• binomial distribution: number of successes in independent trials, each succeeding with the same probability
    • needs independent trials, exactly two outcomes each, constant
- $\binom{n}{k}$ counts the ways to place the $k$ successes among the $n$ trials
- mean $\mu = np$ ( a sum of $n$ indicators, by [[Linearity of Expectation]] ), variance $\sigma^2 = np(1 - p)$
- CDF: $P(X \le k) = \sum_{i=0}^{k} \binom{n}{i} p^i (1 - p)^{n - i}$
  • example: flip a fair coin 10 times, chance of exactly 6 heads
  • negative binomial: flip it around and count the failures before the -th success
    • expected total trials to get successes:
  • when it stops fitting or gets expensive
    • trials not independent ( sampling without replacement ): use the hypergeometric
    • large , small : Poisson with
    • large : normal via the Central Limit Theorem,