Is it possible to obtain the equations of fitted curve and differentiate it to obtain the the rate of change of the data

Hi there,

I have a set of data points which vary with time. I would like to be able to find the rate of change of the variables with time. I thought perhaps I could use the matlab curve fitting tool to find the function that best describes the data and then differnetiate the equations to obtain the rates. I am new to the curve fitting tool. So far I have found that the Shape-Preserving PCHIP fits the data quite well. The equation however is not cited under "Results".

I then used the "Save to workspace" option under "Fit" in order to find out the equation for the function. In the matlab workspace, I opened the "fittedmodel" file which is a 1x1 cfit strcutre (?). Clicking on "Cfit" opens the matlab documentation page for the Cfit function which I don't think represents the function that I can then use and differentiate. Please could you let me know if what I am trying to do is possible and what the best way of doing it is.

Thank you!

Answer 1

[madhan ravi]

Yes it is possible .

Read http://matlab.izmiran.ru/help/techdoc/math/datafun18.html

[minomi]

I read the link but it only helped me as far as I already had got.

When I save the fit to workspace, and it saves "goodness" , "output" and "fitted model" in the workspace. I am not sure what these are and how to get the mathematical equation for the polynomial and its coefficients?