Standard Article

Sampling With Probability Proportional to Size

  1. Ronald Czaja

Published Online: 15 JUL 2005

DOI: 10.1002/0470011815.b2a16066

Encyclopedia of Biostatistics

Encyclopedia of Biostatistics

How to Cite

Czaja, R. 2005. Sampling With Probability Proportional to Size. Encyclopedia of Biostatistics. 7.

Author Information

  1. North Carolina State University, Raleigh, NC, USA

Publication History

  1. Published Online: 15 JUL 2005

Abstract

Sampling with probability to proportionate to size (PPS), as the name implies, involves sampling elements that are typically arranged into natural groupings of different sizes. Sampling PPS is an efficient design when a list of the population is not available; the elements are in clusters or natural groups that differ greatly in size; it is important to control the sample size; costs and equalizing interviewer workloads are important; the use of natural divisions is possible and supplementary information is available by the natural divisions; and when the sample must be drawn in multiple stages. This entry presents a detailed example of a PPS design, a multistage area probability design, and discusses a random digit telephone sample design that uses PPS sampling.

Keywords:

  • multistage;
  • area probability sampling;
  • sampling PPS;
  • cluster sampling;
  • nested sample design;
  • primary sampling units;
  • measures of size;
  • design effect;
  • interviewer work load