Hello all,
I would like to some help regarding the following problem.
I have some data based on some numerical experiments and would like to make a empirical relation out of that. While there are certain tools which can help to give a data fit based on say Least square method, I want to have as accurate fit as possible.
In process of searching for more appropriate fit, I came across Kriging model ( which as per my understanding adds Gaussian type function at the points where exact data is available so that error at that point goes to 0) and thus over interpolated function is more appropriate.
I would like to know how to implement the same in matlab or some other platform.
I know there exist in built curve fittings in MATLAB but could not find regarding the same.
Thanks
(P.S: Kindly correct me if I interpreted Kriging model wrongly)
Hello,
Thanks for your kind reply but this is not what I am looking for. I am familiar with the link you have posted. I am looking for one step over wherein the error at the points where data is available will go to zero by means of local fitting of gaussian function ( which I understand is the whole idea of Kriging model)
I am looking for how to do in matlab or code it in some platform.
Thanks
- Badges
- Science topic
- Similar topics
- Mathematics
- Statistics