Estimation Using Monte Carlo Methods in Nonlinear Random Coefficient Models

몬테카를로법을 이용한 비선형 확률계수모형의 추정

  • 김성연 (동아대학교 경영정보과학부)
  • Published : 2001.09.01

Abstract

Repeated measurements on units under different conditions are common in biological and biomedical studies. In a number of growth and pharmacokinetic studies, the relationship between the response and the covariates is assumed to be nonlinear in some unknown parameters and the form remains the same for all units. Nonlinear random coefficient models are used to analyze such repeated measurement data. Extended least squares methods are proposed in the literature for estimating the parameters of the model. However, neither objective function has closed form expression in practice. This paper proposes Monte Carlo methods to estimate the objective functions and the corresponding estimators. A simulation study that compare various methods is included.

Keywords

References

  1. Technical Report. Division of Clnical Pharmacology. University of California Asymptotic properties fo optimization esimators for the indepensent not identically distributed case with application to extended least squares estimators Beal, S.L.
  2. Journal of Bioharmaceutical Statistics v.13 Some general estimation methods for nonlinear mixed effects models Davidian, M;D.M. Giltinan
  3. Nonlinear Models for Repeated Measurement Data Davidian,M;D.M.Giltinan
  4. Technical Report, Deparment of Statistics, North Carolina State University Consequences of misspecifying assumptions in nonlinear mixed effects hartford, A.;m. Davidian
  5. Ph.D. Dissertation, Department of Statistics, North Carolina State University Extended least squares estimation using Monte Carlo Method in nonlinear random coefficient models Kim, S.
  6. Journal of Computational Graphical Statistics v.4 Approximations to the log-likelihood functin in nonlinear mixed effects model Pinheiro, J.C.;D.M. Bates
  7. Ph.D. Dissertation, North Carolina State University Estimation of nonlinear mixed effects and random coefficient models Ramos, R.Q.
  8. Estimation of nonlinear random coefficient models v.24 Ramos, R.Q.;S.G. Pantula
  9. Journal of Pharmacokinetics and Biopharmaceutics v.8 Evaluation of methods for estmating population pharmacokinetic parameters. I. Michaelis-Menten model: Routine clonical pharmacokinetic data Sheiner, L.B.;S.L. Beal
  10. Journal of Pharmacokinetics and Biophamaceutucs v.13 no.2 Phamacoinetic parameter estimates from several least squares rocedures: Superiority of extended least squares Sheiner, L.B.;S.L. Beal
  11. Biometrics v.48 Mixed effects nonlinear regression for unbalanced reprated measures Vonesh, E.F;R.L. Carter