Skip Navigation Bar

National Information Center on Health Services Research and Health Care Technology (NICHSR)

Precision and Accuracy: Defining the Standard
Page 19 of 40
Researchers need to understand the impact of their content requirements—what they intend to assert based on the data—upon an implied standard that refers to the quality of the data required.

They need to assess:
  • How critical is precision?
  • Do we need approximate information or must the results provide more fine-grained information?

These kinds of questions cannot be answered in the abstract. There is no single standard that applies to all cases. Rather, the amount of precision needed depends on the use of the statistics.

Are they going to be used:
  • For general information. For example, to make statements about the number of people with a condition.
  • As the basis of a scientific inference. For example, to reach conclusions about relationships between risks and conditions.
  • To resolve a dispute. For example, in a law court statistical data may be elicited to help decide whether an event was expected or the result of an injury.
Page 19 of 40