ABSTRACT
Most surveys use a combination of the features presented in Chapters 1 through 6. A survey may be stratified with several stages of clustering and then be calibrated to population quantities. Sampling weights and design effects are commonly used to plan surveys and calculate estimates. This chapter discusses how to construct weights, calculate design effects, and produce graphs of data from complex surveys. The chapter gives a detailed description of the design of the U.S. National Health and Nutrition Examination Survey and shows how all of the concepts discussed so far about sampling apply to that survey.
