error propogation in polyfit

[Kyndig]

I can't seem to find any information about how to find the error propogated
through a polyfit.  More specifically, if I have an experimental error which
is equal for all data points and assumed to be random (gaussian
distribution) so that a least squares fit is applicable, I'd like to know
how to find the standard deviations for the estimators given by polyfit. 
Any suggestions would be greatly appreciated.  Thank you for your time!
-- 
View this message in context: http://www.nabble.com/error-propogation-in-polyfit-tp15450573p15450573.html
Sent from the Octave - General mailing list archive at Nabble.com.