AIC for the non-concave penalized likelihood method (Q2414941)

From MaRDI portal
scientific article
Language Label Description Also known as
English
AIC for the non-concave penalized likelihood method
scientific article

    Statements

    AIC for the non-concave penalized likelihood method (English)
    0 references
    0 references
    0 references
    0 references
    0 references
    17 May 2019
    0 references
    A generalized linear model is considered based on a natural exponential family. A regularization method is presented which provides an estimator with nice asymptotic properties. The asymptotic bias of the estimator is found which yields an information criterion based on the original definition of the Akaike information criterion by considering minimization of the prediction error rather than model selection consistency. In fact a function of the score statistic is derived that is asymptotically equivalent to the non-concave penalized maximum likelihood estimator, and then an estimator is provided of the Kullback-Leibler divergence between the true distribution and the estimated distribution. A simulation study shows the validity of the proposed information criterion for several models.
    0 references
    0 references
    0 references
    0 references
    0 references
    information criterion
    0 references
    Kullback-Leibler divergence
    0 references
    \(\ell _q\) regularization
    0 references
    statistical asymptotic theory
    0 references
    tuning parameter
    0 references
    variable selection
    0 references
    0 references
    0 references
    0 references
    0 references
    0 references
    0 references
    0 references
    0 references
    0 references