SOC 262
Research Methods
Miami University-Oxford
In experimentation, a group of subjects to whom no experimental stimulus is
administered and who resemble the experimental group in all other respects. The comparison of the control group and the experimental group at the end of the experiment points to the effect of the experimental stimulus
feelings of deprivation in the control group may result in their giving up, acting up, or getting angry
the variable being measured, so called because it may depend on the manipulations of the independent variable
An experimental design in which neither the subjects nor the experimenters know which is the experimental group and which is the control.
Where the IV is not manipulated by the experimenter but occurs naturally. No casual conclusions can be made from natural experiments.
In experimentation, a group of subjects to whom an experimental stimulus is administered. Compare with control group.
experimental subjects will drop out before the experiment is completed, this can affect statistical comparisons and conclusions.
object of manipulation (independent variable) in an experiment
problem of generalizing experimental results to the "real world"
a formal experiment conducted outside the laboratory, in a natural setting
Occurs when the dependent variable is more affected by the attention given by its being studied than by the actual stimulus itself
A source of internal invalidity in which some events may occur between pretesting and posttesting and which may confound the experimental results.
The manipulated, influential, experimental factor in an experiment
A source of internal invalidity that involves the process of measurement in pretesting and posttesting.
refers to the possibilty that conclusions drawn from the experimental results may not accurately reflect what went on in the experiment itself
Method of selecting subjects. In connection with experiments, the procedure whereby pairs of subjects are matched on the basis of their similarities on one or more variables, and one member of the pair is assigned to the experimental group and the other to the control group
People growing and changing affects the results of the experiment. Long term - grow older (wiser?). Short term - tired, sleepy, bored, hungry, etc.
one-group pretest-posttest design
observation, stimulus, observation. no random assignment, no control group.
Group: X O(observation, stimulus)
participants are exposed to variable and measured to determine the
influence of the manipulation
a "drug" with no relevant effect. control group believes they too are receiving the stimulus
The remeasurement of a dependent variable among subjects after they’ve been exposed to a stimulus representing an independent variable. See pretesting.
The measurement of a dependent variable among subjects before they are exposed to a stimulus representing an independent variable. See posttesting.
A group of designs that deviate from the principles of the classical design. (no control group, no random assignment)
The process used in matching and based on the most relevant characteristics; half of subjects in each cell go into the experimental group and half into the control group.
A technique for assigning experimental subjects to experimental and control groups randomly.
ruled out by the random assignment of subjects
Solomon four-group design
adresses the problem of testing interacting with the stimulus. Four groups of subjects, assigned randomly from a pool. Combines (pretest-posttest and posttest-only) OXO ____ O O XO ____ O
Static-Group Comparison Group
x-o o Experimental and control group, only a posttest, no random assignment, selection and mortality are threats to internal validity
When test units with extreme scores move closer to the average score (mean) during the course of the experiment
process of testing and retesting influences people's behavior, thereby confounding the experimental results
The Practice of Social ResearchChapter Eight. Experiments
THE CLASSICAL EXPERIMENT
Independent and Dependent Variables
Pretesting and Posttesting
Experimental and Control Groups
The Double-Blind Experiment
Experiments are designed to determine the presence or absence of causal relationships: whether a particular independent variable causes (influences, impacts, determines) a particular dependent variable. Does viewing a film on "Women in Science" reduce prejudice against women? In this case, prejudice is the dependent variable. Viewing the film (or not) is the independent variable, called the stimulus in experimental designs.
To determine whether showing the film reduces prejudice, we must measure levels of prejudice before and after: known as pretesting and posttesting.
To be sure that it was the film that caused any reductions in prejudice, we divide the subjects into two groups: (1) an experimental group to whom we administer the stimulus (show the film) and a control group who do not receive the stimulus. If both groups have a reduction of prejudice, it would not appear that the film caused the difference, but if only the experimental group has reduced prejudice, that supports the possibility that the film makes a difference.
If subjects know they are receiving some treatment, they commonly change based on that expectation (e.g., medical patients improve if they think they are receiving a powerful new drug). This is known as the placebo effect, and subjects are never told whether they are in the experimental or control group. Whenever the dependent variable is measured subjectively (e.g., doctors deciding whether patients have improved), there is a risk that their judgments will be affected by expectations about the effect of the stimulus. In a double-blind experiment, neither the subjects nor the experimenters making judgment measurements know whether subjects are in the experimental or control group.