Exam 7: Experiments

Time series designs preferably include at least how many observations in both pretest and posttest periods?

What is a reason that a true experimental design may not be feasible?

In ex post facto control group designs,comparison groups are assigned prior to treatment.

Which of the following is NOT an example of endogenous change,in which internal validity is compromised because of natural developments in the subjects,independent of experimental treatment?

Which of the following is FALSE about a factorial survey.

A university conducts a series of surveys in which subjects are drawn from first year and graduating students and finds that graduating students demonstrate much higher rates of approval for the university (in terms of whether they think the classes were relevant,the instructors were competent,etc.).The university then claims that more experience with the university leads to higher approval.What source of internal invalidity has the university not considered?

In an experiment,what provides a good estimate of the counterfactual?

After they had failed in the writing exam that was required for all students before graduation,15 students were placed in a class in which they received additional tutoring.After completing this class,all 15 students retook the exam and earned higher scores.Their success was held up as an example that the class curriculum really works.What source of internal invalidity has not been considered?

The potential for interaction of testing and treatment creates the least concern in which of the following designs.

A fixed sample panel design is the same thing as a before-and-after quasi-experimental design.

Although cross-population generalizability is difficult to achieve using experiments,a true experiment usually has high sample generalizability.

Field experiments allow greater control over conditions than do laboratory experiments.

Why aren't experiments very generalizable? What can be done to improve the external invalidity of experiments?

All true experiments require a pretest and a posttest.

In an experiment,the posttest measures ______.

Researcher V wants to compare similar drunk driving laws in several states.She selects states that have similar median incomes,automobile fatalities per capita,and car ownership per capita.She has attempted to match states using what technique?

True experiments require random assignment of subjects to two or more groups.

A quasi-experimental design is indicated if subjects are not randomly assigned to comparison groups.

Explain at least four different ways to improve generalizability in experimental research.

Time order cannot be assured in nonequivalent control group designs.