NWU Institutional Repository

Large sample behavior of the Bernstein copula estimator

dc.contributor.authorJanssen, Paul
dc.contributor.authorSwanepoel, Jan
dc.contributor.authorVeraverbeke, Noël
dc.contributor.researchID10177507 - Swanepoel, Jan Willem Hendrik
dc.date.accessioned2016-06-02T06:22:55Z
dc.date.available2016-06-02T06:22:55Z
dc.date.issued2012
dc.description.abstractBernstein polynomial estimators have been used as smooth estimators for density functions and distribution functions. The idea of using them for copula estimation has been given in Sancetta and Satchell (2004). In the present paper we study the asymptotic properties of this estimator: almost sure consistency rates and asymptotic normality. We also obtain explicit expressions for the asymptotic bias and asymptotic variance and show the improvement of the asymptotic mean squared error compared to that of the classical empirical copula estimator. A small simulation study illustrates this superior behavior in small samplesen_US
dc.identifier.citationJanssen, P. et al. 2012. Large sample behavior of the Bernstein copula estimator. Journa of statistical planning and inference, 142:1189-1197. [https://doi.org/10.1016/j.jspi.2011.11.020]en_US
dc.identifier.issn0378-3758
dc.identifier.urihttp://hdl.handle.net/10394/17578
dc.identifier.urihttp://www.sciencedirect.com/science/article/pii/S0378375811004253
dc.identifier.urihttps://doi.org/10.1016/j.jspi.2011.11.020
dc.language.isoenen_US
dc.publisherElsevieren_US
dc.subjectBernstein estimatoren_US
dc.subjectasymptotic propertiesen_US
dc.subjectcopula estimatoren_US
dc.subjectmean squared erroren_US
dc.titleLarge sample behavior of the Bernstein copula estimatoren_US
dc.typeArticleen_US

Files