Re: How to extract statistics after using



Ed wrote:


Peter Perkins wrote:


Ed wrote:
Hi:
As following function:
[cf_,GOODNESS,OUTPUT] = fit(x,y,ft_ ,'Startpoint',st_)

(1). How to extract statistics after using "fit" function?
I mean "GOODNESS" (SSE,Rsquare....)?
(2). If I saved M-file after CFTOOL had done, the M-file
could
be
applied other "similiar" (x,y) dataset without "huge"
interference?

Ed, I can't tell exactly what problems you are having. As
described in the help,

[FITTEDMODEL,GOODNESS] = FIT(XDATA,YDATA,...) returns
appropriate
goodness-of-fit measures, for the given inputs, in the
structure GOODNESS.
GOODNESS includes the fields: SSE (sum of squares due to
error), R2
(coefficient of determination or R^2), adjustedR2 (degree of
freedom
adjusted R^2, and stdError (fit standard error or root mean
square error).

so the g.o.f. measures are just the fields of the structure.

And yes, the generated M code should be able to fit similar
data
without any
modifications to the code.

Hope this helps.

- Peter Perkins
The MathWorks, Inc.

Sorry, I described ambiguously! Let me put my problem in the
following way:
1. How to extract coefficients (such as Fourier series in a0, a1,
b1,
b2...) from structure variables of statistics which had solved by
using "fit" function.
2. As for Fourier series fitting, one applied CFTOOL M-file to
another "not similar" dataset, which one will received warnings in
Matlab environment. I mean...how to revise the code with adaptive
adjustable coefficients, and there were no huge error or warnings
for
those datasets with correlation coefficient above 50%?

By the way, how to extract a "GOODNESS(SSE,Rsquare....)" structure
variable and split it into different variables?
.



Relevant Pages

  • Re: How to extract statistics after using
    ... How to extract statistics after using "fit" function? ... I mean "GOODNESS"? ... If I saved M-file after CFTOOL had done, ...
    (comp.soft-sys.matlab)
  • Re: Interpreting Q-Q plot
    ... one passing for the 25th and 75th quantile ... isn't very useful since there might be a goodness of fit even if the ... plot. ...
    (sci.stat.edu)
  • Re: Interpreting Q-Q plot
    ... but instead of evaluating the goodness of fit ... line) for a GoF? ... You could try a PP or SP plot instead: see Michael The stabilized probability plot. ...
    (sci.stat.edu)
  • Interpreting Q-Q plot
    ... but instead of evaluating the goodness of fit ... line) for a GoF? ... and what kind of statistically analysis can I do with that? ...
    (sci.stat.edu)
  • Re: GLM for multiple subjects
    ... Peter Perkins wrote: ... Lionel Zupan wrote: ... testing direction and acceleration. ... it was easy since the "fit to the mean across ...
    (comp.soft-sys.matlab)