[R] ED50 calculation in drc package

Hi, I am trying to use drc package to calculate IC50 value. The ED50 calculated in some models (LL4 for example) as a response half-way between the upper and lower limit, which is the definition of the relative IC50 value. Does that mean the ED50 in drc package is IC50? How the ED function in

Re: [R] ED50 calculation in drc package

Lixia: This is not fundamentally an R issue. You seem to have some confusion about what IC50's and ED50's are in the statistical modeling context. I suggest you consult one of the fine statisticians at MD Anderson to help you resolve your confusion. Cheers, Bert On Tue, Jan 3, 2012 at 10:11 AM,

[R] ed50

Asunto: [R] ed50 I am using semiparametric Model  library(mgcv) sm1=gam(y~x1+s(x2),family=binomial, f) How should I  find out standard error for ed50 for the above model ED50 =( -sm1$coef[1]-f(x2)) / sm1$coef [2]   f(x2) is estimated value for non parametric term.   Thanks Two ways

Re: [R] ed50

I don't know how to reparameterise the model. will you please give the detail for reparameterisation and delta method? Thanks --- On Tue, 7/13/10, Rubén Roa r...@azti.es wrote: From: Rubén Roa r...@azti.es Subject: RE: [R] ed50 To: Dipa Hari harid...@yahoo.com, r-help@r-project.org Date

Re: [R] ed50

-Mensaje original- De: r-help-boun...@r-project.org [mailto:r-help-boun...@r-project.org] En nombre de Dipa Hari Enviado el: lunes, 12 de julio de 2010 22:19 Para: r-help@r-project.org Asunto: [R] ed50 I am using semiparametric Model  library(mgcv) sm1=gam(y~x1+s(x2),family

[R] ed50

I am using semiparametric Model  library(mgcv) sm1=gam(y~x1+s(x2),family=binomial, f) How should I  find out standard error for ed50 for the above model ED50 =( -sm1$coef[1]-f(x2)) / sm1$coef [2]   f(x2) is estimated value for non parametric term.   Thanks [[alternative HTML