Mouse Behavioral Testing Volume 226 || Sample Size

✍ Scribed by Wahlsten, Douglas

• Book ID: 111868377
• Publisher: Elsevier
• Year: 2011
• Tongue: English
• Weight: 89 KB
• Edition: 1
• Category: Article
• ISBN: 012375674X
• DOI: 10.1016/b978-0-12-375674-9.10005-9

✦ Synopsis

Once the design and measuring instruments for a study are decided, a sample size must be chosen. This chapter discusses the factors important for deciding sample size. A researcher cannot seek ethics approval, apply for a grant, or defend a thesis proposal unless a good reason can be given for testing a specific number of animals. The correct sample size to use in an experiment depends primarily on three things: the design of the study, the size of the treatment effects that one reasonably expects or hopes will occur, and the acceptable level of risk that effects of that size will indeed occur but the statistical tests will fail to detect. Methods to estimate sample size depend on statistical theory. Therefore, a brief review of some of the basic principles of statistical inference is needed, just enough to understand the elements of a sample size calculation. Computing sample size from statistical theory can be a major challenge because the theoretical distributions of values are complex and asymmetrical, and a different formula needs to be used for each experimental design. But there are many situations where those approaches are not readily applied. Instead, it is possible to make the calculations with the aid of a series of utilities created with Microsoft Excel, each adapted to a specific experimental design.