The distribution of a discrete random variable taking two values, usually 0 and 1. An experiment or trial that has exactly two possible results, often classified as ‘success’ or ‘failure’, is called a Bernoulli trial. If the probability of a success is p and the number of successes in a single experiment is the random variable X, then X is a Bernoulli variable (also called a binary variable) and is said to have a Bernoulli distribution with parameter p. The mean of the distribution is p and the variance is p(1−p). The probability function is given byA binomial variable (see binomial distribution) with parameters n and p is the number of successes in n independent Bernoulli trials and may be regarded as the sum of n independent observations of a Bernoulli variable with parameter p. The phrase ‘Bernoullian trial’ was used in a 1937 book on probability.