Download as pdf or txt
Download as pdf or txt
You are on page 1of 2

v.

Case Calculators – week 2A


A factory has the choice between two methods of producing calculators (methods 1 and 2).
In a random sample of 80 calculators made by method 1, 16 were defective, while in a
random sample of 60 calculators made by method 2, 21 were defective.
a. Test, using 𝛼𝛼 = 5%, whether there is a difference between the two methods with
respect to the percentage of defective calculators.
b. Because method 1 is more expensive than method 2, management wants to know
whether the percentage of defectives for method 2 is more than 3%-points higher
than that for method 1. Test this using 𝛼𝛼 = 5%.
c. Determine a 90%-confidence interval for the difference in percentages of defectives
for the two methods.

a. Hypothesis test
Conditions and assumptions
• Random samples, independent
• Available: nominal (values are: defective or not defective)
• Required: nominal (or higher level)
• 𝑛𝑛1 ∙ 𝑝𝑝̂1 ≥ 5, 𝑛𝑛1 ∙ (1 − 𝑝𝑝̂1 ) ≥ 5, 𝑛𝑛2 ∙ 𝑝𝑝̂2 ≥ 5, 𝑛𝑛2 ∙ (1 − 𝑝𝑝̂2 ) ≥ 5
Hypotheses
𝐻𝐻0 ∶ 𝑝𝑝1 − 𝑝𝑝2 = 0 and 𝐻𝐻1 ∶ 𝑝𝑝1 − 𝑝𝑝2 ≠ 0
1: production method 1, 2: production method 2
Test statistic and its distribution
𝑥𝑥1 = 16 ≥ 5, 𝑛𝑛1 − 𝑥𝑥1 = 80 − 16 ≥ 5, 𝑥𝑥2 = 21 ≥ 5, 𝑛𝑛2 − 𝑥𝑥2 = 60 − 21 ≥ 5
and 𝐻𝐻0 ∶ 𝑝𝑝1 − 𝑝𝑝2 = 𝐷𝐷 with 𝐷𝐷 = 0, so we use:
(𝑝𝑝̂1 − 𝑝𝑝̂2 ) − 0 𝑛𝑛1 𝑝𝑝̂1 + 𝑛𝑛2 𝑝𝑝̂ 2 𝑥𝑥1 + 𝑥𝑥2
𝑍𝑍 = ~ 𝑁𝑁(0, 1) with 𝑝𝑝̂ = =
1 1 𝑛𝑛1 + 𝑛𝑛2 𝑛𝑛1 + 𝑛𝑛2
�𝑝𝑝̂ (1 − 𝑝𝑝̂ ) � + �
𝑛𝑛1 𝑛𝑛2
Rejection region:
𝛼𝛼 = 5% two sided ⟹ 𝑅𝑅𝑅𝑅: 𝑧𝑧 ≤ −𝑧𝑧𝑐𝑐𝑐𝑐𝑐𝑐𝑐𝑐 = −𝑧𝑧0.025 = −1.96 ∨ 𝑧𝑧 ≥ 𝑧𝑧𝑐𝑐𝑐𝑐𝑐𝑐𝑐𝑐 = 1.96
Outcome:
𝑥𝑥1 16 𝑥𝑥2 21 16 + 21 37
𝑝𝑝̂1 = = = 0.20 and 𝑝𝑝̂ 2 = = = 0.35 and 𝑝𝑝̂ = = = 0.264 ⟹
𝑛𝑛1 80 𝑛𝑛2 60 80 + 60 140
(0.20 − 0.35) − 0 −0.15
𝑧𝑧𝑜𝑜𝑜𝑜𝑜𝑜 = = = −1.99
0.0753
�0.264(1 − 0.264) � 1 + 1 �
80 60
Confrontation:
𝑧𝑧𝑜𝑜𝑜𝑜𝑜𝑜 lies in the rejection region, so reject the null-hypothesis.
Conclusion:
Given this sample and a significance level of 0.05, there is sufficient evidence to infer that
there is a difference in percentage of defective products, between production methods 1
and 2.

1
b. Hypothesis test
Conditions and assumptions
• Nominal data
• Random samples, independent
• 𝑛𝑛1 ∙ 𝑝𝑝̂1 ≥ 5, 𝑛𝑛1 ∙ (1 − 𝑝𝑝̂1 ) ≥ 5, 𝑛𝑛2 ∙ 𝑝𝑝̂2 ≥ 5, 𝑛𝑛2 ∙ (1 − 𝑝𝑝̂2 ) ≥ 5
Hypotheses
𝐻𝐻0 ∶ 𝑝𝑝2 − 𝑝𝑝1 = 0.03 and 𝐻𝐻1 ∶ 𝑝𝑝2 − 𝑝𝑝1 > 0.03
or: 𝐻𝐻0 ∶ 𝑝𝑝1 − 𝑝𝑝2 = −0.03 and 𝐻𝐻1 ∶ 𝑝𝑝1 − 𝑝𝑝2 < −0.03
1: production method 1, 2: production method 2
Test statistic and its distribution
𝑥𝑥1 = 21 ≥ 5, 𝑛𝑛1 − 𝑥𝑥1 = 60 − 21 ≥ 5, 𝑥𝑥2 = 16 ≥ 5, 𝑛𝑛2 − 𝑥𝑥2 = 80 − 16 ≥ 5
and 𝐻𝐻0 ∶ 𝑝𝑝1 − 𝑝𝑝2 = 𝐷𝐷 with 𝐷𝐷 ≠ 0, so we use:
(𝑝𝑝̂1 − 𝑝𝑝̂ 2 ) − 𝐷𝐷 𝑥𝑥1 𝑥𝑥2
𝑍𝑍 = ~ 𝑁𝑁(0, 1) with 𝑝𝑝̂1 = and 𝑝𝑝̂ 2 =
𝑝𝑝̂1 (1 − 𝑝𝑝̂1 ) 𝑝𝑝̂ 2 (1 − 𝑝𝑝̂2 ) 𝑛𝑛1 𝑛𝑛2
� +
𝑛𝑛1 𝑛𝑛2
Rejection region:
𝛼𝛼 = 5% one sided ⟹ 𝑅𝑅𝑅𝑅: 𝑧𝑧 ≤ −𝑧𝑧𝛼𝛼 = −1.645
Outcome:
𝑥𝑥1 16 𝑥𝑥2 21
𝑝𝑝̂1 = = = 0.20 and 𝑝𝑝̂ 2 = = = 0.35 ⟹
𝑛𝑛1 80 𝑛𝑛2 60
(0.20 − 0.35) − (−0.03) −0.12
𝑧𝑧𝑜𝑜𝑜𝑜𝑜𝑜 = = = −1.58
0.0761
�0.20 ∙ 0.80 + 0.35 ∙ 0.65
80 60
Confrontation:
𝑧𝑧𝑜𝑜𝑜𝑜𝑜𝑜 does not lie in the rejection region, so do not reject the null-hypothesis.
Conclusion:
Given this sample and a significance level of 0.05, there is insufficient evidence to infer that
the percentage of defective products for method 2 is more than 3% higher than for
method 1.

c. 90%-confidence interval
𝛼𝛼 = 10%

𝑝𝑝̂1 (1 − 𝑝𝑝̂1 ) 𝑝𝑝̂1 (1 − 𝑝𝑝̂2 )


𝑝𝑝1 − 𝑝𝑝2 = 𝑝𝑝̂1 − 𝑝𝑝̂ 2 ± 𝑧𝑧𝛼𝛼 ∙ � +
2 𝑛𝑛1 𝑛𝑛2

= 0.20 − 0.35 ± 1.645 ∙ 0.0761


= −0.15 ± 0.125
⟹ −0.275 < 𝑝𝑝1 − 𝑝𝑝2 < −0.025 (90% confidence)

You might also like