The distribution of a quantity whose logarithm is Gaussian; arises from multiplicative processes.The log-normal distribution describes a random variable whose logarithm is normally distributed. It arises naturally when a quantity is the product of many independent positive factors, such as stock prices, income levels, or the size of biological organisms. Unlike the normal distribution, it is skewed to the right and only takes positive values, making it suitable for data that cannot be negative.
The distribution was first studied by the Scottish mathematician John Aitchison and his colleagues in the 1950s, though its use in economics dates back to the work of Robert Gibrat in 1931 on the 'law of proportionate effect'.
If Y is normally distributed with mean μ and variance σ², then X = e^Y is log-normally distributed. The probability density function is f(x) = (1/(xσ√(2π))) * exp(-(ln x - μ)²/(2σ²)) for x > 0. The mean of X is exp(μ + σ²/2) and the median is exp(μ). The distribution's skewness increases with σ, making it highly asymmetric for large variance.
It is widely used in finance for modeling asset prices (e.g., stock returns), in environmental science for pollutant concentrations, and in biology for the size of organisms or the incubation period of diseases.
The product of many independent positive random variables tends to be log-normal, even if the individual variables are not, due to the central limit theorem applied to their logarithms.


