STAT 100, Section 1 Sample Mid-term Examination I Spring, 2005

The following 50 questions are similar to the types of questions you will see on the
midterm exam. The actual midterm will be 50 to 60 multiple-choice questions.

Question 1. The importance of randomized experiments is that they:

(A) Require only small sample sizes.
(B) Allow the statistician to assign units to the treatment group.
(C) Allow the inference of causation.
(D) None of the above.
Question 2. In a statistical study, the population is:
(A) The group of people or objects for which conclusions are to be made.
(B) The group of people from whom data cannot be collected.
(C) All people in the United States.
(D) The people or objects studied in the sample survey.
Question 3. In a statistical study, the sample is:
(A) A subset of people in the United States.
(B) The group of people or objects for which conclusions are to be made.
(C) The collection of data in sample surveys.
(D) The subset of the population on which the study collects data.
Question 4. To conduct a proper statistical study, a statistician must:
(A) Have a sample which is fully representative of the population.
(B) Have a sufficiently large sample.
(C) Decide whether the study should be an observational study or an experiment.
(D) All of the above.
Question 5. Statistics consists of:
(A) Procedures and principles for obtaining and processing information in order to make
decisions under uncertainty.
(B) Methods for recording all the “stats” in sports events.
(C) Methods for calculating odds for betting on horse races.
(D) The collection of data by the news media.

1
 Use the following material for the next four questions: In 1982, 490,000 subjects
were asked about their drinking habits. Researchers tracked subjects’ death rates until
1991, and found that adults who regularly had one alcoholic drink daily had a lower death
rate than those who did not drink. Most of the subjects were middle-class, married, and
college-educated.
Question 6. This experiment was:
(A) Accurate; there is fundamentally solid anecdotal evidence that people’s health will
improve if they have one drink daily.
(B) An observational study; it would not be ethical for the researchers to randomly assign
subjects to drink alcohol or not.
(C) A randomized experiment; subjects were assigned in a randomized manner to have
one alcoholic drink each day.
(D) Based on a stratified random sample; subjects were stratified randomly into overlap-
ping groups according to whether or not they had one drink daily.
Question 7. This experiment is an example of:
(A) A matched pairs design; two groups were compared, those who had one drink daily
and those who did not.
(B) A prospective study; after recording their drinking habits, subjects were studied into
the future.
(C) A retrospective study; after the nine-year period, survivors were asked about their
drinking habits.
(D) A block design; many groups were compared, e.g., married vs. not married, middle-
class vs. not middle-class.
Question 8. This experiment suffers from :
(A) A lack of generalizability; most subjects were married and college educated, and so
are atypical of Americans. We cannot generalize the study to all Americans.
(B) The presence of interacting variables; e.g., the educational level of the subjects may
be interacting with whether or not they have one drink daily.
(C) The presence of confounding variables. For example, healthier subjects may be more
likely to allow themselves one drink daily.
(D) All of the above.
Question 9. A news headline, reporting the medical study as “Daily Drink Cuts Death!”
is:
(A) Misleading; we can never infer causation from randomized experiments.
(B) Accurate; there is fundamentally solid anecdotal evidence that one drink daily increases
life length and cuts death.
(C) Accurate; stratified random samples lead to randomized experiments, from which we
cannot infer causation.
(D) Misleading; it implies that there is a causal connection between improved health and
the habit of having one drink daily; however, causation cannot be deduced from an
observational study.

2
Question 10. The Gallup Poll, a well-known polling group, regularly surveys the pub-
lic on many issues. The number of interviews on which their surveys are based is,
approximately:
(A) 600 – 1,200
(B) The entire U.S. population.
(C) 60,000 – 120,000
(D) 60–120
(E) 600,000 – 1,200,000

3
 Use the following material for the next four questions: To estimate the unemploy-
ment rate, the Bureau of Labor Statistics contacts about 60,000 households chosen randomly
from a list of all known households. The Bureau asks each adult in every sampled household
whether they are in the labor force, i.e., employed or seeking employment.
Question 11. The sampling frame for this study is:
(A) All adults in the sampled households.
(B) All known households.
(C) All households which were not selected in the sample.
(D) All sampled households.
Question 12. The measurements in the sample are:
(A) The total number of adults in all sampled households.
(B) The employment statuses of the adults in the population.
(C) The employment statuses of all adults who are not in the labor force.
(D) The employment statuses of the adults in the sample.
Question 13. For this study, a unit is:
(A) A unit of measurement.
(B) An adult in any particular household.
(C) A question on the survey answered by each adult in the sample.
(D) An adult who is in the labor force.
Question 14. The population of interest is:
(A) All adults who refused to participate in the survey.
(B) All employed adults.
(C) All adults who are in the labor force.
(D) All known or unknown households.

Queption 15. If a simple random sample of 1,600 subjects is chosen then an approximate
margin of error for making inferences about a percentage of the entire population is:
(A) Impossible to calculate without knowing the percentage observed in the sample.
(B) Very high, because the sample size is a tiny percentage of the population size.
(C) Approximately zero because the sample size is so large.
(D) 1/1, 600, or 0.06%.
√
(E) 1/ 1, 600, or 2.5%.

4
Question 16. The term “randomization” means that we:
(A) Assign the subjects to the random experiment in a systematic manner.
(B) Use a chance mechanism to assign subjects to the treatment and control groups.
(C) Allow subjects to assign themselves randomly to the placebo or treatment group.
(D) We study only a random subset of all observed outcomes of the experiment.
Question 17. The term “control” means that:
(A) We control carefully the cost of performing the experiment.
(B) There must be a basis for making comparisons.
(C) There is a need to control the subjects of the experiment.
(D) We control carefully the observed outcomes of the experiment.

Question 18. In late 1999, a national newspaper reported that about 65%of the 78,000
voters in a Washington, D.C. election also approved the “medical” use of marijuana.
This outcome was claimed to be a sign of strong support by D.C. residents for “medical
marijuana.” This survey method is:
(A) An example of volunteer sampling: It is subject to response biases because supporters
of “medical marijuana” may be more likely to have voted.
(B) A way for bureaucrats to accurately assess public opinion of “medical marijuana.”
(C) An example of stratified random sampling because all voters can be divided into two
strata: those in favor of “medical marijuana” and those who are not.
(D) A probability sampling plan: There is a high chance that the 78,000 voters were
well-scattered across the D.C., and so they constitute a representative sample.
Question 19. A simple random sample of ten subjects from a population is one in which:
(A) A simple way was found to choose ten subjects at random from the population.
(B) We record the data provided by the first ten subjects who respond to the survey.
(C) Any group of ten subjects has the same chance of being the selected sample.
(D) Most, but not all, groups of size ten have the same chance of being selected.
Question 20. In a study of PSU students’ awareness of world issues, a television crew
sampled students sitting in the Hub at 12:00 p.m. (noon). This survey is an example
of:
(A) A volunteer response sample because, to be seen on the evening news, students will
eagerly volunteer their responses.
(B) A haphazard (or convenience) sample, because the Hub is a convenient place to find
students.
(C) A simple random sample, because it is simple to find students at the Hub in a random
manner.
(D) A stratified random sample, because students are stratified by gender and they are
found at the Hub in a random manner.

5
Question 21. A radio advertiser wishes to choose a random sample of size 100 from a
population of 5, 000 listeners. After observing that 5, 000 ÷ 50 = 100, he first selects a
subject at random from the first 50 names in the sampling frame, and then he selects
every 50th subject listed after that one. This method of random sampling is called:
(A) Stratified random sampling.
(B) Systematic random sampling.
(C) Cluster random sampling.
(D) Simple random sampling.
Question 22. In a second study the radio advertiser divides the population into five sepa-
rate groups and then selects a simple random sample from each group. This method
of random sampling is called:
(A) Stratified random sampling.
(B) Volunteer sampling.
(C) Simple random sampling.
(D) Systematic random sampling.
Questiol 23. In a third study, the radio advertiser divides the population into a large
number of groups. He selects a simple random sample of the groups and then surveys
every subject in each of the groups selected. This method of random sampling is
called:
(A) Systematic random sampling.
(B) Random digit dialing.
(C) Cluster sampling.
(D) Stratified random sampling.

Question 24. To assess its employees’ views of new student fees imposed by the state
legislature, a university divided employees into two groups: those with at least 20
years, and those with fewer than 20 years, of service. A random sample was selected
from each group and their views were obtained by telephone. This method of sampling
is likely to be:
(A) Biased, because random digit dialing should have been used to contact employees.
(B) Biased, because the two groups are different in character.
(C) Unbiased, because it is an example of stratified random sampling.
(D) Unbiased, because the population has been stratified by telephone number.
Question 25. In any large data set, the proportion of data falling at or below Q3 , the third
quartile, is:
(A) Dependent on the sample drawn from the population.
(B) 99.7%
(C) 68%
(D) 25%
(E) 75%

6
Question 26. In a boxplot (oriented vertically, with the maximum at the top and the
minimum at the bottom), the proportion of the data falling between the top edge and
the bottom edge of the box itself is
(A) Impossible to say without more information
(B) 99.7%
(C) 68%
(D) 25%
(E) 50%
Question 27. To survey the opinions of its customers, a supermarket grouped its customers
by the days when they did most of their shopping. The supermarket randomly selected
two such groups, and asked all customers in those two groups to complete a survey.
This method of sampling is called:
(A) Stratified random sampling.
(B) Cluster sampling.
(C) Random digit dialing.
(D) Systematic sampling.
Question 28. A pollster studying opinions on gun control divided a city into blocks, then
surveyed the third house to the west of the southeast corner of each block. If that
house consisted of apartments, the westernmost ground floor apartment was selected.
The pollster conducted the survey during daytime, and left a phone number for those
who were away when she tried to interview them. This sampling method is likely to
be:
(A) Unbiased, because the population has been stratified according to city blocks.
(B) Unbiased, because this is an example of systematic sampling.
(C) Biased, because she tried to interview in person those who were away.
(D) Biased; those at home during daytime may have sharply different views from those
not at home.
Question 29. A supermarket manager wants to know if customers would pay slightly
higher prices to have computers available throughout the store to help them locate
items. An interviewer is posted at the entrance door and asked to collect a sample of
100 opinions by asking questions of the next person who came to the door each time
she had completed an interview. This method of sampling is likely to be:
(A) Biased, because only customers will be asked questions.
(B) Unbiased, because there is no reason for a customer not to answer questions.
(C) Biased, because this is an example of a convenience sample.
(D) Unbiased, because any customer has a good chance of being asked questions.

7
Question 30. The Empirical Rule states, in part, that if a data set is approximately
normally distributed (or bell-shaped) then:
(A) About 68% of all observations fall within one standard deviation of the mean.
(B) About 37% of all observations fall within two standard deviations of the mean.
(C) At most 90% of all observations fall within three standard deviations of the mean.
(D) None of the above.
Question 31. For any data set, the standard deviation is:
(A) A measure of central tendency.
(B) The average of the sample mean and quartiles.
(C) The average of the deviations.
(D) A measure of the spread or variability of the data.
Question 32. When a distribution is greatly skewed to the left (i.e., has a long right tail),
the median will usually be:
(A) Smaller than the mean.
(B) In no relation whatsoever to the mean.
(C) Larger than the mean.
(D) Exactly equal to the mean.

8
 Use the following material for the next three questions: A sample of 28 temperature
measurements in ◦ F, all taken at 12:00 p.m., was collected in a coastal town in NC. The
data are given in the following stemplot:

Stemplot of Temperature Readings

3 2
5 5
6 0 1 2 4 48
7 3 5 5 6 8899
8 0 0 2 3 458
9 0 2 3 5 8

Question 33. For the data given in this stemplot, the five-number summary is:
(A) 32, 68, 79, 88, 98
(B) 55, 66, 78.5, 84.5, 95
(C) 32, 66, 78.5, 84.5, 98
(D) 32, 66, 78, 84, 98
Question 34. In this stemplot, the interquartile range is:
(A) 84 - 66 = 18
(B) 88 - 68 = 20
(C) 84.5 - 66 = 18.5
(D) 95 - 55 = 40
Question 35. A second sample of 28 temperature readings in a GA coastal town was also
collected. Each GA measurement was recorded at the same time and date as the
NC data value, and turned out to be exactly 5◦ F higher than the corresponding NC
measurement. We calculate the standard deviation (S.D.) of the two data sets and
conclude that:
(A) The two data sets have the same standard deviations.
(B) The S.D. of the NC data exceeds the S.D. of the GA data by 5◦ F.
(C) The S.D. of the GA data exceeds the S.D. of the NC data by 5◦ F.
(D) None of the above; there is no relationship between the two S.D.’s.

9
 Use the table of standard normal scores and the following material for the next four
questions: As measured by the Stanford-Binet test, IQ scores are approximately normally
distributed with mean 100 and standard deviation 16.
Question 36. A score of 108 on the Stanford-Binet test falls in the:
(A) 80th percentile.
(B) 50th percentile.
(C) 92nd percentile.
(D) 69th percentile.
Quostion 37. A student who scores 108 on the Stanford-Binet test has a standardized
score of:
(A) (108 − 100)/16 = 0.50.
(B) Cannot be calculated because we are given insufficient information.
√
(C) (108 − 100)/ 100 = 0.80.
(D) (108 − 16)/100 = 0.92.
Question 38. Mensa is an organization whose members have IQ scores in the top 2%of the
population. To be admitted to Mensa, a person’s Stanford-Binet IQ score is at least:
(A) 100 + (16 × 2.05) = 132.80.
(B) 100 − (16 × 2.05) = 67.20.
(C) 100 − (16 × 0.98) = 84.32.
(D) 100 + (16 × 0.98) = 115.68.
Question 39. Because of the Empirical Rule (68-95-99.7 Rule), we can conclude that
approximately 68% of all IQ scores will fall between:
(A) 84 and 116.
(B) 32 and 168.
(C) 68 and 132.
(D) 0 and 200.

Question 40. If a data set is normally distributed then:

(A) The mean is smaller than the median or the mode.
(B) The mean is larger than the median but not larger than the mode.
(C) The mean, median and mode are the same.
(D) None of the above.

10
 Use the following material for the next four questions: A researcher asks 1,600
randomly chosen doctors whether or not they take aspirin regularly. She also asks them
to estimate the number of headaches they have had in the past six months, and compares
the number of headaches reported by those who take aspirin regularly to the number of
headaches reported by those who do not take aspirin regularly.
Question 41. In this study, the number of headaches is a:
(A) Response variable.
(B) Explanatory variable.
(C) Confounding variable.
(D) None of the above.
Question 42. This type of study design is a:
(A) Census.
(B) Randomized experiment.
(C) Prospective study.
(D) Retrospective observational study.
Question 43. With regard to all people in the country, this study is likely to:
(A) Provide accurate information because a random sample of size 1,600 has a margin of
error of 2.5%.
(B) Be somewhat unrealistic because doctors are not representative of the population.
(C) Provide inaccurate inferences because 1,600 doctors is a tiny proportion of all people
in the country.
(D) Provide accurate information because the subjects were chosen randomly.
Question 44. This study may be highly unreliable because:
(A) Subjects are unlikely to accurately recall past incidences of headaches.
(B) Subjects should have randomly assigned themselves to the two treatments.
(C) The researcher should have randomly assigned subjects to the two treatments.
(D) Subjects cannot both take aspirin regularly and not take aspirin regularly.

Question 45. To test the effects of sleepiness on driving performance, twenty volunteers
took a simulated driving test under each of three conditions: Well-rested, Sleepy, and
Exhausted. The order in which each volunteer took the three tests was randomized,
and an evaluator rated their driving accuracy without knowing the condition of the
volunteer. This type of experiment is a:
(A) Retrospective observational study.
(B) Single-blind, block design experiment.
(C) Single-blind, matched-pair experiment.
(D) Double-blind, matched-pair experiment.

11
Question 46. In the previous question on a study of sleepiness and its effects on driving
performance, the explanatory variable is:
(A) The condition of sleepiness.
(B) The order in which the volunteers took the tests.
(C) The evaluator’s rating of driving accuracy.
(D) The evaluator’s rating of the driver’s condition.

Quesbion 47. It has been observed that participants in a statistical experiment sometimes
respond differently than they otherwise would because they know that they are in an
experiment. This phenomenon is called the:
(A) Confounding effect.
(B) Placebo effect.
(C) Interacting effect.
(D) Hawthorne effect.
Question 48. It has been observed that participants in a statistical experiment sometimes
respond positively to a placebo, a substance which has no active ingredients. This
phenomenon is called the:
(A) Placebo effect.
(B) Hawthorne effect.
(C) Confounding effect.
(D) Interacting effect.

Question 49. For any data set, the largest number in the five-number summary is the:
(A) Standard deviation.
(B) Outlier.
(C) Third quartile.
(D) Interquartile range.
(E) Maximum.
Question 50. For any data set, the proportion of the data that falls at or above the median
is:
(A) 50%
(B) 25%
(C) 95%
(D) 99.7%
(E) Dependent on the sample which was drawn from the population.

12