Design of Experiments > Main Effect
What is a Main Effect?A main effect is the effect of one independent variable on the dependent variable. It ignores the effects of any other independent variables. In general, there is one main effect for each dependent variable. For example, let’s say you’re conducting a study to see how tutoring and extra homework help to improve math scores. As there are two independent variables (tutoring and extra homework), there are two main effects:
- The effect tutoring has on math scores.
- The effect extra homework has on math scores.
The two independent variables can also work together on the dependent variable. In that case, the effects are called interaction effects.
Testing Main Effects
Main effects can be measured in two ways:
- Simple Main Effects
- Statistical Testing.
Simple main effects are obtained by looking at the results. For example, let’s say you had the following results for the example on how tutoring and extra homework helps to improve math scores, against an average test score of 70:
Tutoring: 85 points
Extra homework: 75 points.
The simple main effect of tutoring is a 15 point increase (compared to the average of 70) and the simple main effect of extra homework is 5 points. The question becomes, is the difference of 10 points between the two measures (i.e. 15 – 5 = 10) significant? In order to answer that question, you should run a statistical test. For example, you could calculate an F statistic for your data.
If you have multiple levels in your independent variables, make sure that your effects are measured as consistent across levels. For example, let’s say you had two extra homework levels of 5 and 10 hours. The main effects of tutoring (10 points in this example) would have to be consistent no matter what hours of homework were assigned.
Note that there doesn’t have to be a main effect. If the students showed an increase of zero for both independent variables, then you could say there isn’t an effect.
If you prefer an online interactive environment to learn R and statistics, this free R Tutorial by Datacamp is a great way to get started. If you're are somewhat comfortable with R and are interested in going deeper into Statistics, try this Statistics with R track.Comments are now closed for this post. Need help or want to post a correction? Please post a comment on our Facebook page and I'll do my best to help!