Answers are grounded in this paper and cite their sources.
SUMMARY The effect of a two-stage sampling design on statistical inference is discussed. A definition of a design effect is given. The structure of design effects for a class of statistics is investigated. Results have both a design-based and a model-based interpretation. The relation between design effects for multivariate statistics and design effects for univariate statistics is considered.
No takes yet. Share an insight, caveat, or question.
C. J. Skinner (1986) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: