| T O P I C R E V I E W |
| noazn |
Posted - 09/12/2007 : 05:35:22 AM
How can I fit two sets of data to two different functions but with the same parameters? |
| 3 L A T E S T R E P L I E S (Newest First) |
| Mike Buess |
Posted - 09/12/2007 : 5:10:57 PM
These two articles might help...
http://www.originlab.com/www/support/resultstech.aspx?ID=128&language=English&Version=All
http://www.originlab.com/index.aspx?s=9&pid=434
Mike Buess
Origin WebRing Member |
| noazn |
Posted - 09/12/2007 : 4:47:46 PM
Thank you, you have been most helpful.
Can you advise me on how to make a fit to a 3D function?
Noaz. |
| Mike Buess |
Posted - 09/12/2007 : 12:41:10 PM
You must create a third fitting function with two dependent variables. If the datasets share the same X column you can get away with one independent variable as shown in the top figure which illustrates the approach for two hypothetical functions, funcA and funcB, each with two parameters, a and b. If the X values are different you'll need two independent variables, xA and xB.
Of course the details are in how to express the functions. If you created both functions yourself you'll just have to write them out completely. Built-in fitting functions have corresponding LabTalk functions which can be used to shorten the expressions. You can find the LabTalk functions for built-in fitting functions here...
http://www.originlab.com/pdfs/curvefittingfunctions.pdf
If you have O70 or O75 I suggest you use OriginC, in which case the LabTalk functions cannot be called directly... The bottom figure shows how to use LabTalk's Lorentz and Gauss functions in OriginC.
Mike Buess
Origin WebRing Member |
