5: Experimental Research Flashcards
All manipulated independent variables must have at least ___
2 levels
Extraneous variables are ___
held constant
Explain the varieties of manipulated independent variables (controlled by the researcher)
Situational variables: Features in the environment that participants might encounter
Task variables: Experimenters vary the type of task performed by subjects
Instructional variables: Manipulated by telling different groups to perform a particular task in different ways
Confound
any uncontrolled extraneous variable that co-varies with the independent variable and could provide an alternative explanation of the results
Dependent variable
used to describe the behaviour that is the measured outcome of the study
Statistical Conclusion Validity
the extent to which the researcher uses statistics properly and draws the appropriate conclusions from the statistical analysis
Ceiling effect vs floor effect
Ceiling effect: Occurs when average scores for the group are so high that no different can be determined between conditions
□ Ex. Test is too easy, everyone gets a good score
Floor effect: All scores are extremely low and cant find a difference between conditions
® Task is too hard
What can reduce Statistical Conclusion Validity
wrong analysis
violate assumptions required for performing a certain analysis
the reliability of the measures used: error variability reduces the chances of finding a significant effect
Construct validity
Refers to whether a test truly measures some construct
In experimental research has a related meaning
○ Refers to the adequacy of the operational definitions for BOTH the independent and the dependent variables used in the study
What are the three ways that external validity should generalize
- to other populations
-to other environments
-to other times
Internal validity
The degree to which an experiment is methodologically sound and confound-free
A researcher feels confident that the results, as measured by the dependent variable, are directly associated with the independent variable and are not the result of some other, uncontrolled factor
Threats to internal validity
Control group absent
study is over a long period of time in which participants receive a pret-test and treatment and a post test
any uncontrolled extraneous factor
Worries with studies extending over time
confound of history: event outside of the study
confound of maturation: become accustomed to their environments/situations over time -developmental changes occurring over the passage of time
regression to the mean
testing: taking the pre-test has an effect on post-test scores
instrumentation: measurement instrument changes from pre to post
Participant problems that threaten internal validity
Subject selection effects: if the groups are non equivalent
Attrition: not completing the study
