8.

3
DEFINE EACH OF THE FOLLOWING:
a. Type I error b. Type II error c.  d. 
1. Type I error (型 1 誤): Reject H0 (Null hypotheses) when it is true.
2. Type II error (型 2 誤): Failing to reject H0 when it is false.
3. α : Significance level (顯著水準), 型 I 誤發生機率可以容忍的上限.
4. β : 型 II 誤發生的機率.
8.15
Explain what a p-value is, and explain how it is used to test a hypothesis.
1) At observed level of significance 檢定犯型 I 誤發生的機率.
2) We reject H0 in favor of H1 at level of significance level α if and
only if p-value is less than α.
a. p-value is < 0.10 → have some evidence that H0 is false.
b. p-value is < 0.05 → have strong evidence that H0 is false.
c. p-value is < 0.01 → have very strong evidence that H0 is false.
d. p-value is < 0.001 → have extremely strong evidence that H0 is false
8.31
THE BANK CUSTOMER WAITING TIME CASE
Letting  be the mean waiting time under the new system, we found in Exercise
8.8(page 304) that we should test H 0 :   6 versus H a :   6 in order to attempt to
provide evidence that  is less than six minutes. The random sample of 100 waiting
times yields a sample mean of x  5.46 minutes and a sample standard deviation of
s  2.475 . Moreover, Figure 8.6 gives the MINITAB output obtained when we use
the waiting time data to test H 0 :   6 versus H a :   6 .
On this output the label “SE Mean,” which stands for “the standard error of the
mean,” denotes the quantity s n , and the label “Z” denotes the calculated test
statistic.
a. Use rejection points to test H 0 vs H a at each of
  0.10,0.05,0.01 and 0.0001
※ Ho: μ≧6; H1: μ< 6, n=100, x = 5.46, s = 2.475
b. Calculate the p-value and verify that it equals 0.0146(0.015 rounded), as shown on
the MINITAB output. Use the p-value to test H 0 vs H a at each of
  0.10,0.05,0.01 and 0.0001 .
x  0
※ z s = (5.46-6)/(2.475/ 100 ) = -2.18, 查表 P-value = 0.0146
n
c. How much evidence is there that the new system has reduced the mean waiting
time to below six minutes?
※ p-value < α = 0.1, 0.05 → reject Ho.
※ For P-value < 0.05, we have strong evidence that H0 is false
Figure 8.6 MINITAB Output of the Test of H 0 :   6 versus H a :   6 in the Bank
Customer Waiting Time Case
Test of mu = 6.000 vs mu < 6.000. The assumed sigma = 2.47
Variable N Mean StDev SE Mean Z P
WaitTime 100 5.460 2.475 0.247 -2.18 0.015
8.69
Suppose we test H 0 : p  0.3 vesus H a : p  0.3 and that a random sample of n =
100 gives a sample proportion pˆ  0.20
a. Test H 0 vs H a at the 0.01 level of significance by using a rejection point.
What do you conclude?
※ H 0 : P0  0.3; H 1 : P0  0.3
※ n= 100; p̂ =0.2
 (0.2  0.3)
p  p0  2.18
※ z = 0.3  0.7
p0 (1  p0 ) / n
100
※ α = 0.01; Zα/2 = ±2.575, → do not reject Ho.
b. Find the p-value for this test
※ two-sided; 查表 P-value = 2×(0.5-0.4854) = 0.0292
c. Use the p-value to test H 0 vs H a by setting  equal to 0.10, 0.05, 0.001.
What do you conclude at each value of  ?
※ p-value < α = 0.1, 0.05 → reject Ho; do not reject α = 0.01, 0.005
8.89
A consumer electronics firm has developed a new type of remote control button that is
designed to operate longer before becoming intermittent. A random sample of 35 of
the new buttons is selected and each is tested in continuous operation until becoming
intermittent. The resulting lifetimes are found to have a sample mean of x  1,241.2
hours and a sample standard deviation of s  110 .8
a. Independent tests reveal that the mean lifetime (in continuous operation) of the
best remote control button on the market is 1,200 hours. Letting  be the mean
lifetime of the population of all remote control buttons that will or could
potentially be produced, set up the null and alternative hypotheses needed to
attempt to provide evidence that the new button’s mean lifetime exceeds the mean
lifetime of the best remote button currently on the market.
(1) Ho: μ≦1200
(2) H1: μ > 1200.
b. Using the previously given sample results, test the hypotheses you set up in part a
by setting  equal to 0.10, 0.05, 0.01, and 0.001. What do you conclude for each
value of  ?
(1) n=35, x= 1241.2, s= 110.8
x  0
(2) Z= z  s =(1241.2-1200)/(110.8/ √ 35) = 2.20
n
(3) ∴ 查表 p-value =0.0139 , reject Ho at α = 0.1, 0.05, Do not reject Ho at
α = 0.01, 0.005.
c. Suppose that x  1,241.2 and s  110.8 had been obtained by testing a sample
of 100 buttons. Test the hypotheses you set up in part a by setting  equal to
0.10, 0.05, 0.01, and 0.001. Which sample (the sample of 35 or the sample of 100)
gives a more statistically significant result? That is , which sample provides
stronger evidence that H a is true? for n=100,
x  0
(1) Z= z  s =(1241.2-1200)/(110.8/ √ 100) = 3.718
n
(2) ∴ 查表 p-value < 0.001→ reject Ho at all the value of α.
(3) That is, n=100 provides stronger evidence that H1 is true
d. If we define practical importance to mean that  exceeds 1,200 by an amount
 that would be clearly noticeable to most consumers, do you think that the result
has practical importance?
Explain why the samples of 35 and 100 both indicate the same degree of practical
importance.
※ Both p-value of n=35 and 100 are less than 0.05, have quite strong
evidence to reject Ho
e. Suppose that further research and development effort improves the new remote
control button and that a random sample of 35 buttons gives x  1,524.6 hours
and s  102.8 hours. Test your hypotheses of part a by setting  equal to 0.10,
0.05, 0.01, and 0.001.
(1) Do we have a highly statistically significant result? Explain.
(2) Do you think we have a practically important result? Explain.
1. X=1524.6, s=102.8, n=35
x  0
2. Z= z  s =(1524.6-1200)/(110.8/ √ 35) = 18.68
n
3. ∴ 查表 p-value << 0.001→ reject Ho at all the value of α.
4. Yes, for p-value << 0.001
5. Maybe, mean value of x is far bigger than 1200