REVIEW PROBLEMS - DO NOT SUBMIT
(CHAPTERS 0, 1, 2, and 3)
Please note that this is NOT a practice exam. This is just a review of problems addressing
some of the concepts you learned in Chapter 0, 1, 2, 3 and 4.
QUESTION 1
1. Suppose that the observational units in a study are the patients arriving at an emergency
room in a given day. For each of the following, indicate if it is a variable, classify it as
categorical (and if it is binary) or quantitative.
a. Blood type
b. Waiting time
c. Mode of arrival (ambulance, personal car, on foot, other)
e. Whether or not the patient is insured
f. Number of stitches required
g. Whether or not stitches are required
h. Assigned room number
QUESTION 2
Tennis players often spin a tennis racquet and observe whether it lands with the logo facing
up or down, to determine who serves first. But is this really a 50-50 process, equally likely to
land with the logo facing up or down? To investigate this, a tennis player spun his racquet
100 times, and he obtained 46 “up” and 54 “down” results. Does this provide much evidence
against believing that spinning the racquet is really a fair 50-50 process?
a. What is the sample statistic?
b. Define the parameter of interest in words.
c. State the null and alternative hypotheses corresponding to this research question.
d. Describe how you could use a coin to conduct a simulation analysis of this study and its
result. Give sufficient detail that someone else could implement this simulation analysis
based on your description. Be sure to indicate how you would decide whether the observed
data provide much evidence against believing that spinning the racquet is really a fair 50-50
process.
e. Use the One Proportion applet to conduct a simulation analysis with at least 1000
repetitions. Report the inputs you use in the applet and draw a sketch of the resulting
distribution. Make sure you clearly label the distribution. Based on this distribution, do you
believe the observed data provide much evidence against believing that spinning the racquet
is really a fair 50-50 process? Explain your reasoning. (Hint: Choose two-sided under
“options”).
f. Can you use a Theory-based approach to answer the research question? Explain.
g. The 95% confidence interval for the probability a racquet lands up is (0.366, 0.557).
Interpret this 95% confidence interval.
h. How do you expect the confidence interval to change if the sample size was 200 and the
sample proportion was still .46?
i. Based on your analyses, would it be legitimate to conclude that the probability a spun
tennis racquet lands up is .5? Discuss both the validity of this conclusion based on your
analyses and what it means to say “probability” in this context.
QUESTION 3
3. The 2004 General Social Survey (GSS) interviewed a random sample of adult Americans.
For one question the interviewer asked: “From time to time, most people discuss important
matters with other people. Looking back over the last six months–who are the people with
whom you discussed matters important to you? Just tell me their first names or initials.” The
interviewer then recorded how many names or initials the respondent mentioned. Results
are tallied in the following table.
The mean was 1.987 friends and the standard deviation was 1.7708 friends.
a. Identify the observational units and the variable in the study. Is the variable categorical or
quantitative?
We used applet to find a theory-based 95% confidence interval shown above
[Link] of the following is a reasonable interpretation of this confidence interval and its
confidence level?
a. Ninety five percent of all adult Americans in this sample reported a number of
close friends within this interval.
b. If you took another sample of 1467 adult Americans, there is a 95% chance that its
sample mean would fall within this interval.
c. You can be 95% confident that the mean number of close friends in the population
of adult Americans is between the endpoints of this interval.
d. This interval captures the number of close friends for 95% of the people in the
population of adult Americans.
c. Look back at the previous question and explain why alternative B is incorrect.
QUESTION 4
4. In a 1993 study, researchers took a sample of people who claimed to have had an intense
experience with an unidentified flying object (UFO) and a sample of people who did not claim
to have had such an experience (Spanos et al., 1993). They then compared the two groups
on a wide variety of variables, including IQ. Suppose you want to test whether or not the
average IQ of those who have had such a UFO experience is higher than 100. The mean IQ
of the 25 people in the study who claimed to have had an intense experience with a UFO
was 101.6; the standard deviation of these IQs was 8.9.
a. State the null and alternative hypothesis in symbols.
b. Identify clearly what the symbol μ represents in this context.
c. Is this a one-sided or a two-sided test? Explain how you can tell.
d. Are the validity conditions met to conduct a one-sample t-test? Explain.
e. Regardless of your answer to the previous question, calculate the test statistic.
f. Write the theory based p-value from the diagram above?
g. Write a sentence interpreting the p-value in the context of this sample and these
hypotheses.
h. Give a conclusion in context, make sure you refer to the parameter.
Question 5:
a. Based on a survey of almost 3,000 adults, researchers Wyatt et al. (Obesity Research,
2002) reported that those who ate breakfast regularly tended to be more successful at
maintaining their weight loss.
1. Identify the explanatory and response variables.
2. Identify a confounding variable that provides an alternative explanation for the
improved success rate of weight loss among regular breakfast eaters, compared to
those who don’t eat breakfast regularly.
b. To investigate whether there is an association between happiness and income level, we
will use data from the 2018 General Social Survey (GSS), cross-classifying a person’s
perceived happiness with their family income level. The GSS is a survey of randomly
selected U.S. adults who are not institutionalized. Here are the data:
1. Identify the explanatory variable. Is it a categorical variable or a quantitative
variable?
2. Identify the response variable. Is it a categorical variable or a quantitative variable?
3. Among above-average-income individuals 0.399 are very happy (190/476); among
average income individuals 0.306 are very happy (319/1,041); and, among
below-average-income individuals 0.204 are very happy (121/594). Does the data
provide any indication of an association between happiness and income level? Why
or why not?
4. Is it okay to conclude that income affects happiness? If yes, explain why. If not,
then identify a confounding variable that provides an alternative explanation for the
association between happiness and income level.
c.
1. Is random sampling or random assignment the more important consideration if the
research question is whether faculty tend to drive older cars than students drive on
your campus?
2. Is random sampling or random assignment the more important consideration if the
research question is whether a waitress generates higher tips by giving her name
when she first greets customers?
d. For each of the studies in (a)–(c), can cause-and-effect conclusions potentially be drawn?
If cause and effect can be determined, explain what may cause what.
1. Subjects were randomly assigned to watch one of two videos, one that was about
a sad situation and one that was about a happy situation. The group that watched the
sad video scored significantly lower on a quiz about their mood.
2. Students collected data on city residents shopping in their city’s downtown stores
and another sample from city residents that were shopping at the mall on the
outskirts of the city. They found that those shopping downtown were significantly
more likely to vote for the school millage than those shopping at the mall.
3. From a random sample of students, it was found that those who are members of
Greek organizations have significantly lower grade point averages.
e. Many studies have found that children who listen to classical music while in the womb or
when younger tend to have higher IQs later in life. These studies are typically done by
surveying parents of older children about whether they played classical music when the child
was younger and conducting an IQ test of the child.
1. Are these studies observational studies or experiments?
2. Will a cause-and-effect conclusion be possible?
3. Identify the observational units in these studies.
4. Identify the explanatory variable in these studies.
5. Identify the response variable in these studies.