## Test Selection for Categorical Data **Key Point:** The choice of statistical test depends on the type of data (categorical vs. continuous) and study design. ### Data Type Analysis - **Outcome variable:** Smoking status (quit vs. not quit) — **categorical/binary** - **Groups:** Two independent groups (Group A vs. Group B) - **Sample size:** n₁ = 150, n₂ = 150 (both > 30, large samples) ### Why Chi-Square Test? The chi-square test is used to compare **proportions/frequencies** across two or more independent groups when: 1. Data is categorical (nominal or ordinal) 2. Groups are independent 3. Expected frequencies in each cell ≥ 5 **Contingency Table:** | Outcome | Group A | Group B | Total | |---------|---------|---------|-------| | Quit smoking | 45 | 30 | 75 | | Did not quit | 105 | 120 | 225 | | Total | 150 | 150 | 300 | **High-Yield:** Chi-square (χ²) compares **observed frequencies** with **expected frequencies** under the null hypothesis of no association. ### Formula Context $$\chi^2 = \sum \frac{(O - E)^2}{E}$$ where O = observed frequency, E = expected frequency ### Test Assumptions Met - ✓ Categorical outcome - ✓ Independent groups - ✓ Large sample size (n > 30 each) - ✓ Expected frequencies > 5 in all cells **Clinical Pearl:** In epidemiological and public health studies, comparing intervention success rates (binary outcomes) between two groups almost always requires chi-square, not t-test.
Sign up free to access AI-powered MCQ practice with detailed explanations and adaptive learning.