Effects of Extreme Values
Brief description and instructions (DRAFT):
Measuring Correlations can be tricky. There are several issues that can make a correlation look weaker or stronger than they really are. One issue is a single extreme value. This value can cause the corrleation to look both stronger and in the different direction that correlation that describes the majority of the data.
Using the illustration:
The main part of the screen shows a graph. In this case, this is a scatter plot where each (x,y) pair is plotted without any connecting line. The second slider to the right of the graph (the r slider) will allow you to set correlation of the main body of the data on the left side of the graph to any level of r you wish from -1 to 1 and randomly select a sample that has that correlation and plot it. The first slider of the graph sets the value of the extreme data value plotted on the right hand side of the graph. The text at the top of the screen will tell you both the correlation of the main body of the data and also the correlation of all the data on the graph, which includes the main body and the extreme value.
Click here to open the applet. It will open a new window that will fill your screen.