04/26 統計學實習課

CH12.1 習題

施映全
[email protected]
 CH12.1
 多獨立母體比例檢定 ( 卡方同質性檢定 )

Not all population proportions are equal

• 檢定統計量： ( 補充公式 )
：第 i 列第 j 欄的觀察值個數
：為真下第 i 列第 j 欄的觀察值個數
( 列為類別變數，欄為母體 )
• 自由度為， r 為類別變數的數量
 多重比較 (Multiple Comparisons Procedure)
• 同時檢定兩兩母體比例是否相同
• 母體比例差需取絕對值：
• 臨界值：
• ，拒絕，兩母體比例有顯著差異
1. Use the sample data below to test the hypotheses

Not all population proportions are equal

where is the population proportion of Yes responses for population i. Using a .05
level of significance, what is the p-value and what is your conclusion?

Populations
Response 1 2 3

Yes 150 150 96

No 100 150 104
算出每列每欄的總數 (Total) ：
 算出為真下的機率
150+150 +96 3 9 6
𝑝= = =0.528
250+ 300+200 7 5 0

算出， e.g.
 算出

2
𝜒 =3.77+ 4.22=7.99 ， 𝑑𝑓 =(2 −1)(3 − 1)=2
查表後可得介於
拒絕
2. Reconsider the observed frequencies in exercise 1

a. Compute the sample proportion for each population.

150
𝑝 1= = 0.6
250
150
𝑝 2= =0.5
300
96
𝑝3 = =0.48
200

b. Use the multiple comparison procedure to determine which population

proportions differ significantly. Use a .05 level of significance.
兩兩母體進行比較， 先算出，再算出 CV ，最後兩者進行比較

，只有母體 1 和母體三的母體比例有顯著差異
4. Electronic Component Supplier Quality Comparison. Benson Manufacturing is
considering ordering electronic components from three different suppliers. The
suppliers may differ in terms of quality in that the proportion or percentage of
defective components may differ among the suppliers. To evaluate the
proportion of defective components for the suppliers, Benson has requested a
sample shipment of 500 components from each supplier. The number of
defective components and the number of good components found in each
shipment are as follows.

a. Formulate the hypotheses that can be used to test for equal proportions of
defective components provided by the three suppliers.

、 、 全然相等
b. Using a .05 level of significance, conduct the hypothesis test. What is the p-value
and what is your conclusion?
算出
e.g.
算出每列每欄的總數 (Total) ：

算出

查表後可得於
拒絕，三家供應商產品
的不良率顯著不相同
c. Conduct a multiple comparison test to determine if there is an overall best supplier
or if one supplier can be eliminated because of poor quality.
15
𝑝 1= =0. 0 3
500
20
𝑝 2= = 0.04
500
40
𝑝3 = =0.08
500

兩兩母體進行比較， 先算出，再算出 CV ，最後兩者進行比較

結果顯示 C 與 A 、 B 母體皆有顯著差異， A 、 B 母體間則無，代表

Benson Manufacturing 應該只考慮向 A 、 B 兩家供應商下訂單
5. Research Classification of Higher Education. The Carnegie Classification of
Institutes of Higher Education categorizes colleges and universities on the basis
of their research and degree-granting activities. Universities that grant doctoral
degrees are placed into one of three classifications: moderate research activity,
higher research activity, or highest research activity. The Carnegie classifications
for public and not-for-profit private doctoral degree-granting universities are
summarized in the following table.

Test the hypothesis that the population proportions of public universities are
equal in each Carnegie classification category. Use a .05 level of significance.
What is the p-value and what is your conclusion?
3 8+ 7 6+ 8 1
、 、 全然相等
𝑝= =0.6132
3 8 +5 8+ 7 6+ 3 1+8 1+3 4

查表後可得於
拒絕，三種等級
2
中公立學校的比例顯著不完全相同
( 𝑓 𝑖𝑗 − 𝑒𝑖𝑗 )
𝜒 =∑
2
=27.4 ， 𝑑𝑓 =(2 −1)(3 −1)=2
𝑒
6. Error Rates in Tax Preparation. A tax preparation firm is interested in comparing
the quality of work at two of its regional offices. The observed frequencies
showing the number of sampled returns with errors and the number of sampled
returns that were correct are as follows.

a. What are the sample proportions of returns with errors at the two offices?
35
𝑝 1= =0.14
2 50
27
𝑝 2= =0.09
300
b. Use the chi-square test procedure to see if there is a significant difference
between the population proportion of error rates for the two offices. Test
the null hypothesis H0: p1 = p2 with a .10 level of significance. What is the p-
value and what is your conclusion? Note: We generally use the chi-square
test of equal proportions when there are three or more populations, but
this example shows that the same chi- square test can be used for testing
equal proportions with two populations.
3 5 +2 7
𝑝= =0 .1127
3 5+ 21 5+ 27 +2 7 3

2
( 𝑓 𝑖𝑗 − 𝑒𝑖𝑗 )
𝜒 =∑
2
=3.4 ， 𝑑𝑓 =(2 −1)(2 −1)=1
𝑒𝑖𝑗
查表後可得於
拒絕，兩地辦公室的錯誤率
顯著不同
c. In the Section 10.2, a z test was used to conduct the above test. Either a test
statistic or a z test statistic may be used to test the hypothesis. However, when
we want to make inferences about the proportions for two populations, we
generally prefer the z test statistic procedure. Refer to the Notes and
Comments at the end of this section and comment on why the z test statistic
provides the user with more options for inferences about the proportions of
two populations.
使用卡方檢定兩母體比例時，其自由度為
當有一個標準常態分配 z ，將其平方後可以得到自由度為 1 的卡方分配
() ，因此在檢定兩母體比例時，檢定統計量永遠等於，
兩者會有著相同的 P-value 。但是使用卡方檢定有所限制，他只能進行
雙尾檢定，而使用 z 分配則可以進行雙尾及單尾檢定，使用上較為自由。
8. Supplier Quality: Three Inspection Outcomes. The Ertl Company is well known
for its high-quality die-cast metal alloy toy replicas of tractors and other farm
equipment. As part of a periodic procurement evaluation, Ertl is considering
purchasing parts for a toy tractor line from three different suppliers. The parts
received from the suppliers are classified as having a minor defect, having a
major defect, or being good. Test results from samples of parts received from
each of the three suppliers are shown below. Note that any test with these
data is no longer a test of proportions for the three supplier populations
because the categorical response variable has three outcomes:
minor defect, major defect, and good.

Using the data above, conduct a hypothesis test to determine if the distribution
of defects is the same for the three suppliers. Use the chi-square test
calculations as presented in this section with the exception that a table with r
rows and c columns results in a chi-square test statistic with (r – 1)(c – 1)
degrees of freedom. Using a .05 level of significance, what is the p-value and
what is your conclusion?
 三家供應商不良品的分配相同
三家供應商不良品的分配不全然相同

算出每列每欄的總數 (Total) ： 算出
 算出

2
𝜒 =2.12+3.43+ 0.15=5.7 ， 𝑑𝑓 =( 𝑟 −1 ) ( 𝑘− 1 )=( 3 − 1 )( 3 − 1 )=4

查表後可得於
不拒絕，三家供應商不良品的分配沒有顯著不同
End