Power Regression


The power regression option finds the equation of an equation of the form y = axb that best fits a set of data. First, press to enter the data . The values of x and y must be greater than zero because the method for determining the values of a and b in the regression equation is a least-squares fit on the values for ln x and ln y.



The data shown here is the points {(2,11.4) (3,17) (5,27.3) (7,36.1) (11,47.7) (13,49.9)}.

Press to view the statistics calculation options.



Select Calculate



To select Power regression, press .



Finally run power regression, press . The best-fitting power equation for this data is y = 7.01x0.8.

The regression equation can be automatically stored in the equation editor by pressing then typing the name of the equation, such as y1, and pressing .


Note: The TI-86 calculates the correlation coefficient, r, as corr.