Final exam – You should know:

Confidence Intervals for a population mean , population proportion, the difference between two populations means and the
population proportions, One- sided confidence bounds - using for hypotheses testing

Testing hypotheses about a population mean, a population proportion, the difference between two population means and proportions
(using normal distribution). You should know how to use both methods to make a decision – critical value approach and p-value, type
I error and type II error, the power of the test , connection between hypotheses testing and a confidence intervals. 9.1- 9.7

Small sample inferences concerning one population mean (confidence interval and test of hypotheses) and two means 10.1-10.5 and
10.8 and testing the equality of variances – Chapter 10.7 (not Confidence Interval)

The analysis of variance – 11.1- 11.6 and 11.11 (one way Anova, checking assumptions , estimating a population mean, estimating a
difference between two population means , looking at the Minitab or R output and determine which one means are different.

Linear regression and correlation – Ch12 .1-12.7- we didn't cover the hypothesis test about a population correlation

Question 1

The following 10 observations are interest rates on unpaid balances on credit cards for a department store: 10.4, 10.1, 9.5, 10.5, 10.6,
9.3, 9.9, 10.7, 9.5, and 10.0.

a)Find the mean and standard deviation of these data (you will not have to do on the exam

b) Calculate the test statistics and specify the rejection region test Ho:µ=10.5 vs Ha:µ<10.5 . Use α=0.01

c)Find a 99% confidence interval for the population mean µ , and explain how t use it for testing Ho:µ=10.5 vs Ha:µ<10.5 Use α=0.01
 𝑠𝑠
99% UCB : 𝑥𝑥̅ + 𝑡𝑡𝑛𝑛−1,𝛼𝛼 = 10.05+ (2.821)(0.4994/√10)=10.495
√𝑛𝑛

I am 99% confident that µ≤10.495 , so µ≤10.05 .

Question 2

a) Is it reasonable to assume that the underlying variances are equal?

b) Using the information from the previous question, are you willing to conclude that there is a significant difference in the mean
numbers of uncontaminated eggplants for the two disinfectants tested?

Question 3
a) Perform the appropriate test of hypothesis to determine whether there is a significant difference, on the average, in the price of tools
between the two stores. Use α=0.05

b.)Find a 95% Confidence interval for the difference ,on the average, in the price of tools between the two stores. Based on this interval,
can one conclude there is a significant difference in the price of tools between the two stores.

Question 4
A study was conducted to measure the growing presence of women in the labor force in 19 cities in the United States between 1968 and
1972. Use Minitab output to answer the following questions:
Are the two samples independent? Explain
Do you think the data provide sufficient evidence to conclude that the labor force participation rate of women has increased?

Question 5
A customer service representative was interested in comparing the average time (in minutes) customers are placed on hold when calling
Southern California Edison and Southern California Gas companies. The representative obtained two independent samples and
calculated the following summary information: Assume populations are normal.

Southern Cal Edison Southern Cal Gas

Sample size 9 12
Sample mean 3.2min 2.8 min
Sample standard deviation 0.5 min 0.7 min
Perform the appropriate test of hypothesis using α=0.05 , to determine whether there is a significant difference in average time a
customer is on hold between two companies.
Estimate the difference in mean waiting time for the two companies with a 95% confidence interval.

Question 6

Two soft drink machines dispense liquids of 10 ounces on average. A sample size of 10 drinks was obtained from each machine and the
sample standard deviations were computed to be s1-1.87 ounces and s2=1.25 ounces.
Perform the appropriate test at α=0.05 to see whether the two machines are equally consistent(i.e equally variable) in the
dispensing of the liquid.
Question 7

a) Does the plot suggest any effect of the design type on the time spent
watching it?
Answer: The plot would suggest that there actually two groups of design
type that affect the time spent watching them. They are A=B, and C=D=E.

b) Is the distribution of the time spent watching figures of type E is symmetric or skewed?
Answer: The distribution seems to be slightly skewed to the left, since the
median is nearer the last quartile, and there is only one whisker
4.Is there significant evidence tliat t11e design type affects the time spent watching it?
Answer: The p-value is 0.002, thus the null hypothesis tliat tl1e mean time in tl1e five
groups are equal can be rejected.
Or use F test F= MST/MSE= 11.22/1.93= 5.82
Leta= 0.05
Decision• Reject Ho ,ifF calc > F o.o5,dfl=4,df2=25,=2.76
Reject Ho at a= 0.05 level ,since 5.82 > 2.76

5.Write down the estimate oft11e population standard deviation cr.

Answer: The estin1ate ofs is Pooled StDev = 1.388.

6.Compute a 95% confidence interval for the time spent watching a design oftype A.

Answer: The 95% confidence interval is

1.388
X±fatl
r =10.650±2.06·
·S/vn .J6 =(9.482,11.818)

7.0n the basis ofthe confidence interval computed by Minitab, do you think one c.an
conclude that there is not a significant difference benveen tl1e time spent watching
designs of type A or B?

A nswPI': ThP. two intP.n·als arP. ov�rl�pping, so thP.rP. is not mnc.h <liff�rP.nc.� hP.1:WP.P.n thP.
two means.

(x., - X8 ±t", Js 1 (11 n, + 1/n2 ) = (10.650 -11.050) ±2.06J1.93(1/6 + 1/6) =

) 2 •

- 0.4 ± 1.65 = (-2.05.1.25)

•
Question 8

An experiment was conducted to observe the effect of an increase in temperature on the potency of an antibiotic. Three 1-ounce portions
of antibiotic were stored for equal lengths of time at each of these temperatures:30°, 50°, 70° 𝑎𝑎𝑎𝑎𝑎𝑎 90°.The potency readings
observed at each temperature of the experiment period are listed here:
Question 9. (check assumptions)(random sample , counts)

In a telephone poll of n = 1, 262 New York voters 795 or 63% of voters surveyed said the Port Authority of NY and NJ should rebuild the World
Trade Center in some form. Do these data provide sufficient evidence to indicate that a majority of New York voters would like to see the New York
World Trade Center rebuilt?

Let p be the proportion of New York voters who think that the World Trade Center should be rebuilt in some form. The hypothesis to be
tested is

=H 0 : p .5 versus H a : p > .5

and the test statistic is

pˆ − p0 .62995 − .5
=z = = 9.233
p0 q0 .5 (.5 )
n 1262

The p-value is P ( z > 9.233) ≈ 0 and H0 is rejected. There is sufficient evidence to indicate that a majority of New York voters want
to see the World Trade Center rebuilt.