Question 1

Selection bias is when subjects develop or change during the experiment as part of an ongoing process independent of the experimental treatment.

Accepted Answer

Selection bias is actually a bias that occurs when the selection of subjects is not random, leading to a sample that is not representative of the population being studied. The statement in the question is actually describing a different type of bias known as maturation bias.

Question 2

Field experiments conducted to evaluate social programs can also involve issues of informed consent.

Accepted Answer

Field experiments may involve testing interventions on individuals or communities without their full knowledge or consent. It is important to ensure that participants are fully informed about the experiment and have the opportunity to opt out if they so choose. This can be a complex issue, especially when the experiment involves vulnerable populations or potential harms.

Question 3

Time Series designs include several pretest and posttest observations, allowing the researcher to study the process by which an intervention has an impact over time.

Accepted Answer

Time Series designs involve multiple observations over time, which allows researchers to track the effects of an intervention or treatment over time. This pretest/posttest approach is a key feature of Time Series designs.

Question 4

In longitudinal research designs, data are collected at one point in time.

Accepted Answer

In longitudinal research designs, data are collected at multiple points in time over a period of months or years.

Question 5

The difficulty of establishing nonspuriousness does not rule out using nonexperimental data to evaluate causal hypotheses.

Accepted Answer

While establishing nonspuriousness is important for establishing causality with nonexperimental data, it is still possible to use such data to evaluate causal hypotheses with appropriate controls and statistical techniques.

Question 6

The Hawthorne effect is named after a famous productivity experiment outside Chicago. Workers were moved to a special room for a study of the effects of lighting intensity and other work conditions on their productivity. After this move, the workers began to increase their output no matter what change was made in their working conditions, even when the conditions became worse. The researchers concluded that the workers felt they should work harder because they were part of a special experiment.

Accepted Answer

This is a correct description of the Hawthorne effect, which refers to the phenomenon of people changing their behavior when they know they are being observed or studied.

Question 7

If researchers are evaluating the effectiveness of a mandatory arrest policy in decreasing incidents of intimate partner assault and a high profile murder trial involving intimate partners is taking place at the same time, it may compromise the results.

Accepted Answer

The high profile murder trial could potentially influence public perception of the effectiveness of the policy and affect the behavior of law enforcement and victims, making it difficult to accurately evaluate the policy's impact.

Question 8

The regression effect is a source of causal invalidity that occurs when subjects who are chosen for a study because of their extreme scores on the dependent variable become less extreme on the posttest due to natural cyclical or episodic change in the variable.

Accepted Answer

This statement accurately describes the regression effect.

Question 9

Quasi-experimental designs are considered quasi-experimental because subjects are not randomly assigned to the comparison and experimental groups.

Accepted Answer

Quasi-experimental designs lack random assignment, which is a key feature of true experimental designs.

Question 10

A true experiment is an experimental study conducted in a real-world setting.

Accepted Answer

A true experiment is an experimental study conducted in a controlled setting where the researcher manipulates one or more independent variables to observe their effects on a dependent variable. It is not conducted in a real-world setting, but rather in a laboratory or other controlled environment.

Question 11

Experimental and comparison groups in ex post facto control group designs are created by random assignment.

Accepted Answer

In ex post facto control group designs, the groups are not created by random assignment but rather by naturally occurring differences or classifications, such as gender or age.

Question 12

A problem with tracking people in research for several years is that it is extremely expensive.

Accepted Answer

Longitudinal studies that track people over several years involve continuous data collection, follow-up interviews, and other expenses, making them very expensive.

Question 13

The Solomon four-group design is a version of a quasi-experiment.

Accepted Answer

The Solomon four-group design is a true experimental design, not a quasi-experimental design, because it includes random assignment of participants to groups, allowing for the control of pretesting effects.

Question 14

Testing, maturation, and regression effects are generally a problem in true experiments.

Accepted Answer

True experiments are designed to control for these effects through random assignment and controlled conditions, minimizing the impact of testing, maturation, and regression effects on the results.

Question 15

When comparison group members become aware that they are being denied some advantage, they may increase their efforts to compensate, creating a problem called the Sam Johnson effect.

Accepted Answer

The correct term for this phenomenon is the John Henry effect, not the Sam Johnson effect. It occurs when control group participants in an experiment increase their efforts because they know they are not receiving the intervention being tested.

Question 16

The only way to reduce the placebo effect in social science research is to treat the comparison group with something similar.

Accepted Answer

The placebo effect arises when a participant's belief in the treatment causes an improvement in their condition. In order to reduce the placebo effect, the comparison group should be treated with a similar intervention that may produce some effect but without the active ingredient of the treatment being tested. This way, any improvement seen in the treatment group can be attributed to the active ingredient of the treatment rather than the placebo effect.

Question 17

Subjects who can be recruited for a laboratory experiment, randomly assigned to a group, and kept under carefully controlled conditions for the study's duration are a representative sample of any large population of interest.

Accepted Answer

While laboratory experiments can provide valuable insights into cause and effect relationships, the small and non-random sample of individuals in such experiments may limit the generalizability of findings to the larger population of interest. Therefore, a laboratory experiment may not necessarily provide a representative sample.

Question 18

Lo, Kim, and Cheng (2008) did cross-sectional research in order to determine if certain offenders were more likely to repeat the same crimes or commit different crimes.

Accepted Answer

The statement accurately reflects the research conducted by Lo, Kim, and Cheng (2008).

Question 19

Carrington and Schulenberg's (2008) study of the effect of the Youth Criminal Justice Act (YCJA) of 2002 in Canada on police discretion with apprehended young offenders illustrates a cross-sectional design.

Accepted Answer

Carrington and Schulenberg's study is an example of a longitudinal design, as it examines changes over time, specifically the impact of the YCJA on police discretion before and after its implementation in 2002.

Question 20

True experiments are particularly well suited to producing valid conclusions about generalizability.

Accepted Answer

True experiments are best suited for establishing cause-and-effect relationships, not necessarily for generalizing findings to broader populations. Generalizability is more related to how representative the sample is of the larger population.

Quiz 6: Causation and Experimentation