Separate specifications for p and n in a binomial GLM For a binomial GLM, both the probability and the number of trials are important for each data entry. Using the glm fucntion in R, how do I specify them separately and explicitly?
Previously, when using glm for the binomial family, I used glm(cbind(V4, V5) ~ V1 + V2 + V3, family=binomial) where V4 is the number of success and V5 is the number of failures. Is there any other way to do it?
 A: There are two main ways to do binomial glms; you mention one (we'll call that the first way). 
There's also a third way I'll cover at the end, which by the sound of it is perhaps what you're after.

The second way 
This is clearly described in the help on GLMs (?glm), which is to supply the outcome for each individual bernoulli (0-1) trial. The help says:

For binomial and quasibinomial families the response can also be specified as a factor (when the first level denotes failure and all others success) or as a two-column matrix with the columns giving the numbers of successes and failures.

(The last part in that quote describes your first way; the first two-thirds describes the way I am discussing now.)
That is, if you give it a factor as your response, it will be interpreted as a 0-1 variable, where the first level of the factor is "0" or "Failure" and all other levels count as "1" or "Success". If you supply such a factor (or a 1-column variable that can be coerced to one) R then "knows" there's a column of 1's for the $n$, so you don't need to specify that.
Here's some sample code to generate some data and run it:
x=c(9:20,5:25)
p=1/(1+exp(-(-7.5+.5*x)))
y=rbinom(x,1,p)
head(y,12)
plot(x,y)
points(x,p,pch=".",cex=4,col=4)
summary(glm(y~x,family=binomial))
points(x,fitted(glm(y~x,family=binomial)),col=3,cex=0.7)

Note that y was numeric (0-1) not a factor but since only one column was supplied it should be coerced to a factor by R; that is, supplying a numeric 0-1 variable works as-is.
Here's the plot the above code produces for my random numbers (if you run the code you'll get different numbers, of course). The black circles are the 0-1 outcomes, $y$, against the independent variable, $x$, while the blue dots are the population $p$'s from which the $y$s were randomly generated. The green circles are the fitted values from the model.

If you want my particular y, here's a copy:
y <- c(0L, 0L, 0L, 0L, 0L, 1L, 0L, 0L, 1L, 1L, 1L, 1L, 0L, 0L, 0L, 0L, 0L, 
      0L, 0L, 0L, 1L, 0L, 1L, 0L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L)


The third way
(This way is the way to do the sample $p$ and $n$ 'separately and explicitly'.)
You can supply sample $p$'s and $n$'s, by giving the $p$'s as the response and the $n$'s as weights:
 x <- c(12,15,16,18,20)
 num.tr <- c(8,10,7,14,6)
 num.s <- c(2,3,3,9,5)
 prop.s <- num.s/num.tr
 glm( prop.s ~ x, weight=num.tr, family=binomial)

Compare that with the "usual" way:
 glm( cbind(num.s, num.tr - num.s ) ~ x, family=binomial)

