Test Bank for Political Science Research Methods

8th Edition Johnson Reynolds Mycoff 1506307825

9781506307824
Download full test bank at:
https://testbankpack.com/p/test-bank-for-political-science-
research-methods-8th-edition-johnson-reynolds-mycoff-
1506307825-9781506307824/

Chapter 6
1. A ________________ is a plan that shows how a researcher intends to study an empirical question.
a. Theory
b. Unit of analysis
c. Summation index
*d. Research design
Learning objective number: 6.6 Summarize different types of observational studies, such as small-N
designs and cross-sectional designs
Cognitive domain: Comprehension
Answer location: Introduction
Question type: MC

2. The most basic experiment, the _________ design, involves two groups and two variables, one
independent and one dependent, as before.
a. Simple pre-test
*b. Simple post-test
c. Complex pre-test
d. Complex post-test
Learning objective number: 6.2 Identify the types and characteristics of randomized experiments.
Cognitive domain: Comprehension
Answer location: Other Randomized Experiments
Question type: MC

3. Which of the following experimental designs contains several pre-treatment and post-treatment
measures, because it is not certain exactly how quickly the effect of the independent variable should be
observed or when the most reliable pre-test measurement of the dependent variable should be taken?
a. Multiple group
*b. Repeated measures
c. Simple post-test
d. Nonrandomized
Learning objective number: 6.2 Identify the types and characteristics of randomized experiments
Cognitive domain: Comprehension
Answer location: Other Randomized Experiments
Question type: MC

4. In a ____________ design, measurements of the independent and dependent variables are taken at
approximately the same time, and the researcher does not control or manipulate the independent variable,
the assignment of subjects to treatment or control groups, or the conditions under which the independent
variable is experienced.
*a. Cross-sectional
Learning objective number: 6.6 Summarize different types of observational studies, such as small-N
designs and cross-sectional designs
Cognitive domain: Comprehension
Answer location: Cross-Sectional Designs: Surveys and Aggregate Analysis
Question type: FIB

5. Which of the following research designs uses treatment and control groups, but the experimenter does
not randomly assigned individual units to these groups?
a. Case study
b. Multiple group
*c. Quasi-experimental
d. Simulation
Learning objective number: 6.3 Discuss quasi-experimental design
Cognitive domain: Comprehension
Answer location: Nonrandomized Designs: Quasi-Experiments
Question type: MC

6. A ____________ is a stimulus given to a treatment group in an experiment.

a. Prompt
*b. Test factor
c. Pre-test
d. Cohort
Learning objective number: 6.1 Explain the ways in which casual assertions can be verified
Cognitive domain: Comprehension
Answer location: Verifying Causal Assertions
Question type: MC

7. ____________ means that the research procedure demonstrated a true cause-and-effect relationship
that was not created by spurious factors.
a. Internal reliability
b. External reliability
*c. Internal validity
d. External validity
Learning objective number: 6.1 Explain the ways in which causal assertions can be verified
Cognitive domain: Comprehension
Answer location: Verifying Causal Assertions
Question type: MC

8. The initial measurement of variables in an experimental design is called a _________.

*a. Pre-test
b. Post-test
c. Operationalization
d. Conceptualization
Learning objective number: 6.2 Identify the types and characteristics of randomized experiments
Cognitive domain: Comprehension
Answer location: The Classical Randomized Experiment
Question type: MC
9. All of the following are true of a causal relationship except
a. It demonstrates covariation
*b. It demonstrates spuriousness
c. The cause precedes the effect
d. Elimination of confounding factors
Learning objective number: 6.1 Explain the ways in which causal assertions can be verified
Cognitive domain: Comprehension
Answer location: Verifying Causal Assertions
Question type: MC

10. A _________ assertion suggests that a change in one thing brings about a change in another.
a. Correlation
b. Spurious
*c. Causal
d. Research
Learning objective number: 6.1 Explain the ways in which causal assertions can be verified
Cognitive domain: Comprehension
Answer location: Verifying Causal Assertions
Question type: MC

11. _____________ can creep into a study if subjects are picked (intentionally or not) according to some
criterion and not randomly.
a. Demand characteristic
b. Experimental mortality
c. Covariation
*d. Selection bias
Learning objective number: 6.1 Explain the ways in which causal assertions can be verified
Cognitive domain: Comprehension
Answer location: Verifying Causal Assertions
Question type: MC

12. _______________ is the extent to which the results of a study can be generalized across populations,
times, and settings, is the touchstone for natural and social scientists alike.
*a. External validity
b. External reliability
c. Internal validity
d. Internal reliability
Learning objective number: 6.1 Explain the ways in which causal assertions can be verified
Cognitive domain: Comprehension
Answer location: Verifying Causal Assertions
Question type: MC

13. A ______________ is a cross-sectional design that introduces a time element.

*a. Panel study
Learning objective number: 6.6 Summarize different types of observational studies, such as small-N
designs and cross-sectional designs
Cognitive domain: Knowledge
Answer location: Observational Studies
Question type: FIB
14. One difficulty with panel studies is that individuals may die, move away, or decide to drop out of the
study—what researchers refer to as ____________.
*a. Mortality
Learning objective number: 6.6 Summarize different types of observational studies, such as small-N
designs and cross-sectional designs
Cognitive domain: Knowledge
Answer location: Internal Validity
Question type: FIB

15. The group that receives the treatment or test stimulus or factor under study is called the
a. Comparative group
b. Control group
c. Simulation group
*d. Experimental group
Learning objective number: 6.2 Identify the types and characteristics of randomized experiments
Cognitive domain: Comprehension
Answer location: Verifying Causal Assertions
Question type: MC

16. ________ designs are characterized by the availability of measures of variables at different points in
time.
*a. Longitudinal (or time series)
Learning objective number: 6.7 Relate the benefits of times series design
Cognitive domain: Knowledge
Answer location: Longitudinal (Time Series) Designs
Question type: FIB

17. How can you distinguish between causal relationships and spurious relationships?
*a. The research must demonstrate that the alleged cause, X, does, in fact, covary with the supposed
effect, Y. The research must show that the cause preceded the effect: X must come before Y in time. After
all, can an effect appear before its cause? Finally, the research must eliminate possible alternative causes,
sometimes termed confounding factors. The research must be conducted in such a way that all possible
joint causes of X and Y have been eliminated.
Learning objective number: 6.1 Explain the ways in which causal assertions can be verified
Cognitive domain: Application
Answer location: Casual versus Spurious Relationships
Question type: SA

18. What is the difference between causation and correlation? In your answer, please give an example.
*a. In social science research as well as common parlance, a “correlation” is simply a statement that two
things are related. If you see one, chances are that you will see the other. But that’s the extent of the
information carried by the statement of correlation. A causal declaration, by contrast, communicates much
more. A change in the state of one thing brings about (in full or in part) a change in the state of another. It
carries with it claims about time order and the elimination of alternative explanations for the observed
relationship. The student should provide an example that demonstrates this difference.
Learning objective number: 6.1 Explain the ways in which causal assertions can be verified
Cognitive domain: Application
Answer location: Causality versus Correlation
Question type: SA

19. What causes a spurious relationship?

*a. A spurious relationship arises because two things, such as viewing negative ads and voting, are both
affected by some third factor and thus appear to be related. Once this additional factor has been identified
and controlled, the original relationship weakens or disappears altogether.
Learning objective number: 6.1 Explain the ways in which causal assertions can be verified
Cognitive domain: Application
Answer location: Casual versus Spurious Relationships
Question type: SA

20. Please identify the most important potential problem with an experimental research design that
measures post-test responses one week after pre-test responses.
*a. The most important potential problem is that the researcher cannot control the environment during the
intervening week and thus the researcher cannot attribute all variation to the test stimulus. It is possible
that extraneous factors have affected the respondents.
Learning objective number: 6.2 Identify the types and characteristics of randomized experiments
Cognitive domain: Application
Answer location: Cross-Sectional Designs
Question type: SA

21. Please explain how an intervention analysis works. In your answer make sure to address when the
dependent variable is measured and how the independent variable is introduced.
*a. An intervention analysis is a nonexperimental time series design, or “interrupted time series analysis,”
where measurements of a dependent variable are taken both before and after the “introduction” of an
independent variable. Here we speak figuratively: as with the other nonrandomized designs, the
occurrence of the independent variable is observed, not literally introduced or administered. We could
observe, for instance, the annual poverty rate both before and after the ascension of a leftist party to see if
regime change makes any difference on living standards. The premeasurements allow a researcher to
establish trends in the dependent variable that are presumably unaffected by the independent variable so
that appropriate conclusions can be drawn about post-treatment measures.
Learning objective number: 6.5 Describe intervention analysis
Cognitive domain: Application
Answer location: Intervention Analysis
Question type: SA

22. Why are experimental designs generally better for making causal inference than nonexperimental
designs?
*a. A nonexperimental design is a strategy for collecting information and data that will be used to test
hypotheses and, if possible, make causal inferences. Such a design is characterized by at least one of the
following: presence of a single group, lack of control over the assignment of subjects to groups, lack of
control over the application of the independent variable, or inability to measure the dependent variable
before and after exposure to the independent variable occurs. Because of these factors, causal inferences
made using nonexperimental designs are not as strong as those possible through the classical randomized
controlled experiment.
Learning objective number: 6.6 Summarize different types of observational studies, such as small-N
designs and cross-sectional designs
Cognitive domain: Application
Answer location: The Classical Randomized Experiment
Question type: SA

23. How would you design an experimental research design? Please use a substantive example in our
answer.
*a. Students’ answers will vary based on the context of their chosen example. But, the answers should
reference each of the five basic characteristics referenced in the chapter. 1. The experimenter establishes
two groups: an experimental group (there can be more than one) that receives or is exposed to an
experimental treatment, or test stimulus or factor; and a control group, so named because its subjects do
not undergo the experimental manipulation. 2. Equally important, the researcher randomly assigns
individuals to the groups. The subjects do not get to decide which group they join. The random
assignment to groups is called randomization, and it means that membership is a matter of chance, not
self-selection. 3. The researcher controls the administration or introduction of the experimental treatment
(the test factor)—that is, the researcher can determine when, where, and under what circumstances the
experimental group is exposed to the stimulus. 4. In an experiment, the researcher establishes and
measures a dependent variable—the response of interest—both before and after the stimulus is given. The
measurements are often called pre- and post-experimental measures, and they indicate whether or not
there has been an experimental effect. An experimental effect, as the term suggests, reflects differences
between the two groups’ responses to the test factor. 5. The environment of the experiment—that is, the
time, location, and other physical aspects—is under the experimenter’s direction. Such control means that
he or she can control or exclude extraneous factors, or influences, besides the independent variable that
might affect the dependent variable. If, for instance, both groups are studied at the same time of day, any
differences between the control and experimental subjects cannot be attributed to temporal factors.
Learning objective number: 6.2 Identify the types and characteristics of randomized experiments
Cognitive domain: Application
Answer location: The Classical Randomized Experiment
Question type: E

24. Please discuss the advantages and disadvantages of an experimental design with respect to internal
and external validity.
*a. Statistical theory tells us that experiments conducted properly can lead to valid inferences about
causality. In this context, however, validity has a particular meaning, namely, that the manipulation of the
experimental or independent (delete extra spaces) variable itself, and not some other variable, influenced
the dependent variable. This kind of validity is known as internal validity, which means the research
procedure demonstrated a true cause-and-effect relationship that was not created by spurious factors.
Social scientists generally believe that a randomized controlled experiment has strong internal validity.
Several things, however, can affect internal validity, including history, maturation, testing with a pre and
post-test, selection bias, experimental mortality, instrument decay, or demand characteristics. While each
of these factors represents a potential pit fall for an experiment when it comes to internal validity, the
experimental design generally has very good internal validity. But, even if we devised the most rigorous
laboratory experiment possible, some readers still might not be convinced that we have found a cause-
and-effect relationship that applies to the real world. The concern is a lack of external validity, the extent
to which the results of an experiment can be generalized across populations, times, and settings. The most
common external validity objection is that experimental results may not be found using a different
population.
Learning objective number: 6.2 Identify the types and characteristics of randomized experiments
Cognitive domain: Application
Answer location: Internal Validity
Question type: E

25. What are the key differences between a multiple group experiment and a classical randomized
experiment with only two groups?
*a. The only difference between a classical randomized experiment and multiple group experiment is that
in a multiple group design more than one experimental or control groups are created so that different
levels of the experimental variable can be compared. This is useful if the independent variable can assume
several values or if the researcher wants to see the possible effects of manipulating the independent
variable in several different ways—or test multiple treatments. Multiple group designs may involve a
post-test only or both a pre-test and a post-test. They may also include a time series component.
Learning objective number: 6.2 Identify the types and characteristics of randomized experiments
Cognitive domain: Application
Answer location: Multiple-Group Design; The Classical Randomized Experiment
Question type: E