| Re: Yet another user with poly_fit problems [message #86094 is a reply to message #86092] |
Wed, 02 October 2013 15:14   |
Gus
Messages: 7
Registered: September 2013
|
Junior Member |
|
|
Alright, I can see now that I do not have a perfect solution. For the purposes of my application, the bulging seen at the end actually concerns me less than the fact that the plotted curve is crossing the ordinate at roughly 17.3. In my application, very small variations in the value of Y (say +/- 0.2) Nevertheless, I was far happier to see reasonable Y values being generated by the new polynomial fit, as opposed to the ridiculous ones I had before.
To contextualize the discussion, I just wanted to say that the actual mathemathical equation used in the fitting is not so important for the engineering application for which I use it for. What is important is that, whichever method I use, it should be consistently applied for future datasets.
Moreover, I expect to always have evenly spaced Y values, but increasingly spaced X values. Perhaps I need to look into the different fitting methods and determine whether one of them is acceptable for all future datasets.
At any rate, this was a very useful discussion because it made people in my office think about a whole new set of situations where we can run into rather problematic results when we have few points to execute a fitting (something that we expect to happen).
Gus
|
|
|
|
comp.lang.idl-pvwave archive
Members
Search
Help
Login
Home
