Combined Practice Set: 2

Question 1:

Many drugs used to treat cancer are expensive. BusinessWeek reported on the cost per treatment of
Herceptin, a drug used to treat breast cancer (BusinessWeek, January 30, 2006). Typical treatment costs
(in dollars) for Herceptin are provided by a simple random sample of 10 patients.

a. Develop a point estimate of the mean cost per treatment with Herceptin.
b. Develop a point estimate of the standard deviation of the cost per treatment with Herceptin.

Solution:

15. a.

b.

Question 2:

The College Board reported the following mean scores for the three parts of the Scholastic Aptitude Test
(SAT) (The World Almanac, 2009):

Critical Reading: 502

Mathematics: 515

Writing: 494

Assume that the population standard deviation on each part of the test is σ = 100.

a. What is the probability that a random sample of 90 test takers will provide a sample mean test score
within 10 points of the population mean of 502 on the Critical Reading part of the test?
b. What is the probability that a random sample of 90 test takers will provide a sample mean test score
within 10 points of the population mean of 515 on the Mathematics part of the test? Compare this
probability to the value computed in part (a).

c. What is the probability that a random sample of 100 test takers will provide a sample mean test score
within 10 of the population mean of 494 on the writing part of the test? Comment on the differences
between this probability and the values computed in parts (a) and (b).

Solution:

25. This value for the standard error can be used for parts (a) and
(b) below.

a. P(z ≤ .95) = .8289

P(z < -.95) = .1711

probability = .8289 - .1711 =.6578

b. P(z ≤ .95) = .8289

P(z < -.95) = .1711

probability = .8289 - .1711 =.6578

The probability of being within 10 of the mean on the Mathematics portion of the test is
exactly the same as the probability of being within 10 on the Critical Reading portion of the
SAT. This is because the standard error is the same in both cases. The fact that the means
differ does not affect the probability calculation.
 c. The standard error is smaller here because the sample size is
larger.

P(z ≤ 1.00) = .8413

P(z < -1.00) = .1587

probability = .8413 - .1587 =.6826

The probability is larger here than it is in parts (a) and (b) because the larger sample size
has made the standard error smaller.

Question 3:

In 2008 the Better Business Bureau settled 75% of complaints it received (USA Today, March 2, 2009).
Suppose you have been hired by the Better Business Bureau to investigate the complaints it received
this year involving new car dealers. You plan to select a sample of new car dealer complaints to estimate
the proportion of complaints the Better Business Bureau is able to settle. Assume the population
proportion of complaints settled for new car dealers is .75, the same as the overall proportion of
complaints settled in 2008.

a. Suppose you select a sample of 450 complaints involving new car dealers. Show the sampling
distribution of p.

b. Based upon a sample of 450 complaints, what is the probability that the sample proportion will be
within .04 of the population proportion?

c. Suppose you select a sample of 200 complaints involving new car dealers. Show the sampling
distribution of p.

d. Based upon the smaller sample of only 200 complaints, what is the probability that the sample
proportion will be within .04 of the population proportion?

e. As measured by the increase in probability, how much do you gain in precision by taking the larger
sample in part (b)?

Solution:
 39. a. Normal distribution with and

b. P(z ≤ 1.96) = .9750

P(z < -1.96) = .0250

P(.71   .79) = P(-1.96  z  1.96) = .9750 - .0275 = .9500

c. Normal distribution with and

d. P(z ≤ 1.31) = .9049

P(z < -1.31) = .0951

P(.71   .79) = P(-1.31  z  1.31) = .9049 - .0951 = .8098

e. The probability of the sample proportion being within .04 of the population mean was
reduced from .9500 to .8098. So there is a gain in precision by increasing the sample size
from 200 to 450. If the extra cost of using the larger sample size is not too great, we should
probably do so.

Question 4:
After deducting grants based on need, the average cost to attend the University of Southern California
(USC) is $27,175 (U.S. News & World Report, America’s Best Colleges, 2009 ed.). Assume the population
standard deviation is $7400. Suppose that a random sample of 60 USC students will be taken from this
population.

a. What is the value of the standard error of the mean?

b. What is the probability that the sample mean will be more than $27,175?

c. What is the probability that the sample mean will be within $1000 of the population mean?

d. How would the probability in part (c) change if the sample size were increased to 100?

Solution:

46.  = 27,175  = 7400

a.

b.

P( > 27,175) = P(z > 0) = .50

Note: This could have been answered easily without any calculations ; 27,175 is the
expected value of the sampling distribution of .

c. P(z ≤ 1.05) = .8531

P(z < -1.05) = .1469

P(26,175   28,175) = P(-1.05  z  1.05) = .8531 - .1469 = .7062

d.
 P(z ≤ 1.35) = .9115

P(z < -1.35) = .0885

P(26,175   28,175) = P(-1.35  z  1.35) = .9115 - .0885 = .8230

Question 5:

A production process is checked periodically by a quality control inspector. The inspector selects simple
random samples of 30 finished products and computes the sample mean product weights . If test results
over a long period of time show that 5% of the values are over 2.1 pounds and 5% are under 1.9 pounds,
what are the mean and the standard deviation for the population of products produced with this
process?

Solution:

49. Sampling distribution of

The area below = 2.1 must be 1 - .05 = .95. An area of .95 in the standard normal table
shows
z = 1.645.
 Thus,

Solve for 

Question 6:

Sales personnel for Skillings Distributors submit weekly reports listing the customer contacts made
during the week. A sample of 65 weekly reports showed a sample mean of 19.5 customer contacts per
week. The standard deviation of those 65 weekly reports was 5.2. Provide 90% and 95% confidence
intervals for the population mean number of weekly customer contacts for the sales personnel.

Solution:

15.

90% confidence df = 64 t.05 = 1.669

19.5 ± 1.669

19.5 ± 1.08 or 18.42 to 20.58

95% confidence df = 64 t.025 = 1.998

19.5 ± 1.998
 19.5 ± 1.29 or 18.21 to 20.79

Question 7:

Workers in several industries were surveyed to determine the proportion of workers who feel their
industry is understaffed. In the government sector, 37% of the respondents said they were understaffed,
in the health care sector 33% said they were understaffed, and in the education sector 28% said they
were understaffed (USA Today, January 11, 2010). Suppose that 200 workers were surveyed in each
industry.

a. Construct a 95% confidence interval for the proportion of workers in each of these industries who feel
their industry is understaffed.

b. Assuming the same sample size will be used in each industry, how large would the sample need to be
to ensure that the margin of error is .05 or less for each of the three confidence intervals?

Solution:

59. a. Government industry 95% margin of error:

95% Confidence interval: .37 .0669 or .3031 to .4369

Health care industry 95% margin of error:

95% Confidence interval: .33 .0652 or .2648 to .3952

Education industry 95% margin of error:

95% Confidence interval: .28 .0622 or .2178 to .3422

Question 8:
The service time in queues should not have a large variance; otherwise, the queue tends to build up. A
bank regularly checks service time by its tellers to determine its variance. A random sample of 22 service
times (in minutes) gives s2=8. Give a 95% confidence interval for the variance of service time at the
bank.

Solution:

6-52. A random sample of n=22 service times yields a variance of s2 = 8. Compute a 95% confidence
interval for the variance.

The Chi-square distribution is used, with n  1 = 22  1 = 21 degrees of freedom. The variance

interval endpoints are:

[
( n−1 ) s 2 ( n−1) s 2
χ
2
a/ 2
, 2
χ 1−a/ 2 .]
Unlike the normal and t distributions, the Chi-square is not symmetrical.

Instead of using symmetrical values Z and Z, or t and t, we must obtain the separate upper and lower
values from the Chi-square distribution. For a level of .95, the value  = 1  .95 = .05, and /2
= .05/2 = .025. Therefore, we need (for 21 degrees of freedom) 2a/2 = 2.025,21 = 35.5 for the right-
hand or upper endpoint, and we need 21-a/2 = 2.975,21 = 10.3 for the left-hand or lower endpoint.
The interval endpoints are thus:

[ (22−1)(8 ) (22−1 )(8 )

35. 5
,
10 .3 ]
= (4.7324, 16.3107),
which is a 95% confidence interval for the unknown population variance of service times.

Note that the left-hand or lower statistic, 2.975, represents the Chi-square statistic which has an
area of .975 to its right (its tail area is .975). Similarly, the right-hand or upper statistic, 2.025,
represents the Chi-square statistic which has an area of .025 to its right (its tail area is .025).
Question 9:

Because of high production-changeover time and costs, a director of manufacturing must convince
management that a proposed manufacturing method reduces costs before the new can be
implemented. The current production method operates with a mean cost of $220 per hour. A research
study will measure the cost of the new method over a sample production period.

a. Develop the null and alternative hypotheses most appropriate for this study.

b. Comment on the conclusion when H0 cannot be rejected.

c. Comment on the conclusion when H0 can be rejected.

Solution:

a. H0: m ³ 220

Ha: m < 220 Research hypothesis to see if mean cost is less than $220.

b. We are unable to conclude that the new method reduces costs.

c. Conclude m < 220. Consider implementing the new method based on the conclusion that
it lowers the mean cost per hour.
Question 10:

Microsoft Corporation makes software packages for use in microcomputers. The company believes that if
at least 25% of present owners of microcomputers of certain types would be interested in a particular new
software package, then the company will make a profit if it markets the new package. A company analyst
therefore wants to test the null hypothesis that the proportion of owners of microcomputers of the given
kinds who will be interested in the new package is at most 0.25, versus the alternative that the proportion
is greater than 0.25. A random sample of 300 microcomputer owners shows that 94 are interested in the
new Microsoft package. Should the company market its new product? Report the p-value.

Ans:

Reject H0.
There is evidence that the proportion of microcomputer owners interested in the software package
is over 25%. The company should probably market the product.
p-value = .5  .4943 = 0.0057.