In the Toolkit 6 manual (p. 97 in the 6.2 edition), it states:
Along the bottom of the Stock Study form are the year labels and six data fields representing historical sales growth, historical earnings growth, estimated (future) sales growth, estimated (future) earnings growth, and the R2 values for sales and EPS growth.
R^2 (R2 or R-squared) is an indicator of how well the historical data conforms to the trend line that is calculated by the program. Toolkit uses the "least squares" to find the trend line that lies closest to all of the plotted points. The R-squared value measures how closely the plotted points are to the trend line, and ranges in value from 0 to 1. The closer the number is to 1 the better, with 1 representing perfect correlation and 0 representing no correlation.
Thus, the closer the R-squared value is to a perfect 1.0, the straighter the line is formed by the points on the graph, or, in other words, the more consistent the growth of the company has been in the past. R-squared is useful when searching for stocks, since you can restrict your search for companies that have a high level of consistency with respect to their historical growth.
Doug