Ex Post Facto Design

Ex Post Facto Design

Ex post facto design is a type of research design in which the researcher studies the effects of an independent variable on a dependent variable after the independent variable has already occurred. This type of design is often used when it is not possible to manipulate the independent variable or when it is unethical to do so.

An ex post facto design is a type of research study in which groups of participants are determined by pre-existing conditions and events from the past. Latin for ‘after the fact’, in ex post facto designs the groups are compared with each other on a dependent variable (like an experimental design) but it is considered a quasi-experimental design because the independent variable is not manipulated.

The independent variable condition is based on pre-existing conditions instead of random assignment. Groups are based on subject variables that are already present in the participants.

For example, researchers are interested in the drink choices of Type 2 diabetics. So they form two groups, a group formed of Type 2 diabetes sufferers and a group with no diagnosed diabetics. The researchers then allow them to choose whatever drink they want from many choices in a waiting room before the study ‘begins’. They then record what each person chooses and analyze the results.

History of Ex Post Facto Design

The term “ex post facto” comes from the Latin words “ex” (meaning “from”) and “post facto” (meaning “after the fact”). The first known use of the term in a research context was in 1895 by the psychologist Hugo Münsterberg.

Characteristics of Ex Post Facto Design

Ex post facto designs are characterized by the following features:

  • The independent variable is not manipulated by the researcher.
  • The dependent variable is measured after the independent variable has already occurred.
  • The researcher cannot control for all of the possible confounding variables.

Other Related Terms

  • Confounding variable: A confounding variable is a variable that is associated with both the independent variable and the dependent variable. Confounding variables can make it difficult to determine the causal relationship between the independent variable and the dependent variable.
  • Correlation: Correlation is a statistical measure of the relationship between two variables. Correlation does not necessarily mean that there is a causal relationship between the two variables.
  • Causal relationship: A causal relationship is a relationship between two variables in which one variable causes the other variable to change.


  • **Shadish, W. R., Cook, T. D., & Campbell, D. T. (2002). Experimental and quasi-experimental designs for generalized causal inference. Boston, MA: Houghton Mifflin.
  • **Kerlinger, F. N. (1986). Foundations of behavioral research (3rd ed.). New York: Holt, Rinehart and Winston.
  • **Babbie, E. R. (2004). The practice of social research (11th ed.). Belmont, CA: Wadsworth.