4.4 Non-parametric tests

2026 Syllabus Objectives

  1. Understand the idea of a non-parametric test and appreciate situations in which such a test might be useful (e.g., when sampling from a population which cannot be assumed to be normally distributed)

  2. Understand the basis of the sign test, the Wilcoxon signed-rank test and the Wilcoxon rank-sum test (including knowledge that Wilcoxon tests are valid only for symmetrical distributions)

  3. Use a single-sample sign test and a single-sample Wilcoxon signed-rank test to test a hypothesis concerning a population median (including the use of normal approximations where appropriate; questions will not involve tied ranks or observations equal to the population median value being tested)

  4. Use a paired-sample sign test, a Wilcoxon matched-pairs signed-rank test and a Wilcoxon rank-sum test, as appropriate, to test for identity of populations (including the use of normal approximations where appropriate; questions will not involve tied ranks or zero-difference pairs)


What are Non-parametric Tests? 🔑

Parametric tests are hypothesis tests carried out when the underlying distribution of the population is known. These tests involve parameters such as the population mean μ\mu and assume an underlying normal distribution. Examples include z-tests and t-tests that we studied in Chapter 9.

Non-parametric tests are hypothesis tests carried out when the underlying distribution of the population is unknown. These tests are particularly useful when:

  • The sample size is small
  • The population cannot be assumed to be normally distributed
  • The data do not meet the assumptions required for parametric tests

In non-parametric tests, the measure of centrality is usually the median rather than the mean, since the median does not depend on knowing the underlying distribution.


Types of Non-parametric Tests 📊

The following table summarizes the main non-parametric tests covered in this subtopic, along with their assumptions:

Type of testTestAssumptions
Single sampleSign testThe underlying data are continuous; The data are independent
Single sampleWilcoxon signed-rank testThe underlying data are symmetric; The underlying data are continuous; The data are independent
Two samplePaired sign testThe data are in matched pairs; The differences between matched pairs are continuous; The data are independent
Two sampleWilcoxon matched-pairs signed-rank testThe data are in matched pairs; The differences between matched pairs are symmetric; The differences between matched pairs are continuous; The data are independent
Two sampleWilcoxon rank-sum testThe two samples are independent; The underlying data are symmetric; The underlying data are continuous

Important: Wilcoxon tests are valid only for symmetrical distributions.

Sign in to view full notes