Inference Under Informative Probability Sampling
摘要
One of the outstanding features of sample surveys is that the samples are often drawn with unequal probabilities, at least at one stage of the sampling process. The selection probabilities are generally known for the sampled units in the form of the sampling weights (inverse of the sampling probability and possibly adjusted for nonresponse or calibration). The sampling weights are in common use for randomization-based inference on finite population quantities of interest, by weighting the sample observations by the corresponding sampling weights.