thanks a lot Renaud. but i was interested in Finney's fiducial confidence intervals of LD50 so to obtain comparable results with SPSS. But your reply leads me to the next question: does anybody know what is the best method (asymptotic, bootstrap etc.) for calculating confidence intervals of LD50? i could "get rid" of Finney's fiducial confidence intervals but only if there was a better method.. any idea?
Renaud Lancelot <[EMAIL PROTECTED]> wrote: Date: Mon, 21 Aug 2006 16:35:49 +0200 From: "Renaud Lancelot" <[EMAIL PROTECTED]> To: "carlos riveira" <[EMAIL PROTECTED]> Subject: Re: [R] Finney's fiducial confidence intervals of LD50 CC: [email protected] Sorry there was a typo in my previous reply: > D50 <- 10^c(logD50 + c(0, -1.96, 1.96) * attr(logD50, "SE")) > names(D50) <- c("D50", "lower", "upper") > D50 D50 lower upper 140.8353 103.3171 191.9777 Best, Renaud 2006/8/21, Renaud Lancelot : > I don't know what Finney's fiducial confidence interval is but if your > problem is to handle the output of dose.p (from MASS), you can do as > follows: > > > library(MASS) > > Response <- c(0, 7, 26, 27, 0, 5, 13, 29, 0, 4, 11, 25) > > Tot <- rep(30.5, 12) > > Dose <- rep(c(10, 40, 160, 640), 3) > > fm <- glm(Response/Tot ~ log10(Dose), family = quasibinomial(link = probit)) > > logD50 <- dose.p(fm, cf = 1:2, p = 0.5) > > D50 <- 10^c(logD50 + c(1, -1.96, 1.96) * attr(logD50, "SE")) > > names(D50) <- c("D50", "lower", "upper") > > D50 > D50 lower upper > 164.9506 103.3171 191.9777 > > Best, > > Renaud > > 2006/8/21, carlos riveira : > > I am working with Probit regression (I cannot switch to logit) can anybody > > help me in finding out how to obtain with R Finney's fiducial confidence > > intervals for the levels of the predictor (Dose) needed to produce a > > proportion of 50% of responses(LD50, ED50 etc.)? > > If the Pearson chi-square goodness-of-fit test is significant (by default), > > a heterogeneity factor should be used to calculate the limits. > > > > Response<-c(0,7,26,27,0,5,13,29,0,4,11,25) > > Tot<-rep(30.5,12) > > Dose<-rep(c(10,40,160,640),3) > > probit<-glm(formula = Response/Tot~ log10(Dose), family=quasibinomial > > (link=probit)) > > D50<- round(10^(dose.p(probit,cf=1:2,p=0.5))) > > > > #This is what SPSS calculates. I would like to reproduce these results with > > R: > > #SPSS RESULTS: > > #PRNT50= 140,83525 > > #CI = 98,37857;205,34483 > > #Regr.coeff= 1,91676 (S.E.=0,16765) > > #Intercept=-4,11856 (S.E.=0,36355) > > Thanks a lot for your help. > > > > Carlos > > > > __________________________________________________ > > > > > > > > [[alternative HTML version deleted]] > > > > ______________________________________________ > > [email protected] mailing list > > https://stat.ethz.ch/mailman/listinfo/r-help > > PLEASE do read the posting guide http://www.R-project.org/posting-guide.html > > and provide commented, minimal, self-contained, reproducible code. > > > > > -- > Renaud LANCELOT > Département Elevage et Médecine Vétérinaire (EMVT) du CIRAD > Directeur adjoint chargé des affaires scientifiques > > CIRAD, Animal Production and Veterinary Medicine Department > Deputy director for scientific affairs > > Campus international de Baillarguet > TA 30 / B (Bât. B, Bur. 214) > 34398 Montpellier Cedex 5 - France > Tél +33 (0)4 67 59 37 17 > Secr. +33 (0)4 67 59 39 04 > Fax +33 (0)4 67 59 37 95 > -- Renaud LANCELOT Département Elevage et Médecine Vétérinaire (EMVT) du CIRAD Directeur adjoint chargé des affaires scientifiques CIRAD, Animal Production and Veterinary Medicine Department Deputy director for scientific affairs Campus international de Baillarguet TA 30 / B (Bât. B, Bur. 214) 34398 Montpellier Cedex 5 - France Tél +33 (0)4 67 59 37 17 Secr. +33 (0)4 67 59 39 04 Fax +33 (0)4 67 59 37 95 --------------------------------- [[alternative HTML version deleted]]
______________________________________________ [email protected] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
