Changing the confidence Interval

2012 11 26
1 个回答
9 次查看（30 天）

0 个投票

Is there a way to change the confidence interval from 95% to say 67% and recalculate the coefficients (with the 95% confidence bounds)? I am using the curve fitting tool for my dataset.

2 个评论
显示 无 隐藏 无

Matt J
Matt J 2012-11-26
Which curve fitting tool?
Lizan
Lizan 2012-11-26
编辑：Lizan 2012-11-26
The MATLAB have a app called "Curve Fitting Tool". By default, the confidence level for the bounds is set to 95%. However I want to make the same fitting with a different confidence level. In a previous version this was possible, but I can't find information on how to change this with the latest version.
You can add any type of confidence level in >Tools>Prediction bounds, but that only plot predicted bounds, the P1, p2 values in the linear fit, y = p1*x + p2 are still calculated with 95% of confidence. I would like to do same calculation but not with the default set confidence value.
So basically I am using the function,
% Fit model to data.
[fitresult, gof] = fit( xData, yData, ft, opts );
to fit the data,..
Any ideas?

请先登录，再进行评论。

请先登录，再回答此问题。

回答（1 个）

Shashank Prasanna
Shashank Prasanna 2012-12-14

1 个投票

You can always save the fitted model from CFTOOL : Fit > Save To Workspace and fun the following command: confint(fittedmodel,0.67)
http://www.mathworks.com/help/curvefit/confint.html

类别

在 帮助中心 和 File Exchange 中查找有关 Get Started with Curve Fitting Toolbox 的更多信息

产品

标签

提问:

Lizan
Lizan
2012-11-26

Community Treasure Hunt

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

Start Hunting!

Translated by