Census vs. Sampling

Surveys can gather information through different methods of observation. However, most surveys employ a questionnaire to measure specific characteristics of the population. There are two main ways to gather this information.

A census survey collects complete information from all participants in the population. General criteria of a census survey include:

• Establish and maintain a complete list of the primary sampling unit (PSU) components.
• All members of the PSU in the fishery must be included
• Validation (used to correct for missing and misreported data)
• Enforceable and enforced

A sample survey uses a representative group of a given population to determine characteristics of the entire population. General requirements of a sample survey include:

• The sample must be representative of the entire population.
• The data collected from the representative sample is expanded to produce an estimate of the total population.
• The estimate has two parts: Point estimate and margin of error.
• Assumptions should be tested to identify and measure potential bias if possible. 

Sample surveys are used when it is not possible or practical to conduct a census to count each individual of an entire population. Everyday examples of sample surveys include political polling, health statistics, and television ratings. Sample surveys are a proven, effective method for gathering accurate information if they are properly designed and the sample design is accounted for in the estimation methods.

View the estimation methods page for an introduction to some of the key elements of sample survey designs, and how they fit into MRIP.