Comments on: A Couple of Topics in Curve Fitting https://blogs.mathworks.com/loren/2018/12/19/a-couple-of-topics-in-curve-fitting/?s_tid=feedtopost Loren Shure is interested in the design of the MATLAB language. She is an application engineer and writes here about MATLAB programming and related topics. Wed, 26 Dec 2018 21:10:42 +0000 hourly 1 https://wordpress.org/?v=6.2.2 By: Felipe Nievinski https://blogs.mathworks.com/loren/2018/12/19/a-couple-of-topics-in-curve-fitting/#comment-47591 Wed, 26 Dec 2018 21:10:42 +0000 https://blogs.mathworks.com/loren/?p=3177#comment-47591 I’d like to hear of fitting plane curves to data points, e.g., circles and ellipses and splines.

]]>
By: Tom Lane https://blogs.mathworks.com/loren/2018/12/19/a-couple-of-topics-in-curve-fitting/#comment-47565 Thu, 20 Dec 2018 14:12:09 +0000 https://blogs.mathworks.com/loren/?p=3177#comment-47565 Peter, those are good topics. On the first question, the Curve Fitting Toolbox has the ability to fit smoothing splines and lowess curves. The Statistics and Machine Learning Toolbox has, among other things, a fitrgp function for fitting Gaussian process models. All of these adapt to the data instead of requiring a parametric equation.

]]>
By: Peter Wittenberg https://blogs.mathworks.com/loren/2018/12/19/a-couple-of-topics-in-curve-fitting/#comment-47559 Wed, 19 Dec 2018 23:24:06 +0000 https://blogs.mathworks.com/loren/?p=3177#comment-47559 Curve fitting is certainly an important topic for me. Many times I do know the theoretical distribution of a set of data or perhaps an equation that I expect this to fit, but sometimes I know virtually nothing about what equation or model is relevant. Would you please discuss in a future blog two items:
1. How should you approach curve fitting if you have not a priori knowledge of what might be a relevant formula or distribution?
2. How should you use MATLAB to get a relevant curve and to compare multiple possible curves?

]]>