Relationships · Categorical data
Chi-Square as Evidence of Association
How different are the observed counts from the counts expected if the variables were independent?
Page 1 of 7 · Big Picture
The big picture: Chi-Square as Evidence of Association
How far are observed counts from independence?
Why a policy analyst should care
Chi-square separates ordinary sampling differences from departures large enough to question independence, but it does not describe the size or policy importance of the association.
Follow the idea from the opening question to a practical decision. These are the conceptual moves this module will develop:
1 Question Does the outcome distribution differ by group?
2 Explore Observed and expected counts
3 Formalize From cell departures to chi-square
4 Transfer Audit a survey comparison
Use the left and right arrow keys to move between pages.