Not Too Big, Not Too Small

Abstract:Running significance tests with small sample sizes can produce incomplete or inaccurate results. In order to overcome this problem, the largest sample size available is chosen to ensure a better picture of the data as well as more desirable confidence intervals. The question is, when is a sample size too large and is there an optimal size for significance tests? How can an optimal sample size be found? Knowing what test to use, what the significant results are and what is an acceptable probability of error are good ways to start finding the right sample …

Access this article
Other ways to access this article

Social Bookmarking

Digg, delicious, NewsVine, Furl, Google, StumbleUpon, BlogMarks, Facebook



Featured advertisers