a Wiener process whose drift is a function of the covariate vector. In the second model the biomarker process is taken to be the difference between a stationary Gaussian process and a time drift whose drift parameter is a function of the covariates. For both models we present statistical methods for estimation of the regression coefficients. The first model is useful for predicting the residual time from study entry to the time a critical boundary is reached while the second model is useful for predicting the latency time from the infection until the time the presence of the infection is detected. We present our methods principally in the context of conducting inference in a population of HIV infected individuals.


Degradation processes Gaussian process models Inverse Gaussian distribution regression models CD4 HIV residual time latency time 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. S. M. Berman, “A Stochastic Model for the Distribution of HIV Latency Time Based on T4 Counts,”Biometrika vol. 77 pp. 733–741, 1990.Google Scholar
  2. S. M. Berman, “Perturbation of Normal Random Vectors by Nonnormal Translations, and an Application to HIV Latency Time Distributions,”Annals of Applied Probability, vol. 4 pp. 968–980, 1994.Google Scholar
  3. L. M. Calzavara, R. A. Coates, J. M. Raboud, et al, “Ongoing high-risk sexual behaviors in relation recreational drug use in sexual encounters: Analysis of 5 years of data from the Toronto Sexual Contact Study,”Ann. Epidemiol. vol. 3 pp. 272–280, 1993.Google Scholar
  4. CDC, Revision of the HIV classification system and the AIDS surveillance definition. Center for Disease Control and Prevention (Atlanta), 1993.Google Scholar
  5. R. S. Chhikara and L. Folks,The Inverse Gaussian Distribution. Theory, Methdology and Applications, Marcel Dekker: New York, 1989.Google Scholar
  6. P. D. Cleary, E. Singer, et al, “Sociodemographic and behavioural characteristics of HIV antibody-positive blood donors,”American Journal of Public Health vol. 78 pp. 953–957, 1988.Google Scholar
  7. W. S. Cleveland and S. J. Devlin, ‘Locally weighted regression: An approach to regression analysis by local fitting,”Journal of the American Statistical Association vol. 83 pp. 596–610, 1988.Google Scholar
  8. K. A. Doksum and A. Hóyland, “Models for Variable-Stress Accelerated Life Testing Experiments Based on Wiener Processes and the Inverse Gaussian Distribution,”Technometrics vol. 34 pp. 74–82, 1992.Google Scholar
  9. J. Fan, “Locally linear regression smoothers and their minimax efficiencies,”Annals of Statistics vol. 21 pp. 196–216, 1993.Google Scholar
  10. N. P. Jewell and J. D. Kalbfleisch, “Marker models in survival analysis and applications to issues associated with AIDS,” InAIDS Epidemiology: Methodological Issues (N. P. Jewell, K. Dietz, and V. T. Farewell, eds.), Birkhäuser: Boston, 1992, pp. 211–230.Google Scholar
  11. J. P. Jewell, K. Dietz, and V. T. Farwell,AIDS Epidemiology: Methodological Issues, Birkhäuser: Boston, 1992.Google Scholar
  12. R. A. Kaslow, D. G. Ostrow, R. Detels, et al, “The Multicenter AIDS Cohort Study: rationale, organization, and selected characteristics of the participants’,American Journal of Epidemiology vol. 126 pp. 310–318, 1987.Google Scholar
  13. M. Lefkopoulou and M. Zelen, “Intermediate clinical events, surrogate markers and survival,”Proceedings of the 1994 Conference on Lifetime Data Models in Reliability and Survival Analysis, in press, 1995.Google Scholar
  14. J. S. Montaner, J. Singer, M. T. Schechter, et al, “Clinical correlates of in vitro HIV-1 resistance of zidovudine. Results of the Multicenter Canadian AZT Trial,”AIDS vol. 7 pp. 189–196, 1993.Google Scholar
  15. S. L. Normand and K. A. Doksum, ‘Nonparametric calibration methods for longitudinal data,” Technical Report #HCP-1994-3, Department of Health Care Policy, Harvard Medical School, Boston, MA, 1994.Google Scholar
  16. D. Ruppert and M. P. Wand, “Multivariate locally weighted least squares regression,”Annals of Statistics vol. 22, to appear, 1994.Google Scholar
  17. W. Winkelstein Jr, D. M. Lyman, N. Padian, R. Grant, M. Samuel, R. E. Anderson, W. Lang, J. Riggs, and J. A. Levy, “Sexual practices and risk of infection by the human immunodeficiency virus,”Journal of the American Medical Association vol. 257 pp. 321–325, 1987.Google Scholar

Copyright information

© Kluwer Academic Publishers 1995

Authors and Affiliations

  • Kjell A. Doksum
    • 1
  • Sharon-Lise T. Normand
    • 2
  1. 1.University of CaliforniaBerkeley
  2. 2.Department of Health Care PolicyHarvard Medical SchoolBoston

Personalised recommendations