Abstract | ||
---|---|---|
The Kullback information criterion, KIC and its univariate bias-corrected version, KICc may be viewed as estimators of the expected Kullback-Leibler symmetric divergence. This correspondence examines the overfitting properties of KIC and KICc through the probabilities of overfitting both in finite samples and asymptotically. It is shown that KIC and KICc have much smaller probabilities of overfitting than the Akaike information criterion, AIC, and its bias-corrected version AICc. |
Year | DOI | Venue |
---|---|---|
2006 | 10.1016/j.sigpro.2006.01.002 | Signal Processing |
Keywords | Field | DocType |
overfitting property,smaller probability,univariate bias-corrected version,Kullback information criterion,finite sample,Akaike information criterion,expected Kullback-Leibler symmetric divergence,bias-corrected version | Akaike information criterion,Model selection,Overfitting,Univariate,Statistics,Mathematics,Estimator | Journal |
Volume | Issue | ISSN |
86 | 10 | Signal Processing |
Citations | PageRank | References |
0 | 0.34 | 3 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Abd-Krim Seghouane | 1 | 193 | 24.99 |
SeghouaneAbd-Krim | 2 | 5 | 0.84 |