Printer Friendly

Practices of Science: Census vs. Survey

 

The purpose of a census is to collect information about every single item you are interested in studying in an area.  For example, if a scientist were interested in the size of intertidal snails along a coastline and wanted to use the census method of surveying, the scientist would measure the size of every single snail along that coastline. 
 
Although collecting information about every individual is useful, taking census data is often logistically impossible due to time and cost constraints. Because scientists know they will likely miss individuals if they try to collect census data, they usually survey an area using samples of the population they are interested in studying instead. To survey an area scientists examine and describe some aspect of an area or environment. Survey samples can be examined to estimate and infer characteristics about the entire population. There are many different ways of performing surveys and many different forms of sampling techniques that can be used to collect data depending on the discipline of the researcher (e.g. geology, geography, psychology) and the goals of the study. Instead of a census, the scientist interested in snail size might survey snail sizes by measuring snails from sample intertidal sites and use this data to infer something about the size of all of the snails along the coastline. 
 
The US Census: Despite the difficulties involved in a census, every ten years the United States Census Bureau tries to collect information from every resident in United States. This information is used to allocate federal funding, Congressional seats, and electoral votes. With the U.S. population totaling over 308 million in 2010, collecting census information is a daunting task. 
 
Although tremendous resources are allocated for the US census, a small percentage of people are inevitably missed. Although it is impossible to know exactly who is missing from the census, researchers know from comparison studies that some segments of the population are easier to count in the census than others. 
 
[Insert SF Fig. 1]
SF Fig. 1. This figure, generated from US Census data collected in 2010, shows the percent change in the US population between 2000 and 2010. The dark blue areas show population increases indicating people are moving into these areas of the country. The dark red areas show population decreases indicating people are moving out of these areas. 
Question Set: 

 

  1. What segments of the population might be missed in the US census? Why?
  2. How might surveying a population by collecting many samples provide more useful information than a census, especially if there are not a lot of resources available to do the study?
  3. What might be some benefits of conducting a census even if you miss some segments of the population? 

Special Feature Type:

Exploring Our Fluid Earth, a product of the Curriculum Research & Development Group (CRDG), College of Education. University of Hawaii, 2011. This document may be freely reproduced and distributed for non-profit educational purposes.