Gaussian Fitting: Finding Error with MATLAB Output

  • Context: MATLAB 
  • Thread starter Thread starter natugnaro
  • Start date Start date
  • Tags Tags
    Fitting Gaussian
Click For Summary
SUMMARY

The discussion focuses on fitting a Gaussian function to data using MATLAB, specifically the output generated by the model. The model parameters include a1 = 2633, b1 = 1824, and c1 = 4.979, with a goodness of fit indicated by an R-square value of 0.9991. The user seeks to express the uncertainty in the parameter c1 as c1 ± M, where M represents the measurement error. The conversation suggests utilizing online calculators for further analysis of measurement errors.

PREREQUISITES
  • Understanding of Gaussian functions and their parameters
  • Familiarity with MATLAB for data fitting
  • Knowledge of statistical measures such as R-square and RMSE
  • Basic concepts of measurement error analysis
NEXT STEPS
  • Explore MATLAB's built-in functions for error estimation in model parameters
  • Research how to calculate confidence intervals for fitted parameters in MATLAB
  • Learn about the application of online calculators for measurement error analysis
  • Investigate advanced statistical techniques for assessing goodness of fit
USEFUL FOR

This discussion is beneficial for data analysts, researchers, and engineers who are involved in statistical modeling and measurement analysis using MATLAB.

natugnaro
Messages
61
Reaction score
1
Hi
I have fitted Gaussian function to some data in matlab.
Now MATLAB gives me this:

General model Gauss1:
f(x) = a1*exp(-((x-b1)/c1)^2)
Coefficients (with 95% confidence bounds):
a1 = 2633 (2628, 2637)
b1 = 1824 (1824, 1824)
c1 = 4.979 (4.97, 4.989)

Goodness of fit:
SSE: 3.694e+004
R-square: 0.9991
Adjusted R-square: 0.9991
RMSE: 4.599

I would like to write my result for c1 like c1\pmM where M is error in measurement,
Since it's been a while I have done any measurement analysis, is it possible to get this error from output above ?
 
Physics news on Phys.org

Similar threads

  • · Replies 6 ·
Replies
6
Views
6K
  • · Replies 12 ·
Replies
12
Views
4K
Replies
28
Views
4K
Replies
2
Views
1K
Replies
3
Views
11K