| Author |
 Topic  |
|
|
SpaceNerd
USA
3 Posts |
 Posted - 02/24/2021 : 10:11:14 PM
|
Hi all,
I am trying to find the best way to fit a multiple variable power law using origin. The functional form I am looking for would end up being-
Y=constant*(X1^n1)*(X2^n2)
with me having data for Y, X1, and X2.
Does any one have any insight into the best way forward with completing this regression in Origin. I am very new to Origin and I apologize if this is a rudimentary exercise, but my head hurts from all of the banging into the table while I have been trying to figure this out.
Thank you in advance for any assistance,
-Chris
Origin Ver. and Service Release (Select Help-->About Origin): OriginPro 2020
Operating System:Win10
|
|
|
YimingChen
1593 Posts |
|
|
SpaceNerd
USA
3 Posts |
Posted - 02/25/2021 : 10:49:57 AM
|
Thanks for the answer Yiming. Yes, I have looked at that short explanation page in great detail, but I am still getting rather stuck trying to do the fit. I have built my equation using the 'function builder' tool (as shown in the screenshot below)
But when I go to use the NLFit tool, it is not creating one plot, but instead trying to fit my two independent variables in two different plots, when I am trying to fit both of these variables in one function.
Do you have any suggestions on how to fix that issue? The way I have it labelled I am looking for V as a function (f^n1)*(four^n2)*A.
~CJC |
 |
|
|
YimingChen
1593 Posts |
Posted - 02/25/2021 : 1:52:49 PM
|
That is normal. Two plots are just (V vs f) and (V vs four). You may need to change the initial value of parameters under Parameters tab, see if the fitting converge.
James |
|
|
|
SpaceNerd
USA
3 Posts |
Posted - 02/26/2021 : 12:24:07 PM
|
Got it to work, thanks for your help.
~CJC |
|
|
| |
Topic |
|
|
|
Multiple variable regression with power law