Bernoulli Distribution

Understanding Bernoulli Distribution

The Bernoulli distribution is one of the simplest discrete probability distributions in statistics. It is a distribution for a random variable that takes on only two possible outcomes, often labeled as 1 (success) and 0 (failure). The Bernoulli distribution is a special case of the binomial distribution where a single trial, or experiment, is conducted. It is named after the Swiss mathematician Jacob Bernoulli who studied this probability distribution in depth.

Characteristics of Bernoulli Distribution

The key characteristic of a Bernoulli distribution is its dichotomous outcome: only two possible results are considered, which makes it particularly useful for modeling events that have a binary outcome, such as a coin toss (heads or tails), a free-throw shot (made or missed), or whether it rains on a particular day (yes or no).

The probability of success (the outcome being labeled as 1) is denoted by 'p', while the probability of failure (the outcome being labeled as 0) is denoted by '1-p'. The mean, or expected value, of a Bernoulli random variable is 'p', and the variance is 'p(1-p)'.

Mathematical Definition

The probability mass function (PMF) of a Bernoulli distributed random variable 'X' is defined as:

P(X = 1) = p

P(X = 0) = 1 - p

where 'p' is the probability of the outcome being a success (X = 1). The PMF can also be expressed using the indicator function:

P(X = x) = p^x * (1-p)^(1-x)

for x in {0, 1}. This compact form of the PMF shows that when x is 1 (success), the probability is 'p', and when x is 0 (failure), the probability is '1-p'.

Applications of Bernoulli Distribution

Bernoulli distribution has numerous applications in various fields. In quality control, it can model the pass/fail outcome of a product inspection. In finance, it can represent the win/loss outcome of a single investment. In medicine, it can be used to model the effectiveness of a treatment where the outcome is either improvement or no improvement. In information theory, it is used to model the binary data in communication channels, such as bits being transmitted correctly or incorrectly.

Properties of Bernoulli Distribution

Some of the important properties of the Bernoulli distribution include:

  • Memoryless: The outcome of one Bernoulli trial does not affect the outcome of another. Each trial is independent.
  • Binary: The distribution is defined only for binary outcomes.
  • Mean and Variance: The mean of the distribution is 'p', and the variance is 'p(1-p)'.
  • Skewness and Kurtosis:

    The skewness of the Bernoulli distribution is given by (1-2p) / sqrt(p(1-p)), and the excess kurtosis is 6p^2 - 6p + 1 / p(1-p).

Relation to Other Distributions

The Bernoulli distribution is closely related to other distributions:

  • When multiple independent Bernoulli trials are conducted, the sum of the outcomes follows a binomial distribution.
  • If the number of trials goes to infinity while keeping the expected number of successes fixed, the distribution of the normalized count of successes converges to a Poisson distribution.
  • The geometric distribution can be thought of as the number of Bernoulli trials needed to get the first success.


The Bernoulli distribution is fundamental in the study of probability and statistics due to its simplicity and the wide range of phenomena it can model. It serves as a building block for more complex distributions and is a staple in introductory statistics and probability courses. Understanding the Bernoulli distribution is essential for anyone looking to grasp the basics of statistical modeling and probability theory.

Please sign up or login with your details

Forgot password? Click here to reset