Earthquake preferred days in the Lake Baikal and Yunnan-Sichuan Regions

<p>Understanding the cyclic and other forces governing geodynamics may provide fundamental clues for unraveling characteristics of earthquakes occurrence, which remains spectacular evidence induced by plate tectonics fueled by tidal drag and associated global cooling of the Earth (Riguzzi et al., 2010; Doglioni and Panza, 2015).</p><p>To check the hypotheses of earthquake-preferred days the nonparametric Kuiper test statistics for cyclic variations applied to the seismic evidence resulting from the empirical distributions of the earthquake origin time versus solar (Julian Day, JD) or lunar (Moon Phase, MP) cycles. We present the results of the Kuiper test application to seismicity of the Lake Baikal and Yúnnán-Sichuan Regions aimed at verification on a solid statistical base the hypotheses of uniform distribution of earthquake origin time JD’s and MP’s in respect to the earthquake magnitude cut-off.</p>

A Myth of Preferred Days of Strong Earthquakes?

Existing evidence on the origin times of magnitude M≥7.5 earthquakes worldwide, based on authoritative earthquake catalogs, does not permit rejection of the null hypotheses of random coincidental occurrence at any time during the Earth or the Moon cycles. Specifically, the nonparametric Kuiper test statistics for cyclic variations applied to seismic evidence resulting from the empirical distributions of the M≥7.5 earthquake origin time Julian day (JD) and the Moon phase (MP) do not allow the rejection of the null hypotheses of uniform distributions within the corresponding cycles. On the other hand, the same Kuiper test permits the rejection of the null hypotheses of the same chance of occurrence on any JD or MP for strong magnitude M≥6.0 earthquakes, at least for the past four decades of presumably the best-earthquake determinations and, in particular, for earthquakes in the Northern Hemisphere (with an evident seasonal pattern). The nonparametric two-sample Kolmogorov–Smirnov test statistics suggest no preferred distances to the Moon at the occurrence of large earthquakes. All of this contributes, to the results of solid statistical testing of hypotheses, for a better understanding of the complex seismic response of the Earth’s lithosphere to periodic gravitational loading.

Validação de Modelos Internos no Brasil: Análise de Metodologias de Backtesting de VaR

The purpose of this paper is to analyze backtesting methodologies of VaR, focusing on aspects as suitability to volatile markets and limited data set. We verify, from regulatory standpoint, tests to complement the Basel traffic light results, using simulated and real data. The results indicate that tests based on failures proportion are not adequate for small samples even fro 1,000 observations. The Basel criterion is conservative and has low power, which does not invalidate its application, as the criterion is only one of the procedures adopted in internal model validation process. Thus, it is suggested using tests that capture the shape of returns distribution, as the Kuiper test, in addition to the Basel criterion.