CMStatistics 2018: Start Registration
View Submission - CMStatistics
B0537
Title: Nearest comoment estimation with unobserved factors Authors:  Dries Cornilly - Vrije Universiteit Brussel (Belgium) [presenting]
Kris Boudt - Vrije Universiteit Brussel and VU Amsterdam (Belgium)
Tim Verdonck - KU Leuven and UAntwerpen - imec (Belgium)
Abstract: A minimum distance estimator is proposed for the higher order comoments of a multi-dimensional distribution exhibiting a lower dimensional latent factor structure. We derive the influence function of the proposed estimator and prove its consistency and asymptotic normality. The simulation study confirms the large gains in accuracy compared to the traditional sample comoments. The empirical usefulness of the novel framework is shown in applications of portfolio allocation under non-Gaussian objective functions and factor extraction in a dataset containing mental ability scores.