On this page
What this lesson covers
A chi-square test of independence assesses whether two categorical classifications are related by comparing observed cell counts with counts expected under independence.
Build expected counts from row and column totals, then sum standardized squared discrepancies. Use the right-tailed chi-square test to assess independence and residuals to locate unusual cells.
How do you calculate the chi-square independence statistic?
For each cell, multiply its row total by its column total and divide by the overall count. Sum (observed − expected)² / expected over all cells, using (rows − 1) × (columns − 1) degrees of freedom.
Expected cell count = row total × column total / overall total
- Expected count in row i, column j under independence
- Total number of observations
Chi-square = sum over all cells of (observed count − expected count)² / expected count
- Observed cell count
- Expected count under independence
- Numbers of rows and columns
For example, the lesson classifies 200 managers by low, medium or high fee and by beating or missing their benchmark. Row totals are 50, 100 and 50; observed beat/miss counts are 30/20, 38/62 and 12/38. Since 80 beat and 120 missed, expected counts are 20/30, 40/60 and 20/30. Summing all six (O − E)² / E contributions gives χ² ≈ 13.83 with (3 − 1) × (2 − 1) = 2 degrees of freedom.
Common mistakes
- Reading a significant chi-square statistic as identifying where the classifications are related is incorrect because the test does not locate the relationship.
Try a practice question
Choose an answer, then check it to read the explanation for every option.
Continue studying in Quizara
In Quizara the lesson comes with more practice questions on the topic, explanations for every option and an AI tutor for your follow-up questions.
Written by the Quizara Editorial Team under our editorial standards.