In this course, you will be required to calculate effect sizes. What is an effect size? An effect size is an indication of the amount of variability in the dependent variable that can be accounted for by the independent variable. If you have an effect size of .50, then your independent variable has accounted for 25% of the variability in the dependent variable. Basically, we are talking about the size of the relationship between the independent and dependent variable. You may have noticed that we are using the correlation coefficient as an effect size. Effect sizes range from .00 to 1.00 with higher values indicating a greater amount 
of variability accounted for by the independent variable.

For example, you conduct a study examining the impact of job applicant appearance and qualifications on the likelihood of being hired. You find that the effect size associated with the main effect of applicant appearance is .50 and the effect size associated with the main effect of qualifications is .25. You can make the statement that the applicant's appearance compared
to qualifications had a stronger impact on the likelihood of being hired. Whether this difference was significant would be determined through a meta-analysis.

The formula for computing the effect size r is:

Where "F(1, -)" refers to any F value with one degree of freedom in the numerator and "df error" refers to the value associated with the degrees of freedom error. If you have an F value with a 2 or greater in the numerator 
[e.g., F (2, 180)] then you cannot calculate an r. 

Using the data from the previous page, you would find r by plugging the correct numbers into the formula.
 

Next, you would round the r to .18. If the r value had been .174, then you would have rounded to ".17"
 

You can also calculate an effect size from a t-value.