Sampling for In Person (Face-to-Face) Surveys
National samples for face-to-face surveys are typically drawn by an area probability method, which relies on US Census figures and maps of the country. The NES used a four-tage process to draw its 2004 national sample. This process is called a multi-stage area probability sample and it was developed by the Survey Research Center at The University of Michigan and the National Opinion Research Center at The University of Chicago many years ago:
The first stage of the process is to select main or "primary" sampling units from the listing of all Metropolitan Statistical Areas (MSAs), single non-MSA counties, and groups of small non-MSA counties.
The second stage involves selection of either census blocks (in urban areas) or enumeration districts (in more rural areas) from the primary stage units.
In the third stage listings of all housing units located within the second stage sampling unit are generated and a sample of these housing units is taken.
The fourth stage involves identifying all adults in a selected household and selecting one on a random basis.