| T O P I C R E V I E W |
| oryieu |
Posted - 02/20/2006 : 08:40:15 AM
Origin Version (Select Help-->About Origin):
Operating System:
hi, i would like to know other than the LEAST SQUARE METHOD, what other methods are there in order to obtain a parabolic curve fit eqn y=ax^2+bx+c from a set of measured data.
cause this method doesnt seems to fit if the data measured are not close to a parabolic curve...
thanks
|
| 1 L A T E S T R E P L I E S (Newest First) |
| Leo_Li |
Posted - 02/20/2006 : 9:13:13 PM
Hi Ryan, I am confused. You said your data are not close to parabolic curve, but you insists to fit it by paraboic funciton? In this case the physical meaning of curve fitting is lost, no matter which regression method is chosen? Maybe you want to try WEIGHTED least square fit if your curve has error bars.
Leo
OriginLab Corp. |
|
|
