T-test for one population

Mean
Dr.Srilakshminarayana.G
An automobile manufacturer substitutes a different engine in cars that were known
to have an average miles-per-gallon rating of 31.5 on the highway. The
manufacturer wants to test whether the new engine changes the miles-per-gallon
rating of the automobile model. A random sample of 100 trial runs gives sample
mean= 29.8 miles per gallon and s=6.6 miles per gallon. Using the 0.05 level of
significance, is the average miles-per-gallon rating on the highway for cars using the
new engine different from the rating for cars using the old engine?
A certain commodity is known to have a price that is stable through time
and does not change according to any known trend. Price, however, does
change from day to day in a random fashion. If the price is at a certain
level one day, it is as likely to be at any level the next day within some
probability bounds approximately given by a normal distribution. The
mean daily price is believed to be $14.25. To test the hypothesis that the
average price is $14.25 versus the alternative hypothesis that it is more
than $14.25, a random sample of 16 daily prices is collected. The results
are sample mean= $16.50 and s=$4.2. Using level of significance 0.05, can
you reject the null hypothesis?
Many recent changes have affected the real estate market. A study was undertaken
to determine customer satisfaction from real estate deals.

Suppose that before the changes, the average customer satisfaction rating, on a
scale of 0 to 100, was 77. A survey questionnaire was sent to a random sample of
50 residents who bought new plots after the changes in the market were instituted,
and the average satisfaction rating for this sample was found to be 84; the sample
standard deviation was found to be s=28. Use a level of significance of your choice,
and determine whether statistical evidence indicates a change in customer
satisfaction. If you determine that a change did occur, state whether you believe
customer satisfaction has improved.
A study was undertaken to evaluate how stocks are affected by being
listed in the Standard & Poor’s 500 Index. The aim of the study was to
assess average excess returns for these stocks, above returns on the
market as a whole. The average excess return on any stock is zero
because the “average” stock moves with the market as a whole. As part
of the study, a random sample of 13 stocks newly included in the S&P 500
Index was selected. Before the sampling takes place, we allow that
average “excess return” for stocks newly listed in the Standard & Poor’s
500 Index may be either positive or negative; therefore, we want to test
the null hypothesis that average excess return is equal to zero versus the
alternative that it is not zero. If the excess return on the sample of 13
stocks averaged 3.1% and had a standard deviation of 1%, do you believe
that inclusion in the Standard & Poor’s 500 Index changes a stock’s excess
return on investment, and if so, in which direction? Explain. Use level of
significance 0.05.
In controlling the quality of a new drug, a dose of medicine is supposed to contain an average
of 247 parts per million (ppm) of a certain chemical. If the concentration is higher than 247
ppm, the drug may cause some side effects; and if the concentration is below 247 ppm, the
drug may be ineffective. The manufacturer wants to check whether the average concentration
in a large shipment is the required 247 ppm or not. A random sample of 60 portions is tested,
and the sample mean is found to be 250 ppm and the sample standard deviation 12 ppm. Test
the null hypothesis that the average concentration in the entire large shipment is 247 ppm
versus the alternative hypothesis that it is not 247 ppm using a level of significance 0.05. Do the
same using level of significance 0.01. What is your conclusion? What is your decision about the
shipment? If the shipment were guaranteed to contain an average concentration of 247 ppm,
what would your decision be, based on the statistical hypothesis test? Explain.
• The Boston Transit Authority wants to determine whether there is any need for changes in
the frequency of service over certain bus routes. The transit authority needs to know
whether the frequency of service should increase, decrease, or remain the same. The transit
authority determined that if the average number of miles travelled by bus over the routes in
question by all residents of a given area is about 5 per day, then no change will be necessary.
If the average number of miles travelled per person per day is either more than 5 or less than
5, then changes in service may be necessary. The authority wants, therefore, to test the null
hypothesis that the average number of miles travelled per person per day is 5.0 versus the
alternative hypothesis that the average is not 5.0 miles. The required level of significance for
this test is 0.05. A random sample of 120 residents of the area is taken, and the sample mean
is found to be 2.3 miles per resident per day and the sample standard deviation 1.5 miles.
Advise the authority on what should be done. Explain your recommendation. Could you state
the same result at different levels of significance? Explain.
According to Money, the average appreciation, in percent, for stocks has been 4.3%
for the five-year period ending in May 2007. An analyst tests this claim by looking
at a random sample of 50 stocks and finds a sample mean of 3.8% and a sample
standard deviation of 1.1%. Using level of significance 0.05, does the analyst have
statistical evidence to reject the claim made by the magazine?
Average total daily sales at a small food store are known to be $452.80. The store’s
management recently implemented some changes in displays of goods, order within aisles, and
other changes, and it now wants to know whether average sales volume has changed. A
random sample of 12 days shows sample mean= $501.90 and s=$65.00. Using level of
significance 0.05, is the sampling result significant? Explain.

New software companies that create programs for World Wide Web applications believe that
average staff age at these companies is 27. To test this two-tailed hypothesis, a random sample
is collected:

41, 18, 25, 36, 26, 35, 24, 30, 28, 19, 22, 22, 26, 23, 24, 31, 22, 22, 23, 26, 27, 26, 29, 28, 23, 19,
18, 18, 24, 24, 24, 25, 24, 23, 20, 21, 21, 21, 21, 32, 23, 21, 20

Test, using level of significance 0.05

A new chemical process is introduced by Duracell in the production of lithium-ion
batteries. For batteries produced by the old process, the average life of a battery is
102.5 hours. To determine whether the new process affects the average life of the
batteries, the manufacturer collects a random sample of 25 batteries produced by
the new process and uses them until they run out. The sample mean life is found to
be 107 hours, and the sample standard deviation is found to be 10 hours. Are these
results significant at the level of significance 0.05 level? Are they significant at the
level of significance 0.01 level? Explain. Draw your conclusion.
Average soap consumption in a certain country is believed to be 2.5 bars
per person per month. The standard deviation of the population is known
to be 0.8. While the standard deviation is not believed to have changed
(and this may be substantiated by several studies), the mean
consumption may have changed either upward or downward. A survey is
therefore undertaken to test the null hypothesis that average soap
consumption is still 2.5 bars per person per month versus the alternative
that it is not. A sample of size n=20 is collected and gives sample mean
2.3. The population is assumed to be normally distributed. What is the
appropriate test statistic in this case? Conduct the test and state your
conclusion. Use level of significance 0.05. Does the choice of level of
significance change your conclusion? Explain.
According to Money, which not only looked at stocks but also
compared them with real estate, the average appreciation for all real
estate sold in the five years ending May 2007 was 12.4% per year. To
test this claim, an analyst looks at a random sample of 100 real estate
deals in the period in question and finds a sample mean of 14.1% and a
sample standard deviation of 2.6%. Conduct a two tailed test using the
0.05 level of significance.

Suppose that the Goodyear Tire Company has historically held 42% of
the market for automobile tires in the United States. Recent changes in
company operations, especially its diversification to other areas of
business, as well as changes in competing firms’ operations, prompt
the firm to test the validity of the assumption that it still controls 42%
of the market. A random sample of 550 automobiles on the road shows
that 219 of them have Goodyear tires. Conduct the test at level of
significance 0.01.
The manufacturer of electronic components needs to inform its buyers
of the proportion of defective components in its shipments. The
company has been stating that the percentage of defectives is 12%. The
company wants to test whether the proportion of all components that
are defective is as claimed. A random sample of 100 items indicates 17
defectives. Use level of significance 0.05 to test the hypothesis that the
percentage of defective components is 12%.

According to Business Week, the average market value of a biotech

company is less than $250 million. Suppose that this indeed is the
alternative hypothesis you want to prove. A sample of 30 firms reveals
an average of $235 million and a standard deviation of $85 million.
Conduct the test at level of significance 0.05 and level of significance
0.01. State your conclusions.
A company’s market share is very sensitive to both its level of advertising and
the levels of its competitors’ advertising. A firm known to have a 56% market
share wants to test whether this value is still valid in view of recent
advertising campaigns of its competitors and its own increased level of
advertising. A random sample of 500 consumers reveals that 298 use the
company’s product. Is there evidence to conclude that the company’s market
share is no longer 56%, at the 0.01 level of significance?

According to a financial planner, individuals should in theory save 7% to 10%

of their income over their working life, if they desire a reasonably
comfortable retirement. An agency wants to test whether this actually
happens with people in the United States, suspecting the overall savings rate
may be lower than this range. A random sample of 41 individuals revealed
the following savings rates per year:
4, 0, 1.5, 6, 3.1, 10, 7.2, 1.2, 0, 1.9, 0, 1.0, 0.5, 1.7, 8.5, 0, 0, 0.4, 0, 1.6, 0.9,
10.5, 0, 1.2, 2.8, 0, 2.3, 3.9, 5.6, 3.2, 0, 1, 2.6, 2.2, 0.1, 0.6, 6.1, 0, 0.2, 0, 6.8
Conduct the test and state your conclusions. Use the lower value, 7%, in the
null hypothesis. Use level of significance 0.01. Interpret.
The theory of finance allows for the computation of “excess” returns, either
above or below the current stock market average. An analyst wants to
determine whether stocks in a certain industry group earn either above or
below the market average at a certain time period. The null hypothesis is
that there are no excess returns, on the average, in the industry in question.
“No average excess returns” means that the population excess return for the
industry is zero. A random sample of 24 stocks in the industry reveals a
sample average excess return of 0.12 and sample standard deviation of 0.2.
State the null and alternative hypotheses, and carry out the test at the 0.05
level of significance.

According to Fortune, on February 27, 2007, the average stock in all U.S.
exchanges fell by 3.3%. If a random sample of 120 stocks reveals a drop of
2.8% on that day and a standard deviation of 1.7%, are there grounds to
reject the magazine’s claim?
According to Money, the average amount of money that a typical person in
the United States would need to make him or her feel rich is $1.5 million. A
researcher wants to test this claim. A random sample of 100 people in the
United States reveals that their mean “amount to feel rich” is $2.3 million
and the standard deviation is $0.5 million. Conduct the test.

The U.S. Department of Commerce estimates that 17% of all automobiles on

the road in the United States at a certain time are made in Japan. An
organization that wants to limit imports believes that the proportion of
Japanese cars on the road during the period in question is higher than 17%
and wants to prove this. A random sample of 2,000 cars is observed, 381 of
which are made in Japan. Conduct the hypothesis test at level of significance
0.01, and state whether you believe the reported figure.
Airplane tires are sensitive to the heat produced when the plane taxis along
runways. A certain type of airplane tire used by Boeing is guaranteed to
perform well at temperatures as high as 125°F. From time to time, Boeing
performs quality control checks to determine whether the average maximum
temperature for adequate performance is as stated, or whether the average
maximum temperature is lower than 125°F, in which case the company must
replace all tires. Suppose that a random sample of 100 tires is checked. The
average maximum temperature for adequate performance in the sample is
found to be 121°F and the sample standard deviation 2°F. Conduct the
hypothesis test, and conclude whether the company should take action to
replace its tires.

An advertisement for Qualcomm appearing in various business publications

in fall 2003 said: “The average lunch meeting starts seven minutes late.” A
research firm tested this claim to see whether it is true. Using a random
sample of 100 business meetings, the researchers found that the average
meeting in this sample started 4 minutes late and the standard deviation was
3 minutes. Conduct the test using the 0.05 level of significance.
Certain eggs are stated to have reduced cholesterol content, with an average
of only 2.5% cholesterol. A concerned health group wants to test whether
the claim is true. The group believes that more cholesterol may be found, on
the average, in the eggs. A random sample of 100 eggs reveals a sample
average content of 5.2% cholesterol, and a sample standard deviation of
2.8%. Does the health group have cause for action?

An advertisement for the Audi TT model lists the following performance

specifications: standing start, 0–50 miles per hour in an average of 5.28
seconds; braking, 60 miles per hour to 0 in 3.10 seconds on the average. An
independent testing service hired by a competing manufacturer of high-
performance automobiles wants to prove that Audi’s claims are exaggerated.
A random sample of 100 trial runs gives the following results: standing start,
0–50 miles per hour in an average of 5.8 seconds and s=1.9 seconds; braking,
60 miles per hour to 0 in an average of 3.21 seconds and s=0.6 second. Carry
out the two hypothesis tests, state the p-value of each test, and state your
conclusions.
Borg-Warner manufactures hydroelectric miniturbines that generate
low-cost, clean electric power from the energy in small rivers and
streams. One of the models was known to produce an average of 25.2
kilowatts of electricity. Recently the model’s design was improved, and
the company wanted to test whether the model’s average electric
output had changed. The company had no reason to suspect, a priori, a
change in either direction. A random sample of 115 trial runs produced
an average of 26.1 kilowatts and a standard deviation of 3.2 kilowatts.
Carry out a statistical hypothesis test, give the p-value, and state your
conclusion. Do you believe that the improved model has a different
average output?
According to the Wall Street Journal, the average American jockey
makes only $25,000 a year. Suppose you try to disprove this claim
against a right-tailed alternative and your random sample of 100 U.S.
jockeys gives you a sample mean of $45,600 and sample standard
deviation of $20,000. What is your p-value?

The engine of the Volvo model S70 T-5 is stated to provide 246
horsepower. To test this claim, believing it is too high, a competitor
runs the engine n=60 times, randomly chosen, and gets a sample mean
of 239 horsepower and standard deviation of 20 horsepower. Conduct
the test, using level of significance 0.01.
At Armco’s steel plant in Middletown, Ohio, statistical quality-control
methods have been used very successfully in controlling slab width on
continuous casting units. The company claims that a large reduction in the
steel slab width variance resulted from the use of these methods. Suppose
that the variance of steel slab widths is expected to be 156 (squared units). A
test is carried out to determine whether the variance is above the required
level, with the intention to take corrective action if it is concluded that the
variance is greater than 156. A random sample of 25 slabs gives a sample
variance of 175. Using level of significance 0.05, should corrective action be
taken?

According to an article in the New York Times, new Internet dating Web sites
use sex to advertise their services. One such site, True.com, reportedly
received an average of 3.8 million visitors per month.
Suppose that you want to disprove this claim, believing the actual average is
lower, and your random sample of 15 months revealed a sample mean of 2.1
million visits and a standard deviation of 1.2 million. Conduct the test using
level of significance 0.05. What is the approximate p-value?
According to The New York Times,3-D printers are now becoming a
reality. If a manufacturer of the new high-tech printers claims that the
new device can print a page in 3 seconds on average, and a random
sample of 20 pages shows a sample mean of 4.6 seconds and sample
standard deviation of 2.1 seconds, can the manufacturer’s claim be
rejected? Explain and provide numerical support for your answer.
The tensile strength of parts made of an alloy is claimed to be at least 1,000
kg/cm2 The population standard deviation is known from past experience to be
10 kg/cm2.It is desired to test the claim at a level of significance of 5% with the
probability of type II error, restricted to 8% when the actual strength is only
995 kg/cm2. The engineers are not sure about their decision to limit type-II
error as described and want to do a sensitivity analysis of the sample size on
actual mean ranging from 994 to 997 kg/cm2 and limits on ranging from 5% to

10%. Prepare a plot of the sensitivity.