The Bernoulli distribution is one of the simplest probability distributions. It is based on the idea of a Bernoulli trial. This is an experiment with only two possible outcomes: "success" which occurs with probability p, and "failure", which occurs with probability 1 − p. The random variable X which equals 1 for a success and 0 for a failure has a Bernoulli(p) distribution.
Parameter | Range | Description |
---|---|---|
p | 0 ≤ p ≤ 1 | Probability of success |
Probability Mass Function
Support
Mean
Variance
Example | p |
---|---|
A fair coin is tossed. Let X = 1 for heads and X = 0 for tails. | 0.5000 |
A fair six-sided die is thrown. Let X = 1 if a 6 is thrown, and 0 otherwise. | 0.1667 |
The probability that an LED light bulb will fail this year is 0.2. Let X = 1 if the bulb fails this year and X = 0 if the bulb continues working. | 0.2000 |
X ∼ Bernoulli(p)
E(X) = , Var(X) =
The expected value can be changed directly by dragging left or right on the chart. This can also be done using the box below the chart which shows the mean ± one standard deviation. As the expected value gets closer to 0 or 1, the variance also approaches zero.
The expected value can be changed directly by dragging left or right on the chart. This can also be done using the box below the chart which shows the mean ± one standard deviation. As the expected value gets closer to 0 or 1, the variance also approaches zero.
The illustration above shows an experiment with only two possible outcomes:
- ❌
- X = 0 indicates "failure" which occurs with probability 1 − p.
- ✅
- X = 1 indicates "success" which occurs with probability p.
The simulation above shows a number U chose randomly from the interval [0, 1]. The light blue line shows the Bernoulli(p) random variable X which equals 1 if U falls in the green interval of length p, and 0 if U falls in the grey interval of length 1 − p. The histogram accumulates the results of each simulation.