Curve Fitting Equation result

1 view (last 30 days)
Merve Ayaz
Merve Ayaz on 14 Apr 2019
Commented: Star Strider on 14 Apr 2019
Hey guys,
When I wrote a custom equation, then matlab solves the equation depending on my graph and give me results. However, result followed by a boundaries in paranthesis like that. What is the meaning of (-10.62, 1.34)??? Thank you

Accepted Answer

John D'Errico
John D'Errico on 14 Apr 2019
Those are approximate confidence limits on the variable as estimated. (Not always very good limits, as I said, approximate.)
If they are wide, then view it as if the solver is not very confidant in the result. They may be wide because you have crappy data. It may be because your model is poor. It may indicate insufficient data. If they are norrow limits, then it suggests you have done a decent job of estimating the parameter.
  2 Comments
Merve Ayaz
Merve Ayaz on 14 Apr 2019
Thank you!
Is there any scientific way to describe a range is whether narrow or wide?
Star Strider
Star Strider on 14 Apr 2019
The most significant problem with your ‘e’ parameter is that the confidence limits include 0. That means ‘e’ is not significantly different from 0, and is therefore not needed in the regression model.

Sign in to comment.

More Answers (0)

Categories

Find more on Biological and Health Sciences in Help Center and File Exchange

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!