Deck 7: Experimental and Quasi Experimental Designs

Question 1

The main reason that experiments in criminal justice are so easy to complete is that the researcher need only secure one experimental and one control group for any project.

Answer 1

False

Question 2

Researchers conduct experiments copiously in an attempt to develop a more generalized understanding about:

A) criminal behavior
B) the sciences
C) the world we live in
D) human behavior

Answer 2

C

Question 3

Which of the following is not a central feature of the classical experiment?

A) variables
B) time order
C) concepts
D) groups

Answer 3

C

Question 4

How many attributes does a dichotomous variable have?

A) 0
B) 1
C) 2
D) 4

Question 5

There may be legal reasons why randomization cannot be used in criminal justice research to assign subjects to either a control group or an experimental group.

Question 6

In the classical experiment subjects are measured on the independent variable before the experiment begins and again after the dependent variable has been manipulated by the researcher.

Question 7

The first decision for selecting subjects for an experiment is:

A) deciding how particular members of the target population will be selected
B) deciding on the target population
C) threats to internal validity
D) threats to external validity

Question 8

Which of the following is least accurate?

A) experimentation is appropriate for hypothesis testing
B) experiments are well suited to research involving well-defined concepts
C) experiments cannot be used in the study of criminal justice policy because they require a hypothesis to test
D) experiments are appropriate for evaluation research

Question 9

Which of the following statements is accurate?

A) to guard against the "Hawthorne effect" in medical research, scientists will give a placebo to the experimental group
B) to guard against the "Hawthorne effect" in medical research, scientists will give the experimental group the independent variable
C) to guard against the "Hawthorne effect" in medical research, scientists will give a placebo to the control group
D) there is no way to guard against the "Hawthorne effect" in medical research

Question 10

Experimentation is an approach to research best suited for exploration.

Question 11

While the interrupted time-series design can be used in cause-and-effect studies, it is really useless in applied studies.

Question 12

The threat of is a concern any time the researcher begins with subjects who exhibit extreme values on the dependent variable.

Question 13

The defining feature of an experiment lies in the control of the independent variable by the experimenter.

Question 14

In case-oriented research a large number of cases are examined in order to understand a small number of variables.

Question 15

Construct validity is concerned with the ability to generalize from the results of the experimental group to the control group.

Question 16

Which of the following is true concerning independent and dependent variables in classical experiments?

A) a variable can be an independent in one experiment and a dependent in another
B) once a variable is designated as an independent variable in one experiment, it can never be used as a dependent variable in another
C) a classical experiment examines the effect of a dependent variable on an independent variable
D) an independent variable in a classical experiment is viewed as the effect because it is dependent upon another variable

Question 17

The independent variable in a classical experiment must be a ratio-level variable.

Question 18

Social science researchers use a control group that hasn't received the experimental stimulus in order to do what?

A) to measure the effect of the independent variable upon the control group
B) as another measure of the effect the independent variable has upon the dependent variable in the experimental group
C) as another measure of the effect the independent variable has upon the dependent variable in the control group
D) to measure the effect of the dependent variable upon the independent variable in the control group

Question 19

Which of the following phrases is most true concerning random assignment to groups?

A) "all other things being equal"
B) "use your best guess"
C) "it is close enough for government work"
D) "you are never 100% sure, so don't worry about it"

Question 20

Which example below is not a random assignment to experimental groups?

A) assign numbers to subjects, put corresponding numbers in a hat and pull out numbers, place the first subject in the experimental group and the second subject in the control group, and continue until all numbers are used
B) ask subjects whether they prefer to be in the experimental group or the control group, and then assign subjects based on their preference
C) flip a coin, assigning subjects getting a head to the control group and those getting a tail to the experimental group
D) use a random number generator after assigning numbers to your subjects

Question 21

The threat to the internal validity of an experiment that is called compensatory treatment refers to which of the following situations?

A) the control group subjects being paid while the experimental group subjects are not
B) the experimental group subjects being paid while the control group subjects are not
C) the subjects in the control group feel deprived of something they consider valuable
D) there is no threat to internal validity called compensatory treatment

Question 22

In an experiment, subjects are given a pretest in an effort to assess their attitudes about a new federal sentencing law that Congress is debating. Subjects assigned to the experimental group are given a series of lectures by experts on the impact the new law will have on prison populations. Immediately after the last lecture, a posttest is given to measure any attitude changes. Anticipating what the test is designed to measure (because of the lectures), those in the experimental group are subject to the threat of:

A) diffusion
B) statistical regression
C) instrumentation
D) testing

Question 23

Two dimensions to generalizability are:

A) construct validity and external validity
B) compensatory rivalry and external validity
C) construct validity and compensatory rivalry
D) none of the above

Question 24

Which of the following is not an accurate example of threats to internal validity of experiments?

A) subjects dropping out of an experiment is a form of mortality
B) creaming is a form of selection bias
C) control group members work harder as a form of compensatory rivalry
D) ability to measure subjects consistently over time

Question 25

The goal of the classical experiment is for the researcher to:

A) have control over the dependent variable
B) have control over the independent variable
C) measure the effect the dependent variable has upon the independent variable
D) make sure the subjects in the control group get the independent variable and those in the experimental group do not

Question 26

Maturation as a threat to internal validity in experiments refers to:

A) some subjects are older than others
B) as people grow and change, results can be impacted
C) only subjects over the age of 21 are mature enough to be part of an experiment
D) none of the above

Question 27

When using a nonequivalent-groups design the researcher will handle subject assignment to groups by:

A) random assignment to experimental and control groups
B) allowing subjects to pick which group they want to be in
C) matching subjects in the experimental group to those in the comparison group
D) convenience

Question 28

In Widom's study of the effects of child abuse and its impact upon later criminal offenses, she selected a sample of children with court records of being abuse victims and gathered a comparison group that was matched on gender, race, age, and socioeconomic status. The technique used in this case was:

A) individual matching
B) aggregate matching
C) randomization
D) all of the above

Question 29

Essentially, an experiment examines the effect of:

A) the world we live in
B) modern science
C) an independent variable on a dependent variable
D) science on sociology

Question 30

You have just completed the LSAT and scored 112. Your roommate who is no smarter than you took the LSAT with you and scored 165. You were so upset with your score that you decided to take the test again and you convinced your roommate to take it with you for moral support. You both received scores on the second exam of 150. What accounted for the differences in scores?

A) statistical regression
B) testing
C) instrumentation
D) maturation

Question 31

Experimentation is best suited for hypothesis testing in:

A) explanatory studies
B) evaluation studies
C) physical studies
D) both explanatory and evaluation studies

Question 32

The threat of history refers to:

A) that some subjects with have had history classes and others have not
B) the realization that some subjects have learned from history while others have not
C) events external to the experiment that will impact the results
D) the fact that only current, relevant subjects need to be studied

Question 33

Which of the following is accurate?

A) threats to internal validity are increased by carefully controlling conditions
B) threats to external validity are decreased by carefully controlling conditions
C) threats to generalizability of research findings in experiments are unrelated to internal validity
D) threats to external validity are increased by carefully controlling conditions

Question 34

Which of the following would be an example of selection bias?

A) volunteers
B) random assignment to experimental and control groups
C) matching of experimental and comparison groups
D) making sure that the quotas are the same for the experimental and comparison groups with respect to important variables

Question 35

Sometimes it is not possible to separate subjects from experimental and control groups and the result is that they may discuss the research. What is the threat that this situation poses?

A) causal time order
B) experimental mortality
C) diffusion or imitation of treatments
D) statistical regression

Question 36

Which of the following is not considered a threat to internal validity in an experimental design?

A) maturation
B) instrumentation
C) randomization
D) statistical regression

Question 37

Which of the following would be an example of experimental mortality?

A) a subject deciding that he/she wants to participate
B) inmates in an experiment at the state maximum-security prison being moved to a minimum-security state prison
C) police officers within one year of retirement participating in a job-satisfaction study
D) police officers changing their behavior during a study because of a new law that was passed

Question 38

Graduates majoring in criminal justice and graduates majoring in psychology from the state university were part of a study to assess the employment success of those receiving their degrees in May 2002. Six months after graduation, a questionnaire was sent out asking about their job-seeking success. What type of design is this?

A) a double-blind experiment
B) a nonequivalent groups design
C) a time-series design
D) a cohort design

Question 39

Shortening the time between pretest and posttest or perhaps even offering cash payments to participants in an experiment are techniques that may be used to:

A) limit diffusion
B) decrease experimental mortality
C) decrease the effects of instrumentation
D) control threats to testing

Question 40

A group of students who completed a research methods class at the local college were given a questionnaire to assess their feelings about the homeless and after were randomly assigned to either the experimental group or the control group. The experimental group was required to volunteer at the local homeless shelter while the control group was not. After one month of volunteering, members of both groups were asked to complete the questionnaire on feelings concerning the homeless again. What type of research design is this?

A) a quasi-experimental design
B) a classical experimental design
C) a time-series design
D) an interrupted time-series design

Question 41

Dr. Smith was interested in whether there would be a reduction in the number of crimes in the central city once closed-circuit cameras went up and were monitored by police. To accomplish this study, Dr. Smith looked at the police records for the four-square-block area where the cameras were installed each week for six months. Dr. Smith was using what method?

A) cohort design
B) time-series design
C) classical experiment
D) quasi-experimental design

Question 42

To assess the impact of child abuse upon later criminality, Dr. Rose chose to select some adults whose names appeared as child abuse victims in local police records and another group of adults who were not victims of abuse. What technique is being employed?

A) cohort design
B) classical experiment
C) double-blind experiment
D) nonequivalent-group design

Question 43

Which is accurate concerning the interrupted time-series design?

A) some event stops or interrupts the research
B) control group subjects are often envious of the attention the experimental group subjects get and interrupt the study
C) makes a long series of observations before and after introducing the experimental treatment
D) none of the above are accurate

Question 44

What process is accomplished by assigning the odd-numbered subjects to the experimental group and the even-numbered subjects to the control group?

A) basic scientific theory
B) independent relation
C) false positive evaluation
D) random assignment

Question 45

When neither the subjects nor the researcher can identify which group is the control group and which is the experimental group, the design is said to be:

A) cross-sectional
B) double-blind
C) a blind experiment
D) of no value

Question 46

The classical experiment makes it possible to satisfy the criterion for cause in two ways. First, the posttest measures for the experimental group (stimulus present) are compared with those for the:

A) control group (stimulus not present)
B) random group (stimulus not present)
C) variable group (stimulus not present)
D) none of the above

Question 47

In social scientific experiments, as in medical experiments, the danger of experimenter bias is further reduced to the extent that the operational definitions of the dependent variables are:

A) clear and precise
B) controlled
C) tested and retested
D) scientifically proven

Question 48

Which of the following statements is true?

A) nonequivalent-groups and time-series designs are two general types of quasi-experiments
B) experiments and time-series designs are two general types of quasi-experiments
C) all research purposes are amenable to the use of experimental designs
D) all of the above are true

Question 49

What technique can be used to help reduce the threat to experimental mortality?

A) increasing the sample size
B) decreasing the sample size
C) shorten the time between the pretest and the posttest
D) select only subjects who are female

Question 50

If randomization is not possible, what should the researcher do?

A) pre- and posttest
B) use the classical design
C) consider using a quasi-experimental design
D) randomization is always possible

Question 51

What can help rule out the threats to internal validity in an experimental design?

A) proper selection and assignment of subjects to groups
B) large sample size
C) small sample size
D) nothing can rule out threats to internal validity

Question 52

A questionnaire is sent to 1,000 police departments in Florida and gathers information on the number of sick days officers use after being involved in a shooting incident. This is an example of what type of research?

A) variable-oriented research
B) case-oriented research
C) experimental design
D) cohort design

Question 53

An interrupted time-series design can be very useful in what type of research?

A) applied research
B) exploratory research
C) descriptive research
D) double-blind research

Question 54

What type of design is illustrated in the following diagram? Experimental Group 0 X 0
Control Group 0 0
Measurement time1 time2 time3

A) time-series design
B) classical experiment
C) cohort design
D) nonequivalent-groups design

Question 55

In criminal justice experiments, what serves as a guard against the effects of the experiments themselves as well as events that may occur outside the laboratory during the course of experiments?

A) variable groups
B) control groups
C) administrative groups
D) posttest groups

Question 56

The statement, "there are no simple formulas for designing an experimental or quasi-experimental study" suggests:

A) that there is an infinite variety of ways to design a study
B) that there is a finite variety of ways to design a study
C) that the one constant is the use of randomization in experiments
D) experiments and quasi-experiments should be used only as a last resort

Question 57

External validity in an experimental design refers to:

A) the researcher's ability to be sure that they are measuring what they think they are measuring
B) the lack of concern with issues internal to the study
C) the ability to apply findings to other populations
D) the ability to know your measures are consistent

Question 58

To guard against most threats to internal validity in the classical experiment the researcher should:

A) focus upon external validity
B) focus upon generalizability
C) use random assignment
D) put subjects only in experimental groups

Question 59

The central features of what experiment type include (1) independent and dependent variables, (2) pretesting and posttesting, and (3) experimental and control groups created through random assignment?

A) casual experiments
B) statistical experiments
C) classical experiments
D) cardinal experiments

Question 60

How does a cohort design differ from other quasi-experimental designs?

A) the use of random assignment to control and experimental groups
B) the use of matching to assign subjects to control and experimental groups
C) there is some date or event in common to all members of the control and the experimental groups
D) all quasi-experimental designs are basically the same

Question 61

Which of the following is not illustrative of the case-study method?

A) it is an in-depth analysis of one or a few cases
B) the cases can be individuals, groups, organizations, or aggregates
C) the study can be both qualitative and quantitative
D) it is observing a group who has similar cases in the court systems

Question 62

How can a researcher be sure that threats to internal validity are being ruled out in the design?

A) sorting out what threats are applicable in which settings
B) comparing the results of several posttests
C) random selection will rule out, or greatly reduce, the chances for statistical regression
D) all the above

Question 63

When it is not possible to create groups through randomization, what options do you have for the research design?

A) a classical experiment
B) nonequivalent groups
C) surveys
D) pre- and posttests

Question 64

With respect to internal validity issues, testing refers to changes in how subjects respond to measurement while ____________________ refers to changes in the measurement process itself.

Question 65

In general, testing refers to changes in how subjects respond to measurement, whereas instrumentation is concerned with:

A) the world we live in
B) changes in the measurement process itself
C) the scientific hypothesis
D) the motive for the experiment itself

Question 66

In a classical experiment the researcher uses a ____________________ to offset the effects of the experiment itself.

Question 67

A(n) ____________________ experiment guards against experimenters' tendency to prejudge results by eliminating the possibility of either the researcher or the subjects knowing which group is the control and which group is the experimental.

Question 68

In the case where the experimental groups and the control groups are not equivalent, which of the following should not be used to address this issue?

A) proceed with the experiment because you can address the issues during your statistical analysis
B) match the groups on important variables
C) use comparison groups instead of control groups
D) match groups on any variables that are significant for the fluctuation in the dependent variable

Question 69

When random assignment to experimental and control groups is not possible the researcher may be forced to use a(n) ____________________ design.

Question 70

The mere fact that subjects know they are being studied can cause them to change their behavior. This phenomenon is known as the ____________________.

Question 71

In Martin Gill's research on the effectiveness of CCTV projects in the UK, which of the following techniques did he use?

A) the research measured fear of crime by citizens before and after the cameras went up
B) the research measured police data before the cameras went up
C) comparison was made only in the area where cameras were in use
D) the research measured if the offenders changed the type of crimes they were committing

Question 72

The main reason why ____________________ is used to select subjects for control and experimental groups in a classical experiment is that the groups will be statistically equivalent.

Question 73

In a classical experiment the independent variable is the cause and the dependent variable is the ____________________.

Question 74

____________________ validity becomes an issue when findings are based on small samples of cases.

Question 75

Which of the following would not be likely to impact a study's external validity?

A) do research in the natural setting
B) experiments where there is too much control of conditions
C) using an unrepresentative sample
D) applied studies reduce external validity

Question 76

One threat to internal validity in criminal justice research that is not very significant is

A) history, because few things happen on a grand scale that would impact criminal justice research
B) maturation, because criminal justice subjects are not in research studies long enough to mature
C) statistical regression, because subjects in the criminal justice system are likely to score lower than the mean anyway
D) the concern about the publication of the findings

Question 77

All but which of the following are examples of double-blind studies?

A) medical experiments where a new drug is tested; one group gets the new drug, the other gets a placebo, and the researcher does not know who got which drug
B) domestic violence studies where intervention is designed to reduce repeat offenses by focusing upon victim strategies when the victim does not know whether he or she is in the control or experimental group
C) any study where the researchers and the subjects do not know whether they are in the experimental or control groups
D) any study where the researchers know who is in the experimental and control groups but promise not to tell the subjects

Question 78

When referring to whether results from experiments conducted in one setting would be obtained in other settings, our main concern is one of ____________________ validity.

Question 79

With regard to experimentation and subject selection, what does random assignment serve to eliminate?

A) systematic bias
B) false positive results
C) experimental morality
D) ambiguity

Question 80

Instead of making one pretest and one posttest measure, the ____________________ makes a longer series of observations before and after introducing an experimental treatment.