Correlation and Regression


A scatterplot displays the form, direction, and strength of the relationship between two quantitative variables. Straight-line (linear) relationships are particularly important because a straight line is a simple pattern that is quite common. The correlation measures the direction and strength of the linear relationship. The least-squares regression line is the line that makes the sum of the squares of the vertical distances of the data points from the line as small as possible.

When "Add data" is checked, click on the plot to add a data point. A point may be dragged to a new location if desired. Drag a point to the trash to remove it.

When "Draw line" is checked, click-drag-release on the plot to draw a line. Drag the end-points of the line to change its slope and location. Drag the line center point to move the line up and down. The blue/green bar above the graph shows the sum of squares for your line, with the smallest possible sum of squares in blue. If your line matches the least-squares regression line the green proportion of the bar will disappear. Drag a line end-point to the trash to remove the line.

Click on the trash to remove the line and all points.