Does R contain a regression function that doesn't assume that
measurements of the
independent variable are error-free, as in standard linear regression?
In other words, I'm looking for a function which solves directly for
the coefficients in the linear model y = a + b*x for the case when both
x and y are considered independent random variables with zero-mean noise
characterized by sd(x) and sd(y), which are independent of specific
observations.
Thanks
Dave
-------------- next part --------------
A non-text attachment was scrubbed...
Name: dthompson.vcf
Type: text/x-vcard
Size: 303 bytes
Desc: Card for David Thompson
Url :
https://stat.ethz.ch/pipermail/r-help/attachments/20020102/78e2f620/dthompson.vcf
