0
$\begingroup$

I know that the probability mass function of the binomial distribution is

$f(k,n,p) = \Pr(k;n,p) = \Pr(X = k) = {n\choose k}p^k(1-p)^{n-k}$

This functions returns the probability of getting exactly k successes within n trials, with p being the probability of success for each trial.

The cumulative function is

$F(k;n,p) = \Pr(X \le k) = \sum_{i=0}^{\lfloor k \rfloor} {n\choose i}p^i(1-p)^{n-i}$

where $\displaystyle \scriptstyle \lfloor k\rfloor \,$ is the "floor" under k, i.e. the greatest integer less than or equal to k. But this cumulative function gives, as I understood, the probability of having the number of successes between 0 and k.

How to get a cumulative function which gives me, at least one success, that is, the probability of having the number of successes between 1 and n.

For example, someone throws an even dice. After throwing 1000 times, what's the probability of getting at least once, the number 6?

$\endgroup$
  • $\begingroup$ Why do you use the floor function? In my opinion it is not necessary, since k is an integer $\endgroup$ – callculus Jul 18 '18 at 20:10
1
$\begingroup$

Hint

$$P(X\geq k) = 1-P(X \lt k)$$

Solution

$$P(X\geq 1) = 1-P(X\lt 1) = 1- {1000\choose 0}\left(1\over 6\right)^0\left(1-{1\over 6}\right)^{999} = 1-({5\over 6})^{999}\approx 1$$ This "trick" is pretty obvious as it stands and it's pretty common to use it when dealing with calculating the cumulative probability of at least $m$ successes of big data sets when $m\ll n$

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.