a statistical technique in which the set of possible values for the
parameters of a distribution is estimated based on the most probable sample of observations that one might have obtained from that population. The values derived from this procedure are referred to as
maximum likelihood parameter estimates or
maximum likelihood estimates and can be used to obtain an overall estimate of how well a given model fits the data. Maximum likelihood techniques are used in several statistical methods, such as
logistic regression, hierarchical linear modeling, and
structural equation modeling. Also called
maximum likelihood estimation (
MLE).