Lecture Slides
Video Lecture (from 2019)
Concepts
Classical Experimental design
Independent variable
Dependent variable
Random assignment
Pretest
Posttest
Experimental group
Control group
Key Concepts:
Double-blind experiment
Confederates
Placebo
Deception
Debrief
Types of experiments:
Classical experimental design
True experiment
Quasi-experiment
One-shot case study
Natural experiment
Field experiment
Validity:
Internal validity
External validity
Variable:
Conceptual
Operational
Classical experimental design
An experiment with seven elements:
- Independent variable
- Dependent variable
- Pretest
- Posttest
- Control group
- Experimental group
- Random assignment
True experiment
An experiment with true random assignment of cases to the control and experimental groups.
E.g. Measure ‘happiness’ after coin flip assigns to drink ‘coke’ or ‘pepsi’.
Quasi-experiment (observational study)
An experiment lacking true random assignment.
E.g. Measure ‘happiness’ of people who regularly drink either ‘coke’ or ‘pepsi’.
One shot case study
An experiment where there is only one experimental group who are observed only once, after experiencing an event.
E.g. Measure ‘emotional distress’ of families of plane crash victims.
Natural experiment
A situation which was not designed as an experiment, but which can be studied using the logic of experiments.
E.g. Compare life expectancy of countries with and without universal public health care systems.
Field experiment (vs lab experiment)
An experiment conducted in some sort of more realistic or natural environment (as compared to in a laboratory).
E.g. Measuring likelihood of lending a phone to people of different ethnicities in a shopping centre (as compared to doing it a similar test on a computer screen in a laboratory, or in a survey).