 Cumulative distribution function of a binomial random variable

I've a random variable X/n, where X is a binomial random variable with p=1/2 and n= 10, 100, 1000. The goal is to plot the cumulative distribution function of X/n.

I'm wondering why the first argument of the command pbinom is x*n.

delta = 1/1000
x = seq(0, 1, by=delta)

plot(x=NULL, y=NULL, xlim=c(0,1), ylim=c(0,1), xlab='x', ylab='CDF')

n = 10
y = pbinom(x*n, n, 1/2)
lines(x, y, type='s', col='red')

n = 100
y = pbinom(x*n, n, 1/2)
lines(x, y, type='s', col='blue')

n = 1000
y = pbinom(x*n, n, 1/2)
lines(x, y, type='s')

If we label the states of X as 0 and 1, x represents the fraction of the n samples that had X = 1. When x = 0, there were no observations of X = 1 and when x = 1, all n of the samples had X = 1. The other 999 values of x * n represent intermediate cases. When n = 10, almost all of the values of x * n do not represent actually realizable results of integer values of observations. The resulting value remains constant until the next integer threshold, making the stair step appearance of the plot.

This topic was automatically closed 21 days after the last reply. New replies are no longer allowed.

If you have a query related to it or one of the replies, start a new topic and refer back with a link.