Weibull distribution
2 views (last 30 days)
Show older comments
I applied a weibull distribution fitting to my data. How can I estimate the associated error?
0 Comments
Answers (2)
Wayne King
on 3 Nov 2011
Hi Ana, did you use fitdist() or wblfit() to get the Weibull parameters?
One thing you can do is use qqplot() to examine the fit graphically.
data = wblrnd(0.5,0.8,100,1);
[parmhat, parmci] = wblfit(data);
pd = ProbDistUnivParam('weibull',[parmhat(1) parmhat(2)]);
qqplot(data,pd);
You can also use a Chi-square goodness of fit test with the null hypothesis that the data are drawn from a Weibull distribution with your estimated parameters:
[h,p] = chi2gof(data,'cdf',{@wblcdf,parmhat(1),parmhat(2)});
0 Comments
Amith Kamath
on 3 Nov 2011
AFAIK, there is no particular relation between error calculation and the model you use to fit the data. They are independently calculated quantities. By this, what I really mean to say is that you could apply any fitting error function to any model that you use to estimate the data. Mean Square Error is generally used for measuring the quality of the fitting, and it is irrespective of what model you've used to fit. I hope this answers the question!
0 Comments
See Also
Categories
Find more on Half-Normal Distribution in Help Center and File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!