Design-based and Model-based Inferences in Survey Sampling

We investigate both the design-based and model-based inferences, which are usual infcrential methods in survey sampling. While the design-based infcrence is on the basis of randomization principle, the model-based inference is based on likelihood principle as well as conditionality principle. There have been some disputes between two inferences for a long time and those have not yet been determined. In this paper we reviewed some issues on two inferences and compared their advantages and disadvantages in some viewpoints.