We introduce a new method for estimating the parameter α of the Clayton copulas within the framework of Algorithmic Inference. The method consists of a variant of the standard bootstrapping procedure for inferring random parameters, which we expressly devise to bypass the two pitfalls of this specific instance: the non independence of the Kendall statistics, customary at the basis of this inference task, and the absence of a sufficient statistic w.r.t. α. The variant is rooted on a numerical procedure in order to find the α estimate at a fixed point of an iterative routine. Numerical results show a good accuracy of the estimates, though paired in some cases with the complexity of the programs which compute them.
Algorithmic inference approach to learn copulas / B. Apolloni, S. Bassis - In: Probabilistic Numerics : Advances in Neural Information Processing Systems 25 (NIPS 2012) Workshop, 8 December 2012, Lake Tahoe, Nevada, USAZurich : Curran Associates, 2012. - pp. 1-5 (( Intervento presentato al 25. convegno Probabilistic Numerics : Advances in Neural Information Processing Systems (NIPS) Workshop tenutosi a Lake Tahoe nel 2012.
Algorithmic inference approach to learn copulas
B. ApolloniPrimo
;S. BassisUltimo
2012
Abstract
We introduce a new method for estimating the parameter α of the Clayton copulas within the framework of Algorithmic Inference. The method consists of a variant of the standard bootstrapping procedure for inferring random parameters, which we expressly devise to bypass the two pitfalls of this specific instance: the non independence of the Kendall statistics, customary at the basis of this inference task, and the absence of a sufficient statistic w.r.t. α. The variant is rooted on a numerical procedure in order to find the α estimate at a fixed point of an iterative routine. Numerical results show a good accuracy of the estimates, though paired in some cases with the complexity of the programs which compute them.Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.