We also look at the graph to determine the direction of the linear relationship. A line that begins in the upper left corner of the plot and ends in the lower right corner (like the relationship shown above) is called a negative relationship. In a negative linear relationship, high scores on the X variable predict low scores on the Y variable.

In the previous example, high levels of self-esteem are associated with low levels of Interpersonal Avoidance. A line that begins in the lower left corner of the plot and ends in the upper right corner is called a positive relationship. In a positive linear relationship, high scores on the X variable predict high scores on the Y variable. Scores scattered randomly around a straight line in the middle of the graph indicate no relationship between variables.

Sometimes a scatter plot will show a curvilinear relationship between two variables. If this happens, we need to use special statistics developed for curvilinear relationships. Each type of relationship is presented below.