몬테카를로법을 이용한 버선형 확률계수모형의 추정

Estimation Using Monte Carlo Methods in Nonlinear Random Coefficient Models

Repeated measurements on 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 nonlinearin 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.