Hello, I would like to calculate the 95% success rate of a test. I have a series of dilutions and the proportion of positive results out of 37 attempts for each of them. I would like to find the concentration that gives 95% success and I used logit regression: ``` df <- data.frame(concentration = c(1, 10, 100, 1000, 10000), positivity = c(0.86, 1, 1, 1, 1)) model <- glm(positivity~concentration, family="binomial", data=df) summary(model) confint(model) ``` When running the model, I get a warning: ``` Warning messages: 1: In eval(family$initialize) : non-integer #successes in a binomial glm! 2: glm.fit: algorithm did not converge 3: glm.fit: fitted probabilities numerically 0 or 1 occurred ``` but I got something: ``` > summary(model)
Call: glm(formula = positivity ~ concentration, family = "binomial", data = df) Deviance Residuals: 1 2 3 4 5 0.00e+00 4.41e-04 2.00e-08 2.00e-08 2.00e-08 Coefficients: Estimate Std. Error z value Pr(>|z|) (Intercept) 0.223 216.154 0.001 0.999 concentration 1.592 216.131 0.007 0.994 (Dispersion parameter for binomial family taken to be 1) Null deviance: 4.6727e-01 on 4 degrees of freedom Residual deviance: 1.9445e-07 on 3 degrees of freedom AIC: 4.3016 Number of Fisher Scoring iterations: 25 ``` How can I now find the concentration that gives 95% positivity? Thanks -- Best regards, Luigi ______________________________________________ R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see 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.
