Parametric and Non-Parametric Tests of Independence
Refresher reading access
Introduction
In many contexts in investments, we want to assess the strength of the linear relationship between two variables—that is, we want to evaluate the correlation between them. A significance test of a correlation coefficient allows us to assess whether the relationship between two random variables is the result of chance. Lesson 1 covers a parametric and a non-parametric approach to testing the correlation between two variables. If we decide that the relationship does not result from chance, then we can use this information in modeling or forecasting using regression models or machine learning covered in later learning modules.
When faced with categorical or discrete data, however, we cannot use the methods discussed in the first lesson to test whether the classifications of such data are independent. If we want to test whether there is a relationship between categorical or discreet data, we can perform a test of independence using a nonparametric test statistic. The second lesson covers the use of contingency tables in implementing this non-parametric test.
Learning Outcomes
The candidate should be able to:
- explain parametric and nonparametric tests of the hypothesis that the population correlation coefficient equals zero, and determine whether the hypothesis is rejected at a given level of significance
- explain tests of independence based on contingency table data
0.75 PL Credit
If you are a CFA Institute member don’t forget to record Professional Learning (PL) credit from reading this article.