Linear regression is an extremely useful “least squares” technique for fitting a linear equation to a set of data. This program calculates means, sums of squares, and sums of cross-products of the dependent and independent values which are entered only once. It also calculates the slope and intercept of the line as well as the coefficients of determination and correlation. The program calculates a predicted dependent variable from a given independent variable and vice versa. It also computes the reduction in sum of squares due to regression, residual sum of squares and degrees of freedom, variance about regression, standard error of the estimate, the standard deviation about the slope, and the t-test on the slope of the line.
South Dakota State University
Evenson, Paul, "Linear Regression Analysis Using a Programable Pocket Calculator" (1978). Agricultural Experiment Station Technical Bulletins (1939-2011). 52.