Is There a Formula for Fitting a Sum of Exponentials to Data Points?

  • Context: Undergrad 
  • Thread starter Thread starter Gonzolo
  • Start date Start date
  • Tags Tags
    Exponential Fit
Click For Summary
SUMMARY

The discussion centers on fitting the equation y = A(exp(-Bx) - exp(-Cx)) to a set of data points, which involves determining the constants A, B, and C. It is established that there is no direct formula for these constants; instead, users must solve three equations derived from three selected (x, y) data points. The least squares method, particularly using Excel, is mentioned as a common approach, although results may vary based on the initial values chosen. Additionally, the discussion highlights the challenge of achieving an exact fit due to inherent noise in experimental data.

PREREQUISITES
  • Understanding of exponential functions and their properties
  • Familiarity with the least squares method for curve fitting
  • Basic knowledge of data analysis using Excel
  • Concept of error analysis in statistical modeling
NEXT STEPS
  • Explore advanced techniques for fitting nonlinear models in Python using libraries like SciPy
  • Learn about error estimation methods for parameters in nonlinear regression
  • Investigate the use of R for statistical modeling and curve fitting
  • Study the impact of data selection on fitting results and model accuracy
USEFUL FOR

Data scientists, statisticians, and researchers involved in modeling experimental data using nonlinear equations and seeking to improve their curve fitting techniques.

Gonzolo
Hi, I want fit the following equation to a set of data points :

[tex]y = A(exp(-Bx)-exp(-Cx)))[/tex]

I found how to determine A and B for one exp : y = Aexp(-Bx), but I'm not sure if there's a formula for A, B and C in such a sum (or difference) of exponentials. Thanks.
 
Mathematics news on Phys.org
There isn't a formula but there is a general concept:
[tex]y = A(exp(-Bx)-exp(-Cx)))[/tex]
has 3 undetermined constants, A, B, and C so you will need to solve three equations for them. Take three of your (x,y) data points and plug the values for x and y into the formula. Solve those three equations for A, B, C.

If you have more than 3 data points, and the formula is not and exact fit, the result will depend upon which 3 you choose.
 
I have tried to fit using the least squares method (with Excel) and that is what I find, that the results depend on what initial values I choose. So if what your saying in your last sentence is generally true, I suppose there no way to find the absolute minimum of the least squares sum, right?

If by exact, you mean that each data point should be on the curve exactly, then no it cannot be exact, since it is true experimental data, and there is a little noise.

Is there a way to determine an error for A, B, and C on the best fit that I choose?
 

Similar threads

  • · Replies 10 ·
Replies
10
Views
4K
  • · Replies 3 ·
Replies
3
Views
782
  • · Replies 6 ·
Replies
6
Views
2K
  • · Replies 16 ·
Replies
16
Views
5K
  • · Replies 9 ·
Replies
9
Views
4K
  • · Replies 13 ·
Replies
13
Views
3K
Replies
6
Views
2K
  • · Replies 1 ·
Replies
1
Views
5K
  • · Replies 19 ·
Replies
19
Views
4K
Replies
8
Views
2K