- refers to the possibility that the conclusions drawn from experimental results may not accurately reflect what went on in the experiment itself.
- the extent to which a study can be attributed to manipulation rather than flaws in research design
Threats to Internal Validity: History
- the pre-test affects the post-test
- issues of conceptualization and operationalization in pre-tests and post-tests
- if a variable is extreme on its first measurement, it will tend to be closer to the average on a second measurement
- watch out for extreme pre-test scores
- comparisons have no meaning unless the groups are equivalent
- watch out for bad matching
- people drop out of a study
- do the subjects that drop out share anything?
- if not, then you have a problem
"The semester I found StudyBlue, I went from a 2.8 to a 3.8, and graduated with honors!"Jennifer Colorado School of Mines