The Akaike information criterion is a measure of the relative goodness of fit of a statistical model. The AIC is grounded in the concept of information entropy, in effect offering a relative measure of the information lost when a given model is used to describe reality. It can be said to describe the tradeoff between bias and variance in model construction, or loosely speaking between accuracy and complexity of the model.
AIC values provide a means for model selection. AIC does not provide a test of a model in the sense of testing a null hypothesis; i.e. AIC can tell nothing about how well a model fits the data in an absolute sense. If all the candidate models fit poorly, AIC will not give any warning of that.
Read more about Akaike Information Criterion: Definition, How To Apply AIC in Practice, AICc, Relevance To Chi-squared Fitting, History, Bayesian Information Criterion
Famous quotes containing the words information and/or criterion:
“I have all my life been on my guard against the information conveyed by the sense of hearing—it being one of my earliest observations, the universal inclination of humankind is to be led by the ears, and I am sometimes apt to imagine that they are given to men as they are to pitchers, purposely that they may be carried about by them.”
—Mary Wortley, Lady Montagu (1689–1762)
“If we are to take for the criterion of truth the majority of suffrages, they ought to be gotten from those philosophic and patriotic citizens who cultivate their reason.”
—James Madison (1751–1836)