R-square value of Probability plot

Is there an easy way to find the R-squared value for a probability plot which I plotted using probplot() in MATLAB?

3 Commenti

dpb
dpb il 13 Ago 2013
Doesn't appear that it returns anything but the handle(s) to the lines drawn; not the fitted parameters.
Looks like you'll need to estimate the coefficients and the compute the SSE and SST
doc normfit % for details
dpb, any reason why you put this as a comment, rather than an answer that could be accepted?
dpb
dpb il 13 Ago 2013
Wasn't sure it qualified as enough detail...but per your suggestion, done. :)

Accedi per commentare.

Risposte (1)

dpb
dpb il 13 Ago 2013

0 voti

Doesn't appear that probplot returns anything but the handle(s) to the lines drawn; not the fitted parameters.
You'll needs must estimate the coefficients and the compute the SSE and SST resulting therefrom.
doc normfit % for details

2 Commenti

Lisha
Lisha il 19 Ago 2013
normfit() only gives me the parameters of the fit right. How do I find the SSE and SST related to the fit? The data of the fit is not available.
dpb
dpb il 19 Ago 2013
Modificato: dpb il 20 Ago 2013
How did you do the plot, then?
If you don't have the data then you have no way to compute the residuals and hence no way to compute SSE (or SST, even).
ADDENDUM:
Perhaps you mean the ancillary statistics beyond the estimated parameters aren't available instead of the underlying data? In that case, my misinterpretation and you then use the definitions of SSE and SST to compute from the residuals which you can obtain by using normpdf with the underlying data and the estimated/fitted mean, std dev. That help?

Accedi per commentare.

Richiesto:

il 13 Ago 2013

Community Treasure Hunt

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

Start Hunting!

Translated by