How to find the erro for fitted parameters?

When using 'lsqnonlin', 'lsqcurvefit', 'fitnlm', 'nlinfit', etc.. It produces optimized parameters. How to find the error of these parameters to report results like a+/- da; b +/- db ( da and db here)? Thanks.

Answer 1

[Star Strider]

To get parameter confidence limits on a nonlinear regression, use the nlparci (link) function.

To get confidence intervals on the fit (prediction), use the nlpredci (link) function.

[John]

Thanks Star!

[Star Strider]

My pleasure!