pwrfit(vx, vy, vg) Returns a vector containing the coefficients
for a power curve of the form a · xb + c
that best approximates the data in vx and vy
using guess values vg. The pwrfit function employs
the Levenberg-Marquardt method for minimization.
Arguments:
vx and vy are vectors of real data
values of the same length, corresponding to the x
and y-values in the data set. There must be at least
3 data points, and the vx values must all be greater than or equal to 0.
vg is a three-element
vector of real guess values for the parameters a,
b, and c in the power
equation.
Notes:
Negative x-values are inappropriate in this setting
because raising them to an arbitrary power can produce complex results that
satisfy the minimization problem, but do not correspond to the real y-values.
If you wish to do a power fit to data in the left-half plane, shift it so
that all x-values are positive, then shift the fitted equation back to get
final results.
To further analyze your data, or determine the suitability of a linear regression,
you may wish to apply other statistics
functions for data analysis.
If you wish to do a power fit that differs from the form above, use genfit.