B1502
Title: Optimal testing for symmetry on the torus
Authors: Sophia Loizidou - University of Luxembourg (Luxembourg) [presenting]
Christophe Ley - University of Luxembourg (Luxembourg)
Andreas Anastasiou - University of Cyprus (Cyprus)
Abstract: In bioinformatics, there has been a growing interest in modelling dihedral angles of amino acids by viewing them as data on the torus. Over the past years, this has motivated new proposals of distributions on the torus, both (pointwise) symmetric and sine-skewed asymmetric. In practice, knowing whether one should use the simpler symmetric models or the more convoluted yet more general asymmetric ones is relevant. So far, only parametric likelihood ratio tests have been defined to distinguish between a symmetric density and its sine-skewed counterpart. A new semi-parametric test is presented, which is valid under a given parametric hypothesis and a very broad class of symmetric distributions. A description of its construction, asymptotic properties under the null and alternative hypotheses, and finite sample behaviour (through Monte Carlo simulations) are given, as well as an application of the test on protein data.
