Improved Hoeffding inequality for dependent bounded or sub-Gaussian random variables
نویسندگان
چکیده
When addressing various financial problems, such as estimating stock portfolio risk, it is necessary to derive the distribution of sum dependent random variables. Although deriving this requires identifying joint these variables, exact estimation variables difficult. Therefore, in recent years, studies have been conducted on bound with dependence uncertainty. In study, we obtain an improved Hoeffding inequality for bounded Further, expand above result case sub-Gaussian
منابع مشابه
Chapter 1: Sub-Gaussian Random Variables
where μ = IE(X) ∈ IR and σ = var(X) > 0 are the mean and variance of X . We write X ∼ N (μ, σ). Note that X = σZ + μ for Z ∼ N (0, 1) (called standard Gaussian) and where the equality holds in distribution. Clearly, this distribution has unbounded support but it is well known that it has almost bounded support in the following sense: IP(|X −μ| ≤ 3σ) ≃ 0.997. This is due to the fast decay of the...
متن کاملAn Extremal Inequality Related to Hypercontractivity of Gaussian Random Variables
We establish that Gaussian distributions are the optimizers for a particular optimization problem related to determining the hypercontractivity parameters for a pair of jointly Gaussian random variables.
متن کاملStrong Laws for Weighted Sums of Negative Dependent Random Variables
In this paper, we discuss strong laws for weighted sums of pairwise negatively dependent random variables. The results on i.i.d case of Soo Hak Sung [9] are generalized and extended.
متن کاملOn the Complete Convergence ofWeighted Sums for Dependent Random Variables
We study the limiting behavior of weighted sums for negatively associated (NA) random variables. We extend results in Wu (1999) and a theorem in Chow and Lai (1973) for NA random variables.
متن کاملFano's inequality for random variables
We extend Fano’s inequality, which controls the average probability of (disjoint) events in terms of the average of some Kullback-Leibler divergences, to work with arbitrary [0, 1]–valued random variables. Our simple two-step methodology is general enough to cover the case of an arbitrary (possibly continuously infinite) family of distributions as well as [0, 1]–valued random variables not nece...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Probability, Uncertainty and Quantitative Risk
سال: 2021
ISSN: ['2367-0126', '2095-9672']
DOI: https://doi.org/10.3934/puqr.2021003