Abstract: The method for retaining sampled units in successive sampling survey for changed probability of selection is introduced. For PPS sampling design, a model-design unbiased predictor for the total of a variable for the target population is proposed, and the optimum matching ratio for the predictor under the assumption of unchanged population is calculated. For RHC sampling design, the equation that the optimum matching ration satisfies is given.

Key words: successive sampling survey, retain sample, matching ratio, RHC sampling design

摘要： 介绍了连续抽样中概率发生变化时保留样本的方法。对于有放回的PPS抽样，在假设的超总体模型之下提出了总体变量总值的模型——设计无偏预报量，并计算了总体不变时保留样本的最优匹配比。对于无放回的RHC抽样，给出了最优匹配比满足的方程。

关键词: 连续抽样, 保留样本, 匹配比, RHC设计