Social Research Methods: Qualitative and Quantitative Approaches

EXPERIMENTAL RESEARCH

artifacts
classical experimental design
compensatory behavior
confederate
confounding variables
control group
cover story
debrief
deception
demand characteristic
design notation
diffusion of treatment
double-blind experiment
equivalent time-series design
experimental design
experimental group

experimental mortality

experimental realism

experimenter expectancy

external validity

factorial design

field experiment

hawthorne effect

history effects

interaction effect

internal validity

interrupted time-series design

laboratory experiment

latin square design

manipulation check

maturation effect

mundane realism

KEY TERMS

naturalistic generalization

one-shot case-study design

placebo effect

posttest

preexperimental designs

pretest

quasi-experimental designs

random assignment

reactivity

selection bias

solomon four-group design

static group comparison design

statistical regression effect

subjects

testing effect

treatment

for causality. In general, experiments tend to be eas-
ier to replicate, less expensive, and less time
consuming than other research techniques. Experi-
mental research also has limitations. First, some
questions cannot be addressed using experimental
methods because control and experimental manip-
ulation are impossible. Another limitation is that ex-
periments usually test one or a few hypotheses at a
time. This fragments knowledge and makes it

necessary to synthesize results across many re-

search reports. External validity is a potential prob-

lem because many experiments rely on small

nonrandom samples of college students.^16

The chapter explained that careful examination

and comparison of results can alert us to potential

problems in research design. Finally, the chapter

presented some practical and ethical considerations

in experiments.

REVIEW QUESTIONS

1.What are the seven elements or parts of an experiment?

2.What distinguishes preexperimental designs from the classical design?

3.Which design permits the testing of different sequences for several treatments?

4.A researcher says, “It was a three by two design with the independent variables

being the level of fear (low, medium, high) and ease of escape (easy/difficult) and

the dependent variable being anxiety.” What does this mean? What is the design

notation, assuming that random assignment with a posttest only was used?