A "Begin" button will appear on the left when the applet is finished
loading. This may take a minute or two depending on the speed of your internet
connection and computer. Please be patient. If no begin button appears, it is
probably because your browser does not support Java 1.1. Click here
for information on how to get a browser that does.
This Java applet shows how the correlation between two variables is affected
by the range of the variable plotted on the X-axis.
When the applet begins, the dataset "Assumptions met" is plotted in
both the upper and lower graphs. For these data, the relationship between X
and Y is linear and the error around the regression
line is the same for all values of X (homoscedasticity).
The following statistics are computed for each graph: N, the number of points; slope, the regression slope (slope); r, Pearson's correlation and sd of est., the standard error of the estimate. The lower graph also shows r(c), Pearson's correlation corrected for restriction of range.
The upper graph has two vertical bars that can be moved with the mouse. You
can use these bars to select a range of points to be included in the lower graph.
The radio buttons located between the graphs allow you to specify whether to
include the points inside the bars or outside the bars. The lower graph and
its associated statistics are based on only the subset of the data specified.
You can select a new dataset with the popup menu. The initial dataset is called
"Assumptions met."
To enter your own data, choose "Enter Data" from the popup menu. A new window will open containing a field that you can type or paste in data. You should have two values on each line. The values should be separated a space or a tab. The scatterplot will use the first variable for the X axis and the second variable for the Y axis. The first line should contain two variable labels. If you leave off the labels the first variable will be called "var1" and the second will be called "var2."