The t-tests reviewed in the previous chapter are suitable for studies with normally distributed results. However, if there are outliers, then the t-tests are not sensitive and non-parametric tests have to be applied. We should add that non-parametric are also adequate for testing normally distributed data. And, so, these tests are, actually, universal, and are, therefore, absolutely to be recommended.
CITATION STYLE
Cleophas, T. J., & Zwinderman, A. H. (2011). Non-Parametric Tests. In Statistical Analysis of Clinical Data on a Pocket Calculator (pp. 9–13). Springer Netherlands. https://doi.org/10.1007/978-94-007-1211-9_4
Mendeley helps you to discover research relevant for your work.