calclulate F-statistic (F-test) on a custom fit

2 次查看（过去 30 天）
Samuel Fonseca
Samuel Fonseca 2012-4-13
I have been looking around and so far I can´t find a solution to this problem. I have a time-series like data set and wrote some code fit the data to a custom fit:
fo_ = fitoptions('method','NonlinearLeastSquares','Lower',[-Inf -Inf -Inf -Inf -Inf 11.999000000000001 5.9989999999999997],'Upper',[Inf Inf Inf Inf Inf 12 6]);
ok_ = isfinite(Mes) & isfinite(P);
if ~all( ok_ )
warning( 'GenerateMFile:IgnoringNansAndInfs',...
'Ignoring NaNs and Infs in data.' );
end
st_ = [0.76574705281324407 0.5312095858606708 0.56903281101487801 0.11028936943862044 0.15894025687112179 0.111780179282573 0.037518452744076058 ];
set(fo_,'Startpoint',st_);
ft_ = fittype('a0+a1*cos(2*pi*x/c1)+b1*sin(2*pi*x/c1)+a2*cos(2*pi*x/c2)+b2*sin(2*pi*x/c2)',...
'dependent',{'y'},'independent',{'x'},...
'coefficients',{'a0', 'a1', 'a2', 'b1', 'b2', 'c1', 'c2'});
Now I need to apply an F-test in order to get a measure of how well the model represents the data ( other estatistic than the ones given by [gof]=...) but I cant find much info on how to do a f-Test on a custom nonlinear model.
Any help or advice will be apreciated

请先登录，再回答此问题。

回答（0 个）

类别

在 Help Center 和 File Exchange 中查找有关 Support Vector Machine Regression 的更多信息

标签

产品

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by