Chapter 11: More on Experiments: Confounding and Obscuring VariablesThreats to Internal Validity: Did the Independent Variable Really Cause the Difference? 1. History threats to internal validity 2. Maturation threats to internal validity 3. Regression threats to internal validity 4. Attrition threats to internal validity 5. Testing threats to internal validity 6. Instrumentation threats to internal validity (Hey, MR. ATI!!!) •Combined threats History Threats to Internal Validity: o Result when some external or “historical” event affects most members of the treatment group at the same time as the treatment, so it’s unclear whether the change in the DV for the experimental group was the result of the treatment or the result of the historical factor . o Threat for the one group design but not for the two-group design .
o Not a threat for the two group ( treatment/experimental and comparison/control ) design. Maturation Threats to Internal Validity: o A change in behavior that emerges spontaneously over time. o Threat to for the one group design. o Not a threat to the two group design. Regression Threats to Internal Validity: o (aka regression to the mean): a statistical concept Attrition Threats to Internal Validity: o Reduction in participant numbers from pretest to posttest. Attrition is only problematic when it’s systematic o Sometimes called ‘subject mortality’ but does not mean that anyone died. o Participants leaving the study. Testing Threats to Internal Validity: o A type of order effect in which there is a change in participants as a result of experiencing the DV (the test) more than once . o Threat to the one group design . o Not a threat to the two-group design. Instrumentation Threats to Internal Validity: o Occurs when a measuring instrument changes over time. Combined Threats: o Selection-history threat : an outside event or factor systematically affects participants at one level of the IV. o Selection-attrition threat : participants in one experimental group experience attrition. Three Potential Internal Validity Threats in Any Experiment
1. Observer bias - Hard to be unbiased 2. Demand characteristics - Controlling for observer bias and demand characteristics (double-blind study, masked study) 3. Placebo effects Placebo Effects o Placebo effects can be powerful. They are not imaginary .
You've reached the end of your free preview.
Want to read all 10 pages?
- Fall '08
- Statistical significance, internal validity, placebo, Professor Mutola