A common problem arising in statistics is to determine the smallest sample size needed to achieve a specified inference goal. Examples of inference goals include finding a 95% confidence interval for a given statistic of width no larger than a specified amount, or performing a hypothesis test at the 5% significance level with power no smaller than a specified amount. These examples and others are discussed more fully below.
Sample Size to Achieve a Given Variance or Relative Variance
One may want to estimate a parameter θ by an estimator \(\hat{\theta }\) based on a sample of size n. Often the variance of \(\hat{\theta },\) \(\mbox{ var}(\hat{\theta }),\) will have the form \(\mbox{ var}(\hat{\theta }) = b/n\) for some known constant b. To achieve a variance of \(\hat{\theta }\) no larger than a specified amount A, one simply sets A = b ∕ n and solves for n: n = b ∕ A. The value of n must be an integer, so one takes n to be the smallest integer no smaller than b ∕ A. Note that nis...
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References and Further Reading
Cohen J (1988) Statistical power analysis for the behavioral sciences, 2nd edn. Erlbaum, Hillsdale
Cohen MP (2005) Sample size considerations for multilevel surveys. Int Stat Rev 73:279–287
Dattalo P (2008) Determining sample size. Oxford University Press, New York
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this entry
Cite this entry
Cohen, M.P. (2011). Sample Size Determination. In: Lovric, M. (eds) International Encyclopedia of Statistical Science. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-04898-2_500
Download citation
DOI: https://doi.org/10.1007/978-3-642-04898-2_500
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-04897-5
Online ISBN: 978-3-642-04898-2
eBook Packages: Mathematics and StatisticsReference Module Computer Science and Engineering