"Akaike's Information Criterion is a criterion for selecting among nested econometric models."

About, Inc. (2006)

"An index used in a number of areas as an aid to choosing between competing models. It is defined as

where

Everitt (1998), The Cambridge Dictionary of Statistics

"Akaike (1973) defined the most well-known criterion as AIC = - ln *L* + *p*, where *L* is the likelihood for an estimated model with *p* parameters."

Hjorth (1994)

"When a model involving *q* parameters is fitted to data, the criterion is defined as -2*L _{q}* + 2

Marriott (1990), A Dictionary of Statistical Terms

"Criterion, introduced by Akaike in 1969, for choosing between competing statistical models. For categorical data this amounts to choosing the model that minimizes *G*^{2} - 2*v*, where *G*^{2} is the likelihood-ratio goodness-of-fit statistic *v* is the number of degrees of freedom associated with the model."

Upton and Cook (2002)

"The **Akaike information criterion (AIC)** (pronounced, approximately, ah-kah-ee-kay), developed by Professor Hirotugu Akaike (?? ??) in 1971 and proposed in 1974, is a statistical model fit measure."

Wikipedia (2006)