Cubic Regression

The cubic regression option finds the equation of a cubic equation of the form y = ax3 + bx2 + cx + d that best fits a set of data. First, enter the data . Press  .

Press  and use  to select CALC.

Press  .

Therefore, the best-fit cubic equation for this data is approximately y = 0.43x3 - 0.42x2 -1.1x -5.1. The TI-83 stores the regression equation. The equation can be graphed and is transfered to  without typing the equation as follows. Press    and use  to select EQ.

Press  to view the regression equation and press . The equation is now entered in . Press . The data points can also be viewed. Access STAT PLOTS by pressing    to turn the plots on. Press .


Note: The resulting cubic equation is an exact fit if four noncollinear, nonparabolic data points are entered.

The TI-83 does not calculate the correlation coefficient r but does calculate the coefficient of determination r2. The value of .999 indicates a very good fit.