Contingency tables, also known as 2x2 tables or fourfold tables, are fundamental tools in statistics used to analyze the association between two categorical variables. In grade 12 statistics, understanding and interpreting contingency tables is a crucial skill, and we'll explore some examples with answers, focusing on chi-square tests for independence.
The chi-square test for independence helps determine if there's a significant association between two categorical variables. We'll use this test to analyze our contingency table examples.
Example 1: Smoking and Cancer
Suppose we have data on smoking habits and cancer from a study of 100 individuals.
| | Smokers | Non-smokers | Total | |-----------|---------|------------|-------| | Cancer | 5 | 2 | 7 | | No Cancer | 20 | 73 | 93 | | Total | 25 | 75 | 100 |
Chi-square Test of Independence
The null hypothesis (H0) is that there's no association between smoking and cancer. Calculate the expected frequencies, chi-square value, and degrees of freedom (df = (number of rows - 1) * (number of columns - 1) = 1).
Using a chi-square calculator or statistical software, we find X^2 = 8.27. With a p-value of 0.004 < 0.05, we reject H0 and conclude there's a significant association between smoking and cancer.
Odds Ratio
The odds ratio (OR) measures the strength of the association. Calculation: (a/c) / (b/d) = (5/2) / (20/73) = 1.8.
Smokers are 1.8 times more likely to have cancer than non-smokers. Since the OR is greater than 1, there's a positive association between smoking and cancer.
Example 2: Exam Preference and Gender
Consider 200 students who prefer either a multiple-choice (MC) or short-answer (SA) exam format and their genders.
| | MC | SA | Total | |-----------|---------|----------|--------| | Male | 60 | 40 | 100 | | Female | 40 | 60 | 100 | | Total | 100 | 100 | 200 |
Chi-square Test of Independence
Calculate expected frequencies, chi-square value, and degrees of freedom (df = 1). We find X^2 = 0.04. With a p-value of 0.84 > 0.05, we fail to reject H0. There's no significant association between exam preference and gender.
In both examples, interpreting contingency tables involves calculating expected frequencies, chi-square values, p-values, and odds ratios (or relative risks). A significant p-value (less than the chosen significance level, typically 0.05) indicates a significant association between the variables.
To enhance your understanding, practice solving more contingency table examples from your textbook or online resources. Familiarize yourself with calculating expected frequencies, chi-square values, and interpreting p-values. This will help you make well-informed decisions when analyzing real-world data, assessing relationships between variables, and drawing meaningful conclusions.