ls a Normal Coputa the Right Coputa?
Abstract
Nowadays coputas are extensivety used in economic and finance apptications, with the Gaussian coputa being very popular despite ruting out non-tinear dependence, particutarty in the [ower tait We derive computationatty simpte and intuitive expressions for score tests of Gaussian copu[as against Generatised Hyperbotic atternatives, which inctude the symmetric and asymmetric Student t, and Hermite polynomiaI expansions We decompose our tests into third and fourth moment anatogues, and obtain more powerful one-sided Kuhn-Tucker versions that are equivatent to the Liketihood Ratio test, whose asymptotic distribution we provide We conduct detaited Monte Carto exercises to study our proposed tests in f inite samptes
This event is organised by the Econometric Institute.
Twitter: @MetricsSeminars
