What is a chi-squared test for independence?

1 Answer
Nov 25, 2015

A chi-squared test for independence tests if there is a significant relationship between two or more groups of categorical data from the same population.

Explanation:

A chi-squared test for independence tests if there is a significant relationship between two or more groups of categorical data from the same population. The null hypothesis for this test is that there is no relation. It is one of the most commonly used tests in statistics.

In order to use this test, your observations should be independent and your expected values should be greater than five.

The equation to calculate a chi square by hand is
https://www.aea267.k12.ia.us/assessment/statistics/chi-square/chi-square-test-of-independence/

Here's an example:
http://www.bmj.com/about-bmj/resources-readers/publications/statistics-square-one/8-chi-squared-tests

Once you have calculated your chi square, you determine your degrees of freedom (the number of levels for one variable minus one multiplied by the number of levels for the other variable minus one). Then refer to a chi square distribution table to see if your calculated value is higher than the value in the table. If it is higher than the table, then you reject the null hypothesis.

To learn more, check out this link .