Chapter 7: Experimental research Flashcards
2 types of experimental research
between-groups and within-groups
Between-groups design
2/more groups formed at random from a sample (independent groups)
Each group receives different level of IV and results of each group are compared
Within-group design
All participants exposed to all levels of the IV
Comparison made between the scores obtained at different levels of the IV for the same participant
Elements (4) of experimental research
Manipulation
Measurement
Comparison
Control
Factorial design
Study with more than one independent variable
Multivariate study
Study with more than one dependent variable
Experimental group
Participants exposed to manipulation of IV
Control group
Participants not exposed to manipulation of IV
Extraneous variables
Variables also present in study but are not studied/investigated
Confounding variables
Extraneous variables that act as an IV and can mask true effects of the IV under investigation
Only present when IV is present
Offer alternative explanation of results
Controlling for confounds (5)
1) Make variable present in all conditions (holding constant)
2) Remove variable
3) Use a placebo control
4) Matching across conditions
5) Randomization
Confounds in within-groups design (6)
1) History
2) Maturation
3) Repeated testing
4) Instrumentation
5) Regression to the mean
6) Environmental conditions
Confounds in between-groups design (5)
1) Assignment bias
2) Differential attrition
3) Compensation
4) Resentful demoralization
5) Environmental conditions
History
External events occurring between the first and second tests influencing the treatment outcome(s)
Maturation
Any systematic changes in biological or physiological condition of participant over time not related to the treatment (physical growth, cognitive development, etc.)
Repeated testing
Possible effects of the pretest on the posttest
Instrumentation
Changes in the characteristics of a measurement instrument over time
Regression to the mean
Whenever participants have extreme scores on a pretest measure, their scores will likely be closer to the mean on a subsequent measure
Assignment bias
When participants are put into groups for reasons other than participation
Differential attrition
When more participants fail to complete the study in the experimental group
Compensatory equalization
Untreated individuals/groups learn of treatment received by others and demand to receive the same treatment or something similar
Compensatory rivalry
Untreated group learns of treatment received by others and works extra hard to see to it that the expected superiority of the treatment group is not demonstrated
Resentful demoralization
When individuals in untreated group learn others are receiving special treatment, they can become less productive, less efficient, or less motivated because of feelings of resentment
Mundane realism
Superficial, usually physical, characteristics of the simulation, which probably have little positive effects on external validity
Experimental realism
Extent to which physiological aspects of the research environment duplicate the real-world environment that is being simulated
