Maximum likelihood

method of estimating the parameters of a statistical model, given observations

Maximum likelihood estimation (or maximum likelihood) is the name used for a number of ways to guess the parameters of a parametrised statistical model. These methods pick the value of the parameter in such a way that the probability distribution makes the observed values very likely. The method was mainly devleoped by R.A.Fisher in the early 20th century. A likelihood estimation, where probabilities are known beforehand is known as Maximum a posteriori estimation.