A Semiparametric Random Intercept Model

A Semiparametric Random Intercept Model

In fitting random-intercept models, it is commonly assumed that random effects and the error terms follow the normal distribution. In many emprical applications, the true distribution of random effects obeys non-parametric and thus the main concern of most recent studies is the use of semiparametric distributions. In this paper, we propose a new class of random-intercept models using the semiparametric distribution.This study focuses on how to estimate parameter in semiparametric random-intercept models. The weighted penalized least squares method is used to fit the model. so, we also prposed G criteria as modification of generalized cross validation in semiparametric regression to choose the optimal smoothing parametr. Using simulation data, it can be shown that this model can work well.

In fitting random-intercept models, it is commonly assumed that random effects and the error terms follow the normal distribution. In many emprical applications, the true distribution of random effects obeys non-parametric and thus the main concern of most recent studies is the use of semiparametric distributions. In this paper, we propose a new class of random-intercept models using the semiparametric distribution.This study focuses on how to estimate parameter in semiparametric random-intercept models. The weighted penalized least squares method is used to fit the model. so, we also prposed G criteria as modification of generalized cross validation in semiparametric regression to choose the optimal smoothing parametr. Using simulation data, it can be shown that this model can work well.