Feature Selection - Optimality Criteria

Optimality Criteria

There are a variety of optimality criteria that can be used for controlling feature selection. The oldest are Mallows' Cp statistic and Akaike information criterion (AIC). These add variables if the t-statistic is bigger than .

Other criteria are Bayesian information criterion (BIC) which uses, minimum description length (MDL) which asymptotically uses, Bonnferroni / RIC which use, maximum dependency feature selection, and a variety of new criteria that are motivated by false discovery rate (FDR) which use something close to .

Read more about this topic:  Feature Selection

Famous quotes containing the word criteria:

    Every sign is subject to the criteria of ideological evaluation.... The domain of ideology coincides with the domain of signs. They equate with one another. Wherever a sign is present, ideology is present, too. Everything ideological possesses semiotic value.
    —V.N. (Valintin Nikolaevic)