central limit theorem: a standalone construct

Abraham de Moivre first derived a version of this result in 1733, showing that the count of successes in many independent trials (a binomial count, such as the number of heads in repeated coin tosses) is closely approximated by the smooth bell-shaped normal curve, a case Pierre-Simon Laplace extended and sharpened in his 1812 Théorie analytique des probabilités, giving what is now called the de Moivre-Laplace theorem. The general statement, that the sum or average of a large number of independent random quantities tends toward a normal distribution almost regardless of how each individual quantity is distributed, was placed on rigorous footing by Aleksandr Lyapunov in 1901 and by Jarl Waldemar Lindeberg in 1922, and George Polya gave the theorem its enduring name, the central limit theorem, in 1920. In plain terms, when many small, independent effects add up, their combined total settles into the familiar bell curve, which is why that curve recurs so widely across measurement and error. What makes the theorem a landmark is its universality: it explains why the normal distribution appears across physics, biology, and the social sciences, and it underwrites much of classical statistical inference, including the confidence intervals and significance tests that rely on the approximate normality of estimates.[1][2][3][4][5]

Unit

A limit theorem in probability theory describing the asymptotic distribution of standardized sums or means of independent random variables

Recovery means

Not applicable

Measured by

Stated and proved as a mathematical theorem under stated conditions; assessed empirically through the convergence of standardized sample sums or means to the standard normal distribution, checked with normal quantile plots and goodness-of-fit tests