2016/12/15 by Yves Tillé, Tillé, Yves, Matthieu Wilhelm +1
Computer Science · Mathematics · #Bayesian Methods and Mixture Models #FOS: Computer and information sciences #Methodology (stat.ME) #Statistical Methods and Bayesian Inference #Survey Sampling and Estimation Techniques
paper · pdf · doi:10.48550/arxiv.1612.04965
openalex publication_date 2016/12/15 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
The aim of this paper is twofold. First, three theoretical principles are\nformalized: randomization, overrepresentation and restriction. We develop these\nprinciples and give a rationale for their use in choosing the sampling design\nin a systematic way. In the model-assisted framework, knowledge of the\npopulation is formalized by modelling the population and the sampling design is\nchosen accordingly. We show how the principles of overrepresentation and of\nrestriction naturally arise from the modelling of the population. The balanced\nsampling then appears as a consequence of the modelling. Second, a review of\nprobability balanced sampling is presented through the model-assisted\nframework. For some basic models, balanced sampling can be shown to be an\noptimal sampling design. Emphasis is placed on new spatial sampling methods and\ntheir related models. An illustrative example shows the advantages of the\ndifferent methods. Throughout the paper, various examples illustrate how the\nthree principles can be applied in order to improve inference.\n