Study Guides (299,274)
CA (140,867)
UTSG (9,787)
SOC (726)

master notes soc 200.doc

114 pages62 viewsFall 2012

Department
Sociology
Course Code
SOC200H1
Professor
Margaret Gassanov;

This preview shows pages 1-3. to view the full 114 pages of the document.
15/12/2012 21:25:00
Chapter 8
Experiments
Three major pairs of components in an experiment:
Independent and Dependent Variable
The independent variable is dichotomous variable (having two attributes, present or not
present) in an experiment
They experiment to see what happens when the independent variable is present or not
present
Independent and dependent variables must be operationally defined (ie. a questionnaire to
define what prejudice means)
Pretesting and Posttesting (that’s actually how it’s supposed to be spelled)
Pretesting: the measurement of a dependent variable among subjects before they are
exposed to a stimulus representing an independent variable
Posttesting: The remeasurement of a dependent variable among subjects after they have
been exposed to a stimulus representing an independent variable
Example: testing a groups prejudice toward aboriginals (pretesting), then making them
watch a Aboriginal history movie, then after having them retested (posttesting) to see if their
attitudes changed after being educated (the variable)
Experimental and Control groups
Experimental groups: In experimentation, a group of subjects to whom an experimental
stimulus is administered
Control group: Should resemble the experimental group in every aspect, but which does
not receive the experimental stimulus
Using a control group allows the researcher to detect any effects of the experiment itself
on the subjects
Trying to avoid a great deal of the Hawthorne effect: any impact of research on the
subject of study
The Double Blind Experiment : An experimental design in which neither the subjects nor
the experiments know which is the experimental group and which is the control.
Selecting Subjects
Probability Sampling
Using a sampling frame, select two probability samples that represent the total population
(of the study) and represent each other
Seldom used
Randomization
Randomly assigning experimental subjects to experimental and control groups
1
You're Reading a Preview

Unlock to view full version

Only half of the first page are available for preview. Some parts have been intentionally blurred.

Page 2
Matching
The procedure when pairs of subjects are matched on the basis of their similarities in one
or more variables, then one member of the pair is assigned to the experimental group and the
other to the control
Variation on Experimental Design: Donald Campbell and Julian Stanley
Pre-Experimental Research Designs (Illustration on page 233 Figure 8-3)
One-Shot Case Study: Surveying people that watched the Aboriginal History movie, and
the answers to the questionnaire seem to show a low level of prejudice. We can’t be sure this is
true because there is no pretest that proves watching the movie is the independent variable to
reducing prejudice
One Group Pretest-Posttest Design: This now adds a pretest for the experimental group
but now lacks a control group (can no long tell the effects of being researched on the group)
Static Group Comparison: (no pretest) Showing the Aboriginal History movie to one
group and not the other to measure to see if the movie made a difference, but the separate groups
may have toatally different levels of prejudice coming in that is unknown
Validity Issues in Experimental Research
Sources of Internal Validity
Internal Validity: refers to the possibility that the conclusions drawn from experimental
results may not accurately reflect what went on in the experiment itself
The threat of internal validity is present whenever anything other than the experimental
stimulus can affect the dependent variable
Twelve of the Several Sources of Internal Validity by Cambpell, Stanley and Cook
History: The beating of an Aboriginal leader during the time of this experiment
Maturation: In a long term experiment subjects opinions will grow and have an effect on
the experiment. In a short one they may grow tired and effect their behavior
Testing: By testing and retesting many times the subjects will grow to be more sensitive
to the issue ands give more thoughtful answers (ie. don’t want to appear prejudice)
Instrumentation: Using different measures in the pre and posttest questionnaire, may
bring different outcomes
Statistical Regression: Like interviewing someone at an extreme, example: having
someone with a low score, they can only get better or stay at that level, they can’t get worse
Selection Biases: Making an assumption on who should go to one group or another
without testing it
Experimental Morality: If someone drops out of the experiment mid way in it will affect
the results
2
You're Reading a Preview

Unlock to view full version

Only half of the first page are available for preview. Some parts have been intentionally blurred.

Page 3
Causal Time Order: When there is ambiguity about what the dependent and independent
variables are
Diffusion or Imitation of Treatments: When subjects can communicate with each other
and pass on ideas or information that could affect the experiment
Comprehension: When you give something extra to one group and not to the other in real
life experiments (ie more care)
Compensatory Rivalry: One group knowing there is a difference and trying to work
harder to be as good as the other group (this one is so stupid idk why they would even know
about each other hmm)
Demoralization: If one group feels deprived of an aspect of help
Sources of External Invalidity
External Validity: the possibility that conclusions drawn from the experimental results
may not be generalizable to the “real” world
Expectations of the research (Group 1 watches the aboriginal movie, Group 2 does not)
Figure 8-5 page 237
In Group 1 the Posttest prejudice should be less than the pretest prejudice
In Group 2 the Prejudice should be the same in the pretest and posttest
In Group 1 posttest should show less prejudice than the Group 2 posttest
The Group 3 posttest should show less prejudice than the Group 4 posttest
Natural Experiments
Occur in the course of social life in the real world, and social researchers can implement
them in somewhat the same way they could design and conduct laboratory experiments
Web Based Experiments
Increasingly common for researchers to use the Web as a place to conduct social science
experiments
Strength and Weaknesses of the Experimental Method
Primary weakness is Artificiality: What happens in the experiment may not reflect what
happen in the real (outside) world
The strengths though include: scientific rigor, the isolation of the independent variable,
the isolation of the independent and dependent variable (which allows causal interference) and
the ease of replication
Chapter 8: Experiments
The Classical Experiment
Independent & Dependent Variables
*dichotomous variable-having 2 attributes
3
You're Reading a Preview

Unlock to view full version


Loved by over 2.2 million students

Over 90% improved by at least one letter grade.