Non-Equivalent Groups Designs

What is the defining characteristic of a nonequivalent groups design?

In a posttest only nonequivalent groups design, what is the most significant threat to internal validity?

How does a pretest-posttest nonequivalent groups design attempt to improve upon the posttest only nonequivalent groups design?

What is meant by 'differential history' as a threat to internal validity in a pretest-posttest nonequivalent groups design?

A researcher studies the effect of a new productivity software. They measure weekly output for 10 weeks in Company A and Company B. After 5 weeks, they introduce the software only in Company A. What type of design is this?

What is the key feature of a pretest-posttest design with switching replication?

What is a major strength of the pretest-posttest design with switching replication?

How does a 'switching replication with treatment removal' design differ from a standard 'pretest-posttest design with switching replication'?

A researcher evaluates a new method of teaching fractions to two third-grade classes. One class gets the new method, the other does not. The researcher compares the scores on the final exam. The classes were not randomly assigned. What is this design?

What additional evidence does the switching replication with treatment removal design provide that a standard switching replication design does not?

In a study on a new teaching method, a researcher selects two classes at the same school, ensures the students have similar standardized math scores, and that the teachers have similar experience. Why are these steps taken?

Why might a pretest-posttest nonequivalent groups design fail to completely eliminate the possibility of confounding variables?

In a pretest-posttest design with switching replication to test an exercise intervention for depression, researchers find that depression decreases in both the patient group and the student control group after the first phase of treatment is given only to patients. What is the most likely explanation?

An interrupted time-series design with nonequivalent groups is an improvement on a simple interrupted time-series design primarily because it adds what component?

Which design provides the strongest evidence for the efficacy of a treatment by demonstrating an effect in two different samples and also showing that the effect reverses when the treatment is withdrawn?

If participants in a pretest-posttest nonequivalent groups design were randomly assigned to their conditions, what would the design become?

A researcher studies two groups of patients with depression. Group A receives an exercise intervention for 4 weeks. Group B does not. After 4 weeks, depression is measured. Then, the intervention is removed from Group A and given to Group B for 4 weeks, after which depression is measured again in both. What is this design called?

What is the primary reason researchers consider groups to be 'nonequivalent' in the designs discussed in Chapter 39?

In a posttest only nonequivalent groups design, a principal assigning 'troublemakers' to one teacher's class and not another introduces what specific problem?

A study on an anti-drug program gives a pretest to students in School A and School B. School A gets the program, School B does not. Both get a posttest. If a celebrity drug overdose occurs and is widely publicized between the pretest and posttest, how would this design help interpret the results?

Which of the following remains a potential threat to internal validity in a switching replication design, according to Chapter 41?

The posttest only nonequivalent groups design consists of how many distinct groups?

In a pretest-posttest nonequivalent groups design, how many measurement points are there for the control group?

In a pretest-posttest design with switching replication involving two groups, when is the third major assessment of the dependent variable conducted?

How many groups are required at a minimum to conduct an interrupted time-series design with nonequivalent groups?

If a researcher conducts a switching replication with treatment removal design with two groups, and finds that depression decreased in the student group after they started exercising but increased in the patient group after they stopped exercising, what does this suggest?

All of the designs discussed in Chapter 39 are considered what type of design?

What is the primary goal of adding a pretest in the pretest-posttest nonequivalent groups design?

In the example of evaluating a new measure for teaching third graders, the text notes that even with a pretest, teachers' styles and classroom environments could still be very different. These are examples of what?

An interrupted time-series design with nonequivalent groups involves taking 20 measurements in the treatment group and 20 measurements in the control group. How many of these measurements in the control group occur after the intervention is introduced in the treatment group?

The key benefit of adding a 'switching replication' to a pretest-posttest design is that it provides better control over which threat to internal validity?

What is the primary logic behind the 'treatment removal' aspect of the switching replication with treatment removal design?

Which nonequivalent groups design is described as being a between-subjects design where participants are not randomly assigned, one group is exposed to a treatment, another is not, and then the two groups are compared?

Imagine a study where one factory reduces work shifts from 10 to 8 hours, and a nonequivalent control factory does not. Productivity is measured weekly for a year. What is this design called?

A study measures depression in a group of patients and a group of students. Patients get an exercise intervention, students do not. Depression is measured again. Then, the students also begin the exercise intervention. Depression is measured a final time. What is this design called?

If a researcher finds that asbestos in one school caused a month-long shutdown during a study, this would represent what kind of threat to a pretest-posttest nonequivalent groups design?

Why do researchers consider nonequivalent groups 'dissimilar in some ways'?

Which design involves a treatment group and a nonequivalent control group, where both are given a pretest and a posttest, but the control group never receives the treatment?

In a pretest-posttest design with switching replication, what helps to control for instrumentation effects?

If a study uses a switching replication with treatment removal design involving two groups, how many distinct phases of treatment administration are there (including no treatment)?

The use of a nonequivalent groups design is a feature of what broader category of research?

In a posttest only nonequivalent groups design, why is it problematic if parents of higher achieving students requested their children be assigned to the treatment group's class?

An interrupted time-series design with nonequivalent groups could be improved by adding a switching replication. How many groups would be needed for this improved design?

Which of the five types of quasi-experimental designs that are between-subjects in nature mentioned in the Key Takeaways (Chapter 40) is NOT explicitly detailed in the main body of Chapter 39?

Which design would be most appropriate for evaluating the effect of a new, permanent surgical procedure on patient outcomes using a control group, when random assignment is not possible?

A researcher improves an interrupted time-series design by locating another manufacturing company that does not plan to change its shift length to use as a nonequivalent control group. What is the primary benefit of this addition?

What is the minimum number of measurement points for a single participant in a pretest-posttest design with switching replication involving two groups?

In a switching replication with treatment removal design, if the depression levels of the patient group do NOT increase after the exercise intervention is removed, what could this suggest?

According to the Key Takeaways of Chapter 40, which of the quasi-experimental designs are considered highest in internal validity?

What is the total number of groups involved in a pretest-posttest design with switching replication?