What are some resources or tips for learning nonparametric statistics?

2 How to learn nonparametric statistics?

Learning nonparametric statistics is best done by practicing with real data and examples. There are many online courses, books, and tutorials that use nonparametric methods and offer hands-on exercises and case studies. For instance, Coursera's Nonparametric Statistics course by the University of Amsterdam, Nonparametric Statistics for Non-Statisticians: A Step-by-Step Approach by Gregory W. Corder and Dale I. Foreman, Nonparametric Statistics with Applications to Science and Engineering by Paul H. Kvam and Brani Vidakovic, and Nonparametric Statistics: A Beginner's Guide by Jayant V. Deshpande and Usha S. Naik all provide excellent resources.

4 How to choose the appropriate nonparametric test?

When selecting an appropriate nonparametric test, it is necessary to consider the type and level of measurement of the data, the number and design of the samples, and the research question or hypothesis. Generally, one should take the following steps: identify the type and level of measurement of the data (nominal, ordinal, interval, or ratio); determine the number and design of the samples (one, two, or more; paired or independent); and recognize the research question or hypothesis (difference, association, or goodness-of-fit). After considering these criteria, match them with the available nonparametric tests and select the most suitable one.

5 How to interpret and report the results of nonparametric tests?

Interpreting and reporting the results of nonparametric tests are similar to those of parametric tests. When reporting, you must provide the test statistic, the degrees of freedom (if applicable), the p-value, and the effect size (if available). Additionally, you must state whether the result is statistically significant or not, and explain its meaning in terms of the research question or hypothesis. For instance, a Wilcoxon signed-rank test comparing pretest and posttest scores of students showed that their scores improved after the intervention (W = 34, p < 0.05). Similarly, a Spearman's rank correlation between income and happiness showed a positive and strong relationship (r = 0.76, p < 0.01), suggesting that higher income is associated with higher happiness.

6 Here’s what else to consider

This is a space to share examples, stories, or insights that don’t fit into any of the previous sections. What else would you like to add?