Skip to content
AP Statistics · Inference for Categorical Data: Proportions

Test of homogeneity

Test of homogeneity appears in 3 reviewed AP Statistics questions and sits in Inference for Categorical Data: Proportions. Below are worked examples showing exactly how the exam tests it, with the answer marked and every distractor explained.

How Test of homogeneity is tested

Example 1Medium
A chi-square test of homogeneity is conducted to compare the distribution of preferred social media platforms among three age groups. The data are organized in a 3 x 4 table (3 age groups, 4 platforms). The calculated chi-square statistic is 18.7. Using a significance level of 0.01, what conclusion can be drawn? (The chi-square critical value for df = 6 at alpha = 0.01 is 16.812.)
  1. AReject H0; there is convincing evidence that preferred-platform distributions differ across age groupsCorrect
  2. BFail to reject H0; there is insufficient evidence of different distributions across age groups
  3. CReject H0; there is convincing evidence that platform preference and age group are independent
  4. DFail to reject H0; the chi-square statistic exceeds the critical value but the sample size is too small

Why A is right

The degrees of freedom are (3 - 1)(4 - 1) = 6. The chi-square statistic of 18.7 exceeds the critical value of 16.812 at alpha = 0.01. Therefore, we reject H0 and conclude there is convincing evidence that the distribution of preferred platforms differs among the three age groups.
Why the other 3 choices miss
B
Incorrect because the chi-square statistic of 18.7 exceeds the critical value of 16.812, so there is sufficient evidence to reject H0.
C
Incorrect because rejecting H0 means we conclude the distributions are different (not independent). Independence would be the null hypothesis claim, which we are rejecting.
D
Incorrect because when the test statistic exceeds the critical value, we reject H0 regardless of sample size concerns. The conditions should have been checked before conducting the test.

Studied alongside

Other concepts from Inference for Categorical Data: Proportions.