Sample size: n = 400
Number of supporters: x = 192
Sample proportion: p̂ = 0.48
MATH 216: Statistical Thinking
Time Allocation: 15 minutes total
A political poll tests if candidate support differs from the historical baseline of 50%. Survey of 400 voters found 192 supporters.
Sample size: n = 400
Number of supporters: x = 192
Sample proportion: p̂ = 0.48
R proportion test output:
1-sample proportions test without continuity correction
data: x out of n, null probability p_0
X-squared = 0.64, df = 1, p-value = 0.4237
alternative hypothesis: true p is not equal to 0.5
95 percent confidence interval:
0.433 0.527
sample estimates:
p
0.48
Questions: - State the null and alternative hypotheses - What is the statistical decision at α = 0.05? - Interpret the confidence interval
A manufacturer tests if their new process reduces defect rate below the historical 10%. In a batch of 500 products, 40 were defective.
Sample size: n = 500
Defective products: x = 40
Defect rate: p̂ = 0.08
R proportion test output:
1-sample proportions test without continuity correction
data: x out of n, null probability p_0
X-squared = 2.2222, df = 1, p-value = 0.068
alternative hypothesis: true p is less than 0.1
95 percent confidence interval:
0.0000000 0.096
sample estimates:
p
0.08
Questions: - State the null and alternative hypotheses - What is the statistical decision at α = 0.05? - What practical recommendation would you make?
A company tests if customer satisfaction exceeds 80%. Survey of 250 customers found 210 satisfied.
Sample size: n = 250
Satisfied customers: x = 210
Satisfaction rate: p̂ = 0.84
R proportion test output:
1-sample proportions test without continuity correction
data: x out of n, null probability p_0
X-squared = 2.5, df = 1, p-value = 0.057
alternative hypothesis: true p is greater than 0.8
95 percent confidence interval:
0.795 1.000
sample estimates:
p
0.84
Questions:
A clinical trial tests if a new treatment has a success rate different from the standard treatment’s 65% success rate. In a study of 300 patients, 195 showed improvement.
Sample size: n = 300
Patients improved: x = 195
Success rate: p̂ = 0.65
R proportion test output:
1-sample proportions test without continuity correction
data: x out of n, null probability p_0
X-squared = 0, df = 1, p-value = 1
alternative hypothesis: true p is not equal to 0.65
95 percent confidence interval:
0.596 0.704
sample estimates:
p
0.65
Questions: