We prove that Linnik distributions are geometrically infinitely divisible, and clarify a characterization theorem for Linnik distributions concerning the stability of geometric summation. An explicit expression for absolute moments of Linnik distributions is also given.
A Note on the Comedian for Elliptical Distributions
β Scribed by Michael Falk
- Publisher
- Elsevier Science
- Year
- 1998
- Tongue
- English
- Weight
- 228 KB
- Volume
- 67
- Category
- Article
- ISSN
- 0047-259X
No coin nor oath required. For personal study only.
β¦ Synopsis
The comedian COM(X, Y) of random variables X, Y is a median based robust alternative to the covariance of X of Y. For the bivariate normal case it is known that COM(X, Y ), standardized by the median absolute deviations of X and Y, is a symmetric, strictly increasing and continuous function of the correlation coefficient \ with range [&1, 1] and can therefore serve as a robust alternative to . We show that this result, which is not true in general, extends to elliptical distributions even in the case where moments of X, Y do not exist.
π SIMILAR VOLUMES
It is well known that the sample covariance is not an efficient estimator of the covariance of a bivariate normal vector. We extend this result to elliptical distributions and we propose a simple explicit estimator, which is efficient in the normal case and which outperforms the sample covariance in
An algebraic method is given for the power series expansions of the Jacobi elliptic functions, based on the properties of the algebra associated with differential equations defining the functions.
The present paper deals with the determination of the fundamental frequency of vibration of clamped and simpty supported elliptical plates carrying concentric, concentrated masses. Numerical values of the fundamental frequency coefficient are presented as a function of the plate aspect ratio and of
The existence and uniqueness of a weak solution of a Neumann problem is discussed for a second-order quasilinear elliptic equation in a divergence form. The note is a continuation of a recent paper, where mixed boundary value problems were considered, which guaranteed the coerciveness of the problem
Suppose X,, X,, ..., X, are independent and identically distributed random variables with absolutely continuous distribution function F. It is known that if F is standard normal distribution then (i) 2 X : is a chi-square with n degrees of freedom and (ii) nX2 is a chi-square with 1 degrees of freed