MATHS ASSIGNMENT
STATISTICAL INFERENCE
MATH 1281-01
UNIT 2
HYPOTHESIS TESTING FOR PROPORTIONS
Part 1
Question 1a
Context:
Sample size: n = 441
Sample proportion: p̂ = 0.38
Claim: Fewer than 50% of adults avoid college due to affordability.
Significance level: α = 0.05
Hypotheses:
H₀: p = 0.50
Hₐ: p < 0.50
Conditions
Independence: The sample is random and less than 10% of the population (441 < 10% of all
U.S. adults).
Success-Failure:
np₀ = 441 × 0.50 = 220.5
n(1 − p₀) = 441 × 0.50 = 220.5
1 Both > 10, so the normal approximation is valid (Diez et al., 2019).
z=np0(1−p0)p^−p0=4410.5⋅0.50.38−0.50≈−5.04
z=(p^−p0p0)/sqrt{(1−p0)}n={{0.38 - 0.50}}/{{sqrt{\frac{{0.5 . 0.5}}{441}}}} =−5.04
Z=−5.04
P-value:
For z = -5.04, p-value ≈ 0.0000005 (based on z-distribution tables or JASP software).
Conclusion:
Since the p-value is much smaller than α = 0.05, we reject the null hypothesis. There is strong
evidence that fewer than 50% of adults avoid college due to affordability (Diez et al., 2019).
Question 1b
Goal: Find the required sample size for a 1.5% margin of error at a 90% confidence level.
Using the formula:
ME=z∗⋅sqrt {p(1−p)/n}⇒n={(p(1−p)(z∗)^2)/ME^2}
Assume p = 0.5 for maximum variability.
z* for 90% = 1.645 (Diez et al., 2019):
n={(0.25⋅(1.645) ^2)/(0.0152)} =3,005
Answer: A sample size of approximately 3,005 is recommended.
Part 2
Question 2a
Given:
Texas: n₁ = 13,270, p̂ ₁ = 0.07
Dallas: n₂ = 4,681, p̂ ₂ = 0.068
Confidence level: 95%
Conditions:
Independence: Random samples and sample sizes < 10% of the populations.
Success-Failure:
Texas: 929 successes, 12,341 failures
Dallas: 318 successes, 4,363 failures
All > 10, so conditions met (Diez et al., 2019).
Confidence Interval Formula:
CI=(p^1−p^2)±z∗⋅ sqrt{(p^1(1−p^1))/n1)+((p^2(1−p^2)/n2)}
=0.002±1.96⋅ sqrt (0.00000491+0.00001352) =0.002±1.96⋅0.00429=0.002±0.0084⇒
(−0.0064,0.0104)
Interpretation:
We are 95% confident the true difference in sleep deprivation rates between Texas and
Dallas residents is between -0.64% and 1.04%. Since 0 is in this interval, we conclude
that the difference is not statistically significant (Diez et al., 2019).
Question 2b
Hypotheses:
H₀: p₁ = p₂
Hₐ: p₁ ≠ p₂
Pooled Proportion:
p^=(929+318)/(13270+4681) = 0.0695
Test Statistic:
z=(0.07−0.068)/ sqrt{(0.0695⋅0.9305⋅(1/13270+1/4681)} = 0.47
P-value:
Using standard normal distribution, p-value ≈ 0.638.
Conclusion:
Since p > 0.05, we fail to reject the null hypothesis. There is not enough evidence to conclude a
significant difference in sleep deprivation rates between Texas and Dallas residents (Diez et al.,
2019).
References
Diez, D. M., Barr, C. D., & Çetinkaya-Rundel, M. (2019). OpenIntro statistics (4th ed.).
OpenIntro. https://www.openintro.org/book/os/
