Confidence Intervals and Sample Size
Abstract
Many of the misunderstandings and misuses of confidence intervals can be avoided if the following properties are kept in mind: (1) the interval is a statement about a characteristic of a statistical population, (2) the interval is derived from a random sample of that population and is subject to sampling variation, i.e., another sample and a repetition of the test would be expected to yield a different interval; and (3) the confidence coefficient is not associated with a particular interval but with the particular method of calculating it. (Author)
Document Details
- Document Type
- Technical Report
- Publication Date
- Jan 25, 1967
- Accession Number
- AD0718229
Entities
Organizations
- United States Army Test and Evaluation Command