Nonparametric inference refers to statistical methods that do not make any assumptions about the underlying probability distribution of the data. In other words, nonparametric methods do not require the data to follow a specific mathematical model or to have a specific set of parameters.

Nonparametric inference is often used when the data are not normally distributed or when the sample size is small. Nonparametric methods are also commonly used when the assumptions of parametric methods cannot be met, such as when the data are skewed or have outliers.

Some examples of nonparametric methods include:

1. Wilcoxon rank-sum test: A nonparametric test used to compare two independent samples.

2. Kruskal-Wallis test: A nonparametric test used to compare three or more independent samples.

3. Mann-Whitney U test: A nonparametric test used to compare two independent samples.

4. Spearman's rank correlation coefficient: A nonparametric measure of the strength of association between two variables.

5. Kendall's tau: A nonparametric measure of the strength of association between two variables.

Nonparametric methods are often considered to be more robust than parametric methods because they do not rely on assumptions about the underlying distribution of the data. However, nonparametric methods may have less power than parametric methods when the assumptions of the latter are met.