Non-parametric tests make fewer assumptions than parametric tests about the underlying population distribution and are distribution-free. They are commonly used for skewed data, small sample sizes, and ordinal data, and examples include the Wilcoxon rank sum test and sign test. In contrast, parametric tests assume a specific distribution like normal and are more powerful but require meeting more assumptions.
Non-parametric tests make fewer assumptions than parametric tests about the underlying population distribution and are distribution-free. They are commonly used for skewed data, small sample sizes, and ordinal data, and examples include the Wilcoxon rank sum test and sign test. In contrast, parametric tests assume a specific distribution like normal and are more powerful but require meeting more assumptions.
Non-parametric tests make fewer assumptions than parametric tests about the underlying population distribution and are distribution-free. They are commonly used for skewed data, small sample sizes, and ordinal data, and examples include the Wilcoxon rank sum test and sign test. In contrast, parametric tests assume a specific distribution like normal and are more powerful but require meeting more assumptions.
• Parametric tests make assumptions about the underlying distribution
in the population • Non-parametric tests do not make assumptions about the underlying distribution, and are often called distribution-free tests. Parametric vs. Non-parametric Tests Parametric Tests Non-parametric tests Makes assumptions about the underlaying distribution Distribution-free of the data Central measure: mean Central measure: median Commonly used for normally distributed data Commonly used for skewed, small sample size, and ordinal data Examples: t-test, z-test, F test for variances, likelihood Examples: Wilcoxon rank sum test, sign test, bootstrap ratio test tests
Remark: Parametric tests are usually more powerful than their