[R] limit of detection (LOD) by logistic regression

S Ellison S.Ellison at LGCGroup.com
Tue Jul 24 11:19:42 CEST 2012


> set 1; however the figure obtained from the sample set 2 
> shows that interpolation is not correct.
I don't think the interpolation is incorrect; what is making it look incorrect is using a straight line to represent a logistic regression.

Try adding the predicted values for the line to your plot:

lines( dil <- 10^seq(-1, 6, 0.05), predict(model, newdata=data.frame(dilution=dil), type="response"))
 

S Ellison

*******************************************************************
This email and any attachments are confidential. Any use...{{dropped:8}}



More information about the R-help mailing list