Deck 14: More About Quasi-Experiments

Question 1

A study was done in Pueblo, CO, to compare the pattern of heart attack rates across the year before and the year after a public smoking ban had been enacted. The researchers who conducted this study used a(n) ______ design.

A) equivalent time series
B) interrupted time series
C) one-group posttest only
D) nonequivalent control group

Answer 1

interrupted time series

Question 2

In a(n) ______ design, the researcher considers the difference between the pretest and posttest scores across the control and experimental groups.

A) nonequivalent time series
B) noninterrupted time series
C) one-group posttest-only
D) nonequivalent groups

Answer 2

nonequivalent groups

Question 3

Quasi-experiments are not experiments because they lack ______.

A) random assignment
B) any type of comparison
C) a dependent variable
D) pre- and posttest

Answer 3

random assignment

Question 4

The Solomon four-group design is a pretest-posttest design where ______.

A) the experimental and control groups are randomly assigned
B) there are two experimental and control groups, one that takes the pretest and one that does not take the pretest
C) a historical event is used at the "treatment"
D) the experimental group is randomly assigned

Question 5

A ______ is a type of research design where behavior is measured both before and after a treatment or condition is implemented.

A) pretest-posttest design
B) Solomon four-group design
C) quasi-design
D) time-series

Question 6

______ occur(s) when participants choose not to complete a study.

A) Attrition
B) Testing effects
C) Group differences
D) Maturation

Question 7

______ would help control for bias in a pretest-posttest design.

A) Increasing the amount of time between the pretest and posttest
B) Including a control group that does not receive the treatment
C) Using fewer subjects
D) Using the posttest scores as the dependent variable

Question 8

An example of a quasi-experiment is ______.

A) two groups of participants (those who are left-handed and those who are right-handed) are asked to perform a speeded cognitive task to compare performance for the two groups
B) participants take a handedness questionnaire with score indicating the degree of right- and left-handedness to look for a relationship between handedness score and time to complete a cognitive task
C) participants are randomly assigned to conditions where a cognitive task is given with speeded or non-speeded instructions to determine if there is an effect of instruction type of task performance
D) participants are randomly assigned to two groups

Question 9

The Solomon four-group design allows a researcher to measure ______.

A) all confounding variables that may be present
B) the effect of taking the pretest on the scores on the posttest
C) group differences between the control and experimental groups
D) the causal effect of the treatment

Question 10

______ occur when participants are tested more than once in a study with early testing affecting later testing.

A) History effects
B) Testing effects
C) Group differences
D) Maturation effects

Question 11

A time series design where the "treatment" is an independent event, such as a historical event is called a(n) ______.

A) equivalent time series
B) interrupted time series
C) one-group posttest only
D) nonequivalent control group

Question 12

Of the following, ______ are not considered a source of bias problematic in pretest-posttest designs.

A) history effects
B) testing effects
C) group differences
D) placebo effects

Question 13

When participants are randomly assigned to levels of the independent variable in an experiment to control for individual differences as an extraneous variable this is called ______.

A) extraneous assignment
B) level assignment
C) random transfer
D) random assignment

Question 14

A non-equivalent pretest-posttest design contains a control group that ______.

A) has been randomly assigned
B) has not been randomly assigned
C) does not take the pretest
D) does not take the posttest

Question 15

A time series design where the "treatment" is implemented by the researcher is called a(n) ______.

A) nonequivalent time series
B) noninterrupted time series
C) one-group posttest only
D) nonequivalent control group

Question 16

In terms of the way data are analyzed, a quasi-experiment is most like ______ research design.

A) experimental
B) correlational study
C) case study
D) phenomenological study

Question 17

Pretest-posttest designs are quasi-experiments when they do not contain a ______.

A) confounding variable
B) dependent variable
C) randomly assigned control group
D) independent variable

Question 18

Of the following, ______ might be a reason a researcher would use a quasi-experiment.

A) more internally valid than experiments
B) easier to design
C) age is their variable of interest
D) more externally valid than experiments

Question 19

Time series designs are pretest-posttest designs that ______.

A) include a randomly assigned control group
B) compare a pattern of scores over time before and after the treatment
C) include groups that do not take the pretest
D) include groups that do not take the posttest

Question 20

The difference between an interrupted time series design and an equivalent time series design is that the interrupted time series design includes a ______ event, while a noninterrupted time series design includes a ______ treatment.

A) psychological; nonpsychological
B) nonpsychological; psychological
C) naturally occurring; researcher implemented
D) researcher implemented; naturally occurring

Question 21

A high score achieved at posttest may be an extreme score in some cases, and with additional testing, these students may score closer to their original mean, this is known as ______.

A) regression toward the mean
B) deterioration
C) unrealistic scores
D) weakening of the mean

Question 22

It would be ______ to randomly assign some participants to smoke in order to conduct an experiment because this would force participants to endure something harmful.

A) ethical
B) unethical
C) perfectly fine
D) wise

Question 23

When researchers are studying differences between soldiers who have been to Iraq and those who have not, the researchers are studying the effects of ______.

A) subject variables
B) convenience variables
C) experimental variables
D) manipulated variables

Question 24

When participants are selected because they have or have not experienced something unique in the real world (e.g., they have lived in a homeless shelter/not lived in a shelter), researchers call this type of independent variable a(n) ______.

A) selected treatment
B) experience treatment
C) subject treatment
D) natural treatment

Question 25

Participants may become more hopeful about their lives if they know they are being treated for depression. This is an example of ______.

A) history effects
B) testing effects
C) group differences
D) maturation effects

Question 26

The Benenson et al. (2009, Study 1) study examined gender as a subject variable because ______.

A) gender cannot be randomly assigned
B) gender could not be concluded as tolerance difference
C) roommate assignments could not be manipulated
D) history effects biased the results

Question 27

Using pretests to organize groups can be problematic because scores on posttest measures may be affected not (just) by the treatment but by ______.

A) history effects
B) regression to the mean
C) nonequivalent groups
D) individual differences

Question 28

Effects of history are ______ to occur in pretest-posttest designs.

A) least likely
B) most likely
C) unlikely
D) not known

Question 29

In the simplest type of pretest-posttest design, a behavior is measured ______.

A) once
B) twice
C) three times
D) four times

Question 30

If participants are randomly assigned to the control group and the treatment group, the study becomes a(n) ______.

A) experiment
B) quasi-experiment
C) qualitative study
D) correlational study

Question 31

Participants may become fatigued or bored with the test after taking it once, exhibiting ______.

A) history effects
B) testing effects
C) group differences
D) maturation effects

Question 32

The best way to minimize the effects of maturation is to include a ______ group that does not receive the treatment to allow a comparison of groups that have similar experiences except for the treatment.

A) control
B) placebo
C) experimental
D) investigational

Question 33

______ are natural changes that occur to the participants during the course of a study that can result in bias.

A) History effects
B) Testing effects
C) Group differences
D) Maturation

Question 34

Quasi-experiments involve comparing groups of non-randomly assigned subjects.

Question 35

Attrition is also called ______.

A) mortality
B) death
C) dropouts
D) abrasion

Question 36

As with pretest-posttest designs, limitations of time series designs exist due to possible ______ factors that can affect a score pattern change other than the treatment or event of interest.

A) independent
B) dependent
C) extraneous
D) control

Question 37

Due to the focus on patterns of scores over time, traditional data analysis techniques are typically inadequate to test hypotheses for the ______ types of designs.

A) pretest-posttest
B) pretest
C) posttest
D) time-series

Question 38

______ can occur when participants score higher or lower than their personal average--the next time they are tested, they are more likely to score near their personal average, making scores unreliable.

A) Regression toward the mean
B) Deterioration
C) Unrealistic scores
D) Weakening of the mean

Question 39

The ______ variable allows comparison of groups of participants without manipulation.

A) quasi-experiment/subject
B) quasi-experiment/participant
C) true experiment/subject
D) true experiment/participant

Question 40

______ are events that occur during the course of a study to all or individual participants that can result in bias.

A) History effects
B) Testing effects
C) Group differences
D) Maturation

Question 41

Attrition results in data being deleted from a study (or a portion of a study).

Question 42

Explain the difference between interrupted and non-interrupted time series designs.

Question 43

Discuss maturation and how it impacts research studies. Please provide examples.

Question 44

Quasi-experiments are the most useful designs for answering causal research questions.

Question 45

Discuss history effects and its impact on research studies. Please provide examples.

Question 46

Discuss the quasi-experiment design of Benenson and Koulnazarian (2008) study to investigate at what age gender differences appear in help-seeking behaviors.

Question 47

An interrupted time series design uses a treatment that is an independent event that the researchers can manipulate.

Question 48

Subject variables are considered experimental variables, while natural treatment variables are considered quasi-independent variables.

Question 49

Explain why quasi-experiments are not as useful as experiments in answering causal research questions.

Question 50

Attrition reduces the validity of the data by making it less generalizable.

Question 51

Inclusion of a control group spreads the attrition (on average) across the groups and allows the researcher to make group comparisons to test the effect of the independent variable.

Question 52

Explain how time-series designs are different from other pretest-posttest designs.

Question 53

Researchers might choose interrupted-time-series designs when they are interested in the effect of a naturally occurring treatment.

Question 54

Research done in educational settings often involves a quasi-experiment, because the researcher cannot affect the classroom students are in or the teacher they have.

Question 55

Many applied studies that examine realistic behaviors make use of quasi-experiments because random assignment would be difficult or impossible or unethical.

Question 56

The researcher compares the scores from the pretest and the posttest, looking for a change based on the treatment or condition occurring in time between the two measurements.

Question 57

Attrition is best handled by inclusion of a control group.

Question 58

Effects of history (and other sources of bias that occur over time) are least likely to occur in pretest-posttest designs.

Question 59

Limitations of time series designs exist due to possible extraneous factors that may affect a score pattern change other than the treatment or event of interest.

Question 60

Random assignment of participants is less likely in time-series designs with a researcher-implemented treatment than an independent event examined in an interrupted time series design.