Factorial design
Factorial design is a quantitative design that has two or more independent variables (factors), where variables have two or more values (levels), and all possible combinations of every level of each factor are considered. So, if there are two factors and each has two levels, there are four combinations and this is called a 2×2 factorial design. In this design, the researcher cannot control the independent variable.
History
This design was first introduced by Ronald Fisher in his book “The Design of Experiments” in 1935. He argued that factorial designs were more efficient than studying one factor at a time. Frank Yates contributed in the analysis of designs by the Yates algorithm.
Principal Use
This design is used when the researchers are interested in assessing the effects of two or more independent variables and for testing for interactions among variables. With this design, researchers can assess the joint effect of all variables in one experiment instead of having separate experiments for each variable
Advantages
- This design is very effective to examine interactions between different factors
- Factorial design is an efficient and cost-effective way to study multiple factors in one study, instead of conducting a series of independent studies
- By examining all factors, this design improves the validity and precision of the study
Shortcomings
- Factor analysis cannot identify causality
- More than one interpretation can be made of the same data
- It is difficult to identify the factors because multiple attributes can be correlated for no reason
Reference
- El Saadawi, G. et al. (2007). A natural language intelligent tutoring system for training pathologists: implementation and evaluation. Advances in Health Sciences Education, [Electronic publication ahead of print].
- Han Kim, J. et al. (2004). Discovering significant and interpretable patterns from multifactorial DNA microarray data with poor replication. Journal of Biomedical Informatics, 37 (4):260-8.
- http://en.wikipedia.org/wiki/Factorial_design
