(Fall 2023) STAT 1010 Homework 7 Due: Friday, December 1 at 11:59pm

1. Mark each statement True or False. If you believe that a statement is false, briefly explain why you
think it is false.
(a) (1 point) All other things the same, a 90% confidence interval is shorter than a 95% confidence
interval.

True.

(b) (1 point) If we double the sample size from n = 50 to n = 100, the length of the confidence interval
is reduced by half.

False it is decreased by a factor of root 2.

(c) (1 point) If zero lies inside the 95% confidence interval for µ, then zero is also inside the 99%
confidence interval for µ.

False, 0 could be close to the bounds of the 95% CI and then cut out when moving to 99%.

(d) (1 point) To guarantee a margin of error of 0.05 for the population proportion p, a survey needs to
have at least 500 respondents.

MOE = Distance from center to edge of CI = score * s/sqrt(n). Therefore False as MOE depends on n and
s.
(Fall 2023) STAT 1010 Homework 7 Due: Friday, December 1 at 11:59pm

(e) (1 point) If the standard two-sample t-test rejects H0 : µ1 − µ2 ≤ 100, then µ1 is more than 100
larger than µ2 .

False. This test depends on the significance level alpha. So we are more than 100-a% sure that u1 is
more than 100 larger than u2.

(f) (1 point) If the two-sample confidence interval for µ1 − µ2 includes 0, then we should conclude that
µ1 = µ2 .

False, just because the CI includes a value does not mean that that is the value.

(g) (1 point) If the boxplots of the data for the two groups overlap, then the two means are not
significantly different.

False, box-plots deal with proportions not weighted proportions(means).

2. A retailer maintains a Web site that it uses to attract shoppers. The average purchase amount is $80.
The retailer is evaluating a new Web site that would, it hopes, encourage shoppers to spend more. Let
µ represent the average amount spent per customer at its redesigned Web site. Mark each statement
True or False. If you believe that a statement is false, briefly explain why you think it is false.
(a) (1 point) The appropriate null hypothesis for testing the profitability of the new design sets µ = 80.

True

Page 2
(Fall 2023) STAT 1010 Homework 7 Due: Friday, December 1 at 11:59pm

(b) (1 point) If the α-level of the test is α = 0.05, then there is at most a 5% chance of incorrectly
rejecting H0 .

True

(c) (1 point) If the standard deviation is estimated from the data, then a z-statistic determines the
p-value.

False a t-stat would be used.

3. (2 points) The clothing buyer for a department store wants to be sure the store orders the right mix of
sizes. As part of a survey, she measured the height (in inches) of men who bought suits at this store.
Her software reported the following confidence interval:

With 95.00% confidence, 70.9 < µ < 74.5.

(a) Summarize the interpretation of the software’s results in a sentence.

There is a 95% chance that the mean men's height is between 70.9 and 74.5.

Page 3
(Fall 2023) STAT 1010 Homework 7 Due: Friday, December 1 at 11:59pm

(b) What’s the margin of error for this interval?

1.8in

(c) If the researcher had calculated a 99% confidence interval, would the output have shown a longer
or shorter interval?

A longer interval.

4. (2 points) Find the appropriate percentile from a t-distribution for constructing the following confidence
intervals:
(a) 90% t-interval with n = 12.

t = 1.833

Page 4
(Fall 2023) STAT 1010 Homework 7 Due: Friday, December 1 at 11:59pm

(b) 95% t-interval with n = 6.

t = 2.447

(c) 99% t-interval with n = 15.

t = 2.947

5. (2 points) Hoping to lure more shoppers downtown, a city builds a new public parking garage in the
central business district. The city plans to pay for the structure through parking fees. During a two-
month period (44 weekdays), daily fees collected averaged $1,264 with a standard deviation of $150.
(a) What assumptions must you make in order to use these statistics for inference?

That the sample size is large enough for the CLT to apply.

(b) Write a 90% confidence interval for the mean daily income this parking garage will generate, rounded
appropriately.

Xbar +- 1.684SD(Xbar) = 1264 +- 1.684(150) = (1011, 1517)

Page 5
(Fall 2023) STAT 1010 Homework 7 Due: Friday, December 1 at 11:59pm

(c) Give a 90% confidence interval for the total revenue earned during five weekdays.

(5055, 7583)

6. (2 points) A sample of 150 calls to a customer help line during one week found that callers were kept
waiting on average for 16 minutes with s = 8.
(a) Find the margin of error for this result if we use a 95% confidence interval for the length of time
all customers during this period are kept waiting.

MOE = score * s/sqrt(n) = 1.976 * 8/sqrt(150) = 1.29

(b) Interpret for management the margin of error.

We are 95% confident that the average time callers will wait will be 16+- 1.29.

Page 6
(Fall 2023) STAT 1010 Homework 7 Due: Friday, December 1 at 11:59pm

(c) If we only need to be 90% confident, does the confidence interval become wider or narrower?

Narrower.

7. (2 points) Consider the following test of whether a coin is fair. Toss the coin three times. If the coin
lands either all heads or all tails, reject H0 : p = 1/2. (The p denotes the chance for the coin to land on
heads.)
(a) What is the probability of a Type I error for this procedure?

1/4

(b) If p = 3/4, what is the probability of a Type II error for this procedure?

3/4

Page 7
(Fall 2023) STAT 1010 Homework 7 Due: Friday, December 1 at 11:59pm

8. (4 points) Performance Tires plans to engage in direct mail advertising. It is currently in negotiations
to purchase a mailing list of the names of people who bought sports cars within the last three years. The
owner of the mailing list claims that sales generated by contacting names on the list will more than pay
for the cost of using the list. (Typically, a company will not sell its list of contacts, but rather provides
the mailing services. For example, the owner of the list would handle addressing and mailing catalogs.)
Before it is willing to pay the asking price of $3 per name, the company obtains a sample of 225 names
and addresses from the list in order to run a small experiment. It sends a promotional mailing to each
of these customers. The data for this exercise show the gross dollar value of the orders produced by
this experimental mailing. The company makes a profit of 20% of the gross dollar value of a sale. For
example, an order for $100 produces $20 in profit.
(a) Why would a company want to run an experiment? Why not just buy the list and see what happens?

Because conducting an experiment helps them to figure out whether the list is a worthwhile purchase or not.

(b) Why is a hypothesis test relevant in this situation?

You can test the claim using a hypothesis test.

Page 8
(Fall 2023) STAT 1010 Homework 7 Due: Friday, December 1 at 11:59pm

(c) Describe the appropriate hypotheses and type of test to use. Choose (and justify) an α-level for
the test. Be sure to check that this choice satisfies the necessary conditions.

H0: profit <= 0

(d) Suppose that the company got the average earnings $33.66 and standard deviation s = $97.02. Test
the null hypothesis and report a p-value. If examination of the data suggests problems with the
proposed plan for testing the null hypothesis, revise the analysis appropriately.

n = 225
t - stat = (0.2(33.66) - 0) / 0.2(97.02)/sqrt(225) = 5.2
p - value = 1.976

Page 9
(Fall 2023) STAT 1010 Homework 7 Due: Friday, December 1 at 11:59pm

(e) Summarize the results of the test. Make a recommendation to the management of Performance
Tires (avoid statistical jargon, but report the results of the test).

Yes it is profitable to buy the mailing list.

9. (2 points) Based on data collected in 2010, 23 percent of women wanted to buy a Google Android smart
phone or tablet. Among men, 33 percent were interested in an Android purchase next. The survey
contacted 240 women and 265 men.
(a) Might the comparison between these two samples be confounded with a hidden factor? If so, identify
such a factor.

Perhaps income could confound this sample.

Page 10
(Fall 2023) STAT 1010 Homework 7 Due: Friday, December 1 at 11:59pm

(b) Find the 95% confidence interval for the difference between the proportion of men (pm ) and the
proportion women (pf ) interested in buying an Android device.

Pm - Pf ~ N(0.1, 1.57*10^-3)

95% CI = (0.022, 0.178)

ok because np and n(1-p) are both > 10

(c) What are the implications of the confidence interval for sales executives at Google?

They are 95% sure that men are more likely to want an android as their next purchase.

10. (4 points) Anyone who’s ever watched late-night TV knows how many people want to lose weight the
easy way. On the basis of recent medical studies, there may be such a thing. Glaxo Smith Kline bought
the drug Orlistat with the hopes of turning it into a modern miracle. Results in prior clinical trials had
found that when Orlistat was combined with a diet, subjects taking Orlistat lost more weight. After
about a year, a randomized experiment found that obese subjects taking this medication had lost about
11 more pounds, on average, than others who were also dieting, but taking a placebo. Further studies
showed similar results.
This drug had moderate success, but Glaxo Smith Kline wanted to take it before the Food and Drug
Administration (FDA) and ask the agency to approve it for over-the-counter sales. They wanted it to
be available without a prescription. To assemble more information, the company needs help in designing
a study to test the drug for college students. The company needs to know how many students it must
enroll in order to see if the drug works.

Page 11
(Fall 2023) STAT 1010 Homework 7 Due: Friday, December 1 at 11:59pm

(a) Worldwide sales were about $500 million in 2004, but projected to soar to more than $1.5 billion
annually with the greater access of over-the-counter sales. Do you think it would be damaging to
Glaxo Smith Kline’s case if the proposed study did not find the drug to be helpful?

Yes, it would most definitely harm their sales and perhaps change the FDA's opinion.

(b) If the study costs $5,000 per subject to run but the potential upside is $1 billion, why should the
size of the study matter? Why not recruit thousands?

Larger studies may take longer to carry out and time is expensive.

Page 12
(Fall 2023) STAT 1010 Homework 7 Due: Friday, December 1 at 11:59pm

(c) To get FDA recognition, this study requires a randomized experiment. Let’s assume half of the
subjects receive a placebo and half receive Orlistat. If the subjects are healthy students who take
half the dose taken by the obese people in prior studies, would you expect the amount of weight
loss to be as large as in previous studies?

No it would likely be smaller.

(d) Is a two-sample confidence interval of the difference in means appropriate for this analysis?

Yes we could use a difference in means CI to see how likely it is that the college students
lose less weight than the obese people.

Page 13
(Fall 2023) STAT 1010 Homework 7 Due: Friday, December 1 at 11:59pm

(e) Will the presence of lurking factors lead to confusion over the interpretation of the difference in
means?

No as it is a randomized control trial which should negate OMB due to the law of large numbers.

(f) What would you recommend if the variation in weight loss is different in the two groups, with those
taking Orlistat showing much more variation than those taking the placebo?

Due another clinical trial.

Page 14
(Fall 2023) STAT 1010 Homework 7 Due: Friday, December 1 at 11:59pm

(g) For the following calculations, let’s assume that Glaxo Smith Kline expects those taking Orlistat to
have lost 6 pounds more than the controls after six months. Pilot studies indicate that the SD for
the amount of weight lost by an individual is σ = 5. If the study enrolls 25 students in each group
(a total of 50), is it likely that the difference between the two sample means will be far from zero?

H0: Ud - Up <= 0
H1: Ud - Up > 0
alpha = 0.05
n = 50
Assuming H0 => Ud - Up ~ N(0, 2)
t - stat = 6/2 = 3
p - value = 1.676
Therefore yes it is likely that the difference between the two sample means will be far from 0.

(h) Repeat part (g), with 100 students enrolled in each group.

Ud - Up ~ N(0, 0.5), therefore even more likely so yes as new t - stat = 12

Page 15
(Fall 2023) STAT 1010 Homework 7 Due: Friday, December 1 at 11:59pm

(i) Do you think it’s likely that the confidence interval with 25 or 100 in each group will include zero
if in fact µ1 − µ2 = 6?

No it is unlikely to include 0

(j) If the claimed value for σ is too small, what will be the likely consequence for the choice of a sample
size?

You would need a larger sample to correct for that.

Page 16
(Fall 2023) STAT 1010 Homework 7 Due: Friday, December 1 at 11:59pm

(k) Which sample size would you recommend, 25 in each group or 100?

I would recommend 100 in each group for the sake of accuracy.

(l) This drug has some embarrassing side effects (e.g., incontinence). Would this affect your recom-
mendation of how many subjects to enroll? Why?

No we can't take those considerations into effect when testing a drug.

Page 17