Model order estimation via penalizing adaptively the likelihood (PAL)
2013 (English)In: Signal Processing, ISSN 0165-1684, E-ISSN 1872-7557, Vol. 93, no 11, 2865-2871 p.Article in journal (Refereed) Published
This paper introduces a novel rule for model order estimation based on penalizingadatively the likelihood (PAL). The penalty term of PAL, which is data adaptive (as the name suggests), has several unique features: it is "small" (e.g. comparable to AIC penalty) for modelorders, let us say n(0), less than or equal to the true order, denoted by no, and it is "large" (e.g. of the same order as BIC penalty) for n > n(o); furthermore this is true not only as the data sample length increases (which is the case most often considered in the literature) but also asthe signal-to-noise ratio (SNR) increases (the harder case for AIC, BIC and the like); and this "oracle-like" behavior of PAL's penalty is achieved without any knowledge about n(0). Thepaper presents a number of simulation examples to show that PAL has an excellent performance also in non-asymptotic regimes and compare this performance with that of AIC and BIC.
Place, publisher, year, edition, pages
2013. Vol. 93, no 11, 2865-2871 p.
Research subject Signal Processing
IdentifiersURN: urn:nbn:se:uu:diva-205725DOI: 10.1016/j.sigpro.2013.03.014ISI: 000322937700001OAI: oai:DiVA.org:uu-205725DiVA: diva2:642567