Contents
What is required in a nonparametric test?
What are Nonparametric Tests? In statistics, nonparametric tests are methods of statistical analysis that do not require a distribution to meet the required assumptions to be analyzed (especially if the data is not normally distributed). Due to this reason, they are sometimes referred to as distribution-free tests.
Do non parametric tests require random sampling?
The researcher can choose to perform a non-parametric test if the data do not fit all the necessary assumptions for a parametric test. Besides, a parametric test has no assumption for a random sampling but rather for a normal distribution. (But yes, the scales have to be interval or ratio).
When do you need to use a nonparametric test?
When the outcome is not normally distributed and the samples are small, a nonparametric test is appropriate. The Kruskal-Wallis Test A popular nonparametric test to compare outcomes among more than two independent groups is the Kruskal Wallis test.
How to determine sample size to perform a non-parametric statistical hypothesis test?
How to determine the sample size to perform a non-parametric statistical hypothesis test such as Mann-Whitney-Wilcoxon? The aim is to perform a comparison between two methods for which I can arbitrate the amount of data. However, collecting this type of data is very time-consuming as it depends on long simulation runs.
When is a nonparametric test robust to the central limit?
Tests are robust in the presence of violations of the normality assumption when the sample size is large based on the Central Limit Theorem (see page 11 in the module on Probability).
How to determine the sample size to perform a non-power test?
You should compute the sample size needed for a two-sample t-test, and then divide the sample size by the Pitman Asymptotic Relative Efficiency (ARE). It represents the asymptotic limit of the ratio of sample sizes needed by the two tests to achieve equal power.