Definition: The Chi-square (χ²) test is a non-parametric statistical hypothesis test used to determine if there is a statistically significant association between two categorical variables, comparing observed frequencies in categories to expected frequencies under the null hypothesis of no association.
The Chi-square test is fundamentally employed to assess whether an observed distribution of categorical data significantly differs from an expected distribution, or more commonly in public health, to determine if two categorical variables are independent of each other. The test operates under a null hypothesis that there is no association between the variables, meaning the distribution of one variable is the same across all categories of the other. By comparing the actual counts (observed frequencies) in each category of a contingency table against the counts that would be expected if the null hypothesis were true (expected frequencies), the test calculates a chi-square statistic. This statistic, along with the degrees of freedom, is then used to derive a p-value, which indicates the probability of observing such a difference (or a more extreme one) if the null hypothesis were true.
In public health, the Chi-square test is an invaluable tool for identifying potential relationships and disparities within populations. For instance, it can be used to investigate if there is a significant association between a particular exposure (e.g., living near a pollution source) and a health outcome (e.g., respiratory illness), or to assess if the distribution of a health behavior (e.g., regular exercise) differs significantly across various demographic groups (e.g., age, socioeconomic status, race/ethnicity). Public health researchers also use it to evaluate the effectiveness of interventions by comparing the proportion of individuals achieving a desired outcome in an intervention group versus a control group. While powerful for categorical data, it’s crucial to ensure adequate sample sizes and avoid situations where expected cell counts are very low, as this can affect the test’s validity.
Key Context:
- Categorical Variables and Contingency Tables: The Chi-square test is specifically designed for analyzing associations between two or more categorical variables, typically organized into a contingency table (cross-tabulation).
- Null Hypothesis and p-value: The test evaluates a null hypothesis of no association or independence between variables, with the resulting p-value indicating the strength of evidence against this hypothesis.
- Fisher’s Exact Test: For situations with small sample sizes or when more than 20% of expected cell counts in a contingency table are less than 5, Fisher’s Exact Test is often preferred as a more appropriate alternative to the Chi-square test.