Evidlake
Menu

Sampling Frame

Also known as: sample frame, coverage error.

The list or source a sample is actually drawn from. Whatever the frame leaves out cannot appear in the sample, however large the sample is.

Updated Last reviewed

Synthetic dataExamples on this page use synthetic data created for illustration.

Definition

A sampling frame is the actual list or source from which a sample is drawn, such as a directory, a ranking page or a customer table. Anything the frame leaves out has no chance of being sampled, so the frame, not the sample size, sets what the results can describe.

In plain terms

The target population is what you want to know about; the frame is what you can reach. They are often different. A survey drawn from a phone book misses people without a listed number; a study of “the market” drawn from a best-seller list sees only the best sellers.

A large sample of a narrow frame is still a narrow view. The honest wording is “this describes the items on the frame”. When you do not know how much of the population the frame covers, say that coverage is unknown rather than implying it is complete.

Example

A study wants the average price of all 20,000 kitchen items in a marketplace. It uses the “top 100 best sellers” list as its frame and measures all 100 (a 100% sample of the frame).

ItemsAverage price (synthetic)
Population: all kitchen items20,00040
Frame: the top-100 list100 (0.5%)25

Measuring every item on the list does not make the figure 25 an estimate of the market’s 40. It describes the best-seller list.

Common misunderstandings

  • “A big sample fixes a bad frame.” More items from the same frame repeat the same blind spot.
  • “If I take everything on the frame there is no bias.” The frame itself is a selection.
  • “Frame and population are the same.” The gap between them is what coverage error measures.
  • Population and Sample

    The population is everything you want to know about; the sample is the part you observed. Statistics asks what the second says about the first.

  • Survivorship Bias

    A selection error from studying only what survived a process and ignoring what dropped out along the way.

  • Data Snapshot

    A complete record of a list or table as it stood at one moment, kept as a unit with its time, scope and completeness, so later versions can be compared against it.

References

  1. Robert M. Groves et al.. Survey Methodology . Wiley, 2009. ISBN 978-0470465462.
  2. Sharon L. Lohr. Sampling: Design and Analysis . Chapman and Hall/CRC, 2021. ISBN 978-0367273415.