> I wonder if anyone can help with this? I had a look in the archives but didn't turn anything up.
>
> We are using linear regression models to look for relationships among biological measures. These are mainly plasma levels of various small molecules. The analysis of these is associated with analytical error. The analytical error may vary with concentration (low CV at higher concentration, higher CV at lower concentrations). The question is how do we include the analytical error in the independent and/or dependent variables in our regression models?
>
> I had a look around the Internet for information on fuzzy linear regression and found the program FuReA. This however does not seem to calculate an overall measure of goodness of fit, nor does it provide SE of the regression parameters.
>
> Is there anything else out there? Am I barking up the wrong tree?
>
> Thanks in anticipation
>
>
> Peter Hudson
>
> Peter Hudson
> Principal Biochemist
> Wrexham Maelor Hospital
> Wales, UK. LL13 7TD
> [log in to unmask]
>
|