Weak properties and robustness of t-Hill estimatorsSpringer Science and Business Media LLC - - 2016
Pavlina Jordanova, Zdeněk Fabián, Philipp Hermann, Luboš Střelec, Andrés Rivera, Stéphane Girard, Sebastián Torres, Milan Stehlík
We describe a novel method of heavy tails estimation based on transformed score (t-score). Based on a new score moment method we derive the t-Hill estimator, which estimates the extreme value index of a distribution function with regularly varying tail. t-Hill estimator is distribution sensitive, thus it differs in e.g. Pareto and log-gamma case. Here, we study both forms of the estimator, i.e. t-...... hiện toàn bộ
Exact asymptotics of component-wise extrema of two-dimensional Brownian motionSpringer Science and Business Media LLC - Tập 23 - Trang 569-602 - 2020
Krzysztof Dȩbicki, Lanpeng Ji, Tomasz Rolski
We derive the exact asymptotics of
$ {\mathbb {P} \left \{ \underset {t\ge 0}{\sup } \left (X_{1}(t) - \mu _{1} t\right )> u, \ \underset {s\ge 0}{\sup } \left (X_{2}(s) - \mu _{2} s\right )> u \right \} },\ \ u\to \infty , $
where (X1(t), X2(s))t, s≥ 0 is a correlated two-dimensional Brownian motion with correlation ρ ∈ [− 1,1] and μ1, μ2 > 0. It appears that the play between ρ and μ1, μ2 lead...... hiện toàn bộ
Tail asymptotics for the sum of two heavy-tailed dependent risksSpringer Science and Business Media LLC - Tập 9 - Trang 107-130 - 2006
Hansjörg Albrecher, Søren Asmussen, Dominik Kortschak
Let X
1
, X
2 denote positive heavy-tailed random variables with continuous marginal distribution functions F
1 and F
2, respectively. The asymptotic behavior of the tail of X
1
+X
2 is studied in a general copula framework and some bounds and extremal properties are prov...... hiện toàn bộ
Distribution of the height of local maxima of Gaussian random fieldsSpringer Science and Business Media LLC - Tập 18 - Trang 213-240 - 2014
Dan Cheng, Armin Schwartzman
Let {f(t) : t ∈ T} be a smooth Gaussian random field over a parameter space T, where T may be a subset of Euclidean space or, more generally, a Riemannian manifold. We provide a general formula for the distribution of the height of a local maximum ℙ{f(t
0) > u|t
0 is a local maximum of f(t)} when f is non-stationary. Moreover, we establish asymptotic approximations ...... hiện toàn bộ
Asymptotics of convolution with the semi-regular-variation tail and its application to riskSpringer Science and Business Media LLC - Tập 21 - Trang 509-532 - 2018
Zhaolei Cui, Edward Omey, Wenyuan Wang, Yuebao Wang
In this paper, according to a certain criterion, we divide the exponential distribution class into some subclasses. One of them is closely related to the regular-variation-tailed distribution class, and is called the semi-regular-variation-tailed distribution class. The new class possesses several nice properties, although distributions in it are not convolution equivalent. We give the precise tai...... hiện toàn bộ
Large Deviation Probabilities for Square-Gaussian Stochastic ProcessesSpringer Science and Business Media LLC - - 1999
Yuri Kozachenko, Oksana Moklyachuk
We investigate properties of square-Gaussian stochastic processes. These processes are formed by quadratic forms of Gaussian processes or by limits in the mean square of quadratic forms of Gaussian processes. Special classes of these processes are determined and investigated. For processes from these classes estimates of large deviation probability are obtained. These estimates we use to estimate ...... hiện toàn bộ
Polynomial power-Pareto quantile function modelsSpringer Science and Business Media LLC - Tập 13 - Trang 291-314 - 2009
Yuzhi Cai
In this paper we propose a polynomial power-Pareto quantile function model and a Bayesian method for parameters estimation. We also carried out simulation studies and applied our methodology to real data sets empirically. The results show that a quantile function approach to statistical modelling is very flexible due to the properties of quantile functions, and that the combination of a power and ...... hiện toàn bộ