Interaction Effect is a research term that often confuses students, but is not that difficult if you just take it slowly and one step at a time. Let’s start with a scientific definition of interaction effect; “the differing effect of one independent variable on the dependent variable, depending on the particular level of another independent variable” (Cozby, 1997; p. 314). Believe it or not, this is one of the best definitions we could find, but we still think it is not very clear, so let’s try an example. Let’s say you are doing a study on the effect of some sleep drug (Halcion) and alcohol consumption on overall sleep time.
As you can see, there are two independent variables (IVs) and one DV. The IVs are 1) sleep drug (Halcion), and 2) alcohol consumption. The DV is overall sleep time. Now, let’s say we randomly assign participants to receive either 1 mg (milligram) or 10 mg of Halcion. These then are the “levels” of the IV (one level is 1 mg, one level is 10 mg). In addition, we randomly assign participants to different levels of the other IV; either 12 oz beer or 36 oz beer. So, we have four groups overall; two IVs with two Levels each. What possible outcome could we get. It is possible that each IV by itself influences sleep (e.g., that the sleep drug affects sleep time and also possibly that
alcohol affects sleep time).
But what about the fact that participants are getting both the sleep drug and alcohol? Isn’t it possible that the two IVs are “interacting” in some way to affect sleep time? The answer is yes, and this is the interaction effect. It is possible that levels of the IVs interact and affect the DV differently than each by itself. For example, maybe there is no effect when participants get only 1 mg of the sleep drug and 12 oz of beer. But when you give them 1 mg of the sleep drug and 36 oz of beer there is an effect. In this case, you would have an interaction effect. See, it’s not too bad…is it?