Quasi-experiment Information
A quasi-experiment is an observational study in which the subjects to be observed are not randomly assigned to different groups in order to measure outcomes, as in a randomized experiment, but grouped according to a characteristic that they already possess.[1][2]
Contents |
Example
For example, a quasi-experiment to measure the effects of living in a single- or two-parent home on children's response to different forms of advertising would group the children by whether they live in a single- or two-parent home, show them some sample ads, and measure the correlation between how they respond to the ads and the number of parents in their home.
Ethics
A true experiment would randomly assign children at birth to single- or two-parent homes in order to control for all other variables. Quasi-experiments are commonly used in the social sciences, where often it's not practical or ethical to set up the independent variable as in a true experiment.
A possible example is to examine social groups into two categories: Parents who spank their children and parents who don't spank their children. From a correlative study, it could be examined if there is a positive correlation between spanking and aggressive behavior later in life. However, to simply ask parents to spank their children may not be practical nor ethical.
Some authors distinguish between a natural experiment and a "quasi-experiment".[3][1] The difference is that in a quasi-experiment the causal factor is manipulated by the researcher, while in a natural experiment the causal factor varies 'naturally'.
Disadvantages
Quasi-experiments are more open to confounding.[1] In the example above, a variation in the children's response to the ads is plausibly influenced by uncontrolled factors, for example, cultural background, language spoken at home, parents' income level, and others.
References
- ^ a b c DiNardo (2008)
DiNardo, J. (2008). "Natural experiments and quasi-natural experiments". In Durlauf, Steven N.; Blume, Lawrence E. The New Palgrave Dictionary of Economics (Second ed.). Palgrave Macmillan. doi:10.1057/9780230226203.1162. http://www.dictionaryofeconomics.com/article?id=pde2008_N000142.
- ^ Rossi, Peter Henry; Mark W. Lipsey, Howard E. Freeman (2004). Evaluation: A Systematic Approach, 7th Ed.. SAGE. pp. 237. ISBN 978-0761908944.
- ^ Shadish, Cook, and Cambell. 2002. Experimental and Quasi-Experimental Designs for Generalized Causal Inference. Houghton Mifflin Company, Boston.
- DiNardo, J. (2008). "Natural experiments and quasi-natural experiments". In Durlauf, Steven N.; Blume, Lawrence E. The New Palgrave Dictionary of Economics (Second ed.). Palgrave Macmillan. doi:10.1057/9780230226203.1162. http://www.dictionaryofeconomics.com/article?id=pde2008_N000142.
External links
- Quasi-Experimental Design at the Research Methods Knowledge Base
Categories: Social sciences | Experimental design | Observational study | Evaluation methods
|