Survey Frame
A survey frame is a list used for survey sampling.
Description
AAPOR recognizes four types of frames:
- List frames
- Address-based frames
- Random-digit dial (RDD) telephone frames
- Probability-based panel frames
This does purposefully exclude the statistics of non-probability web panels.
The details of a frame establish the universe for survey inference.
List Frames
A list of specifically-named individuals.
List frames are commonly taken as a complete population. Assumptions about over-coverage and under-coverage should be examined.
ABS Frames
A list of specific addresses; the specific residents are not necessarily known, nor whether they are eligible.
RDD Frames
A procedure for randomly generating telephone numbers.
Dual-frame RDD (DFRDD) refers to drawing two random samples for landline telephone numbers and cellphone numbers.
First, all possible hundred-digit blocks form the frame. These are (in the U.S.) the full set of 8-digit prefixes for which there are 100 10-digit phone numbers. The best practice, when it is feasible, is to remove the hundred-digit blocks with 0 or 1 residential numbers (according to either published phone books or collected data). A SRS with replacement is then drawn from this frame. This forms the first important probability of selection.
Stratified RDD sampling relies on the segmentation of the hundred-digit block frame. Generally, this is done according to geographic bounds (state, county, or ZIP code) for which 3-digit area codes can be roughly matched. Given this information and additional statistics, e.g. which ZIP codes have higher concentrations of black residents, it can be possible to segment the frame by demographic propensities.
For each selection (because a hundred-digit block can be selected multiple times), a random 10-digit phone number from the hundred-digit block is called. In some cases, 10-digit phone numbers are tried sequentially until a response is collected. This reveals one strength of the hundred-digit block--a call center can be directed to contact some number of households with a prefix, and the interviewers are free to replace the specific households as needed.
From a household, there are often multiple possible respondents. A screening protocol is used to decide on the best respondent. This forms the second important probability of selection.