Estimation and inference in pharmacokinetic models: The effectiveness of model reformulation and resampling methods for functions of parameters

  • Donna Niedzwiecki
  • Jeffrey S. Simonoff
Pharmacometrics

Abstract

It is well known that high parameter estimate correlations and asymptotic variance estimates can cause estimation and inference problems in the analysis of pharmacokinetic models. In this paper we show that analysis of three important functions of pharmacokinetic parameters, the half-life, mean residence time, and the area under the curve, can sometimes be greatly improved by reformulating the model to address collinearity and by using the bootstrap to form confidence intervals. The resultant estimators can be more accurate than the original ones, and resultant confidence intervals can be narrower. Of the three measures, the half-life estimator is much better behaved than the estimators of mean residence time and area under the curve under collinearity, suggesting that it (or measures like it) should be used more often.

Key words

pharmacokinetic modeling nonlinear estimation collinearity bootstrap 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    D. M. Bates and D. G. Watts.Nonlinear Regression Analysis and its Applications, Wiley, New York, 1988.CrossRefGoogle Scholar
  2. 2.
    D. M. Allen. Parameter estimation for nonlinear models with emphasis on compartmental models.Biometrics 39:629–637 (1983).PubMedCrossRefGoogle Scholar
  3. 3.
    W. J. Westlake. Problems associated with analysis of pharmacokinetic models.J. Pharm. Sci. 60:882–885 (1971).PubMedCrossRefGoogle Scholar
  4. 4.
    H. G. Boxenbaum, S. Riegelman, and R. M. Elashoff. Statistical estimations in pharmacokinetics.J. Pharmacokin. Biopharm. 2:123–148 (1974).CrossRefGoogle Scholar
  5. 5.
    P. M. Laskarzewski, D. L. Weiner, and L. Ott. A simulation study of parameter estimation in the one and two compartment models.J Pharmacokin. Biopharm. 10:317–334 (1982).CrossRefGoogle Scholar
  6. 6.
    J. G. Reich. On parameter redundancy in curve fitting of kinetic data. In L. Endrenyi (ed.),Kinetic Data Analysis: Design and Analysis of Enzyme and Pharmacokinetic Experiments, Plenum Press, New York, 1981, pp. 39–50.CrossRefGoogle Scholar
  7. 7.
    C. M. Metzler. Estimation of pharmacokinetic parameters: Statistical considerations.Pharmacol. Ther. 13:543–556 (1981).PubMedCrossRefGoogle Scholar
  8. 8.
    J. S. Simonoff and C.-L. Tsai. The use of guided reformulations when collinearities are present in nonlinear regression.Appl. Statist. 38:115–126 (1989).CrossRefGoogle Scholar
  9. 9.
    B. Efron.The Jackknife, the Bootstrap and Other Resampling Plans, SIAM, Philadelphia, 1982.CrossRefGoogle Scholar
  10. 10.
    W. J. Kennedy, Jr. and J. E. Gentle.Statistical Computing, Marcel Dekker, New York, 1980.Google Scholar
  11. 11.
    D. A. Belsley, E. Kuh, and R. E. Welsch.Regression Diagnostics: Identifying Influential Data and Sources of Collinearity, Wiley, New York, 1980.CrossRefGoogle Scholar
  12. 12.
    D. A. Freedman. Bootstrapping regression models.Ann. Statist. 9:1218–1228 (1981).CrossRefGoogle Scholar
  13. 13.
    D. A. Freedman and S. C. Peters. Bootstrapping a regression equation: Some empirical results.J. Am. Statist. Assoc. 79:97–106 (1984).CrossRefGoogle Scholar
  14. 14.
    D. V. Hinkley. Bootstrap methods.J. Royal Statist. Soc. Ser. B. 50:321–337 (1988).Google Scholar
  15. 15.
    J. S. Simonoff and C.-L. Tsai. Jackknifing and bootstrapping quasi-likelihood estimators.J. Statist. Comput. Simulation 30:213–232 (1988).CrossRefGoogle Scholar
  16. 16.
    C. F. J. Wu. Jackknife, bootstrap and other resampling methods in regression analysis (with discussion).Ann. Statist. 14:1261–1350 (1986).CrossRefGoogle Scholar
  17. 17.
    T. J. DiCiccio and J. P. Romano. A review of bootstrap confidence intervals.J. Royal Statist. Soc. Ser. B 50:338–354 (1988).Google Scholar
  18. 18.
    A. C. Davison, D. V. Hinkley, and E. Schechtman. Efficient bootstrap simulation.Biometrika 74:555–566 (1987).Google Scholar
  19. 19.
    J. R. Gleason. Algorithms for balanced bootstrap simulations.Am. Statist. 42:263–266 (1988).Google Scholar
  20. 20.
    E. S. Soofi. Effects of collinearity on information about regression coefficients.J. Economet. 43: in press.Google Scholar
  21. 21.
    IMSL.User's Manual: STAT/LIBRARY, IMSL, Houston, TX, 1987.Google Scholar
  22. 22.
    T. S. Weng. Comparison of generalized half-life and mean residence time derived from compartment analysis of pharmacokinetic data.Proc. ASA Biopharm. Sec. pp. 135–141 (1988).Google Scholar
  23. 23.
    J. S. Simonoff and C.-L. Tsai. Jackknife-based estimators and confidence regions in nonlinear regression.Technometrics 28:103–112 (1986).CrossRefGoogle Scholar
  24. 24.
    L. B. Sheiner and S. L. Beal. Pharmacokinetic parameter estimates from several least squares procedures: Superiority of extended least squares.J. Pharmacokin. Biopharm. 13:185–201 (1985).CrossRefGoogle Scholar
  25. 25.
    S. L. Beal and L. B. Sheiner. Heteroscedastic nonlinear regression.Technometrics 30:327–388 (1988).CrossRefGoogle Scholar

Copyright information

© Plenum Publishing Corporation 1990

Authors and Affiliations

  • Donna Niedzwiecki
    • 1
  • Jeffrey S. Simonoff
    • 2
  1. 1.Division of BiostatisticsMemorial Sloan-Kettering Cancer CenterNew York
  2. 2.Department of Statistics and Operations Research, Leonard N. Stern School of BusinessNew York UniversityNew York

Personalised recommendations