A Method Study Of Model-Assisted Sampling Estimation

This paper studies mainly how to estimate by super population regression model in the phase of sampling estimation and dissert systematically methods of model-assisted sampling estimation under different super population regression models in order to structure an integrated system of research.In the first chapter of this paper, there is detailed expound about methods of model-assisted estimation. At the same time, some notions, such as auxiliary information, super population model and model-assisted estimation, are defined. In second chapter, a universal super population regression model, namely generalized regression model is put forward and generalized regression estimator under this model is deduced. The method succeeds in introducing auxiliary variable into the formula of estimator and the precision of estimation is improved greatly. General conclusions introduced from this chapter are basic conclusions which help to study thoroughly succedent issues. The contents from the third chapter to the fifth chapter are the kernels which are a series of applications of generalized regression model and generalized regression estimator. At first, this paper constructs ratio model, linear regression model, post-stratified regression model and nonparametric regression model through different regressive relationship between auxiliary variable and study variable. And then this paper study systematically these methods of sampling estimation under regression model-assisted theories. Thus, an integrated system of research about model-assisted sampling estimation is constructed. At last, the sixth chapter makes a summary of this paper, put forward some shortcomings and prospects applied foreground of this paper.