Quartic Regression
The quartic regression option finds the equation of a fourth degree polynomial
of the form
y = ax4 + bx3 + cx2 + dx + e
that best fits a set of data.
First, press 
to
enter the data .
The data shown here is the points {(2,11.4) (3,17) (5,27.3) (7,36.1) (11,47.7) (13,49.9)}.
To view the statistics calculation options press
.
Press find the quartic regression optiion -- polynomial of degree four, P4Reg.
Select P4Reg, .
Run quartic regression by pressing
. Scroll to the right to see all of the coefficients.
Therefore, the best-fit quartic equation for this data is approximately
y = .00011x4 - .0104x3 - .0504x2 + 6.037x - 3.89.
(Note the scientific notation for the first term.)
Note: The resulting quartic equation is an exact fit if five non-collinear, non-parabolic,
non-cubic data points are entered.
The TI-86 does not calculate the correlation coefficient r.