How do I find the Logistic Distribution for a Logit Regression in R As far as I am aware, R gives the output of a logit model, of the form:
glm.logit=glm(model,binomial(),Data.df)

as the log-odds ratio.
I would like to obtain the distributional function $\frac{exp(\beta'x_i)}{1+exp(\beta'x_i)}$ from my model
 A: Not sure what you are after, but if you wonder whether we could display prediction as probabilities instead of on the log-odds scale, you can simply use a dedicated function or call the predict method with argument type = "response", as shown below:
data(birthwt, package = "MASS")
birthwt$lwt <- birthwt$lwt * 0.45
birthwt$race <- factor(birthwt$race, levels = 1:3, labels = c("white", "black", "other"))
fm <- low ~ lwt + race
m <- glm(fm, data = birthwt, family = binomial)
d <- expand.grid(lwt = seq(40, 100), race = factor(levels(birthwt$race)))
d$yhat <- predict(m, d, type = "response")

The predictions can easily be plotted using any R graphical backend. Here is an example using ggplot:
library(ggplot2)
library(directlabels)
p <- ggplot(data = d, aes(x = lwt, y = yhat, color = race)) +
       geom_line(aes(group = race), size = 1) +
       guides(color = FALSE) +
       labs(x = "Mother weight (kg)", y = "Pr(low = 1)", caption = "Predicted response curves")
direct.label(p + aes(label = race), method = "smart.grid")


Note also that there are builtin tools for the logit function, $\text{logit}(x) = \frac{x}{1-x}$, or her loyal companion $\frac{1}{1 + \exp(-x)}$, namely qlogis() and plogis, which stand for the quantile and cumulative distribution functions for the logistic distribution.
