M
Milan Stehlík
Researcher at Johannes Kepler University of Linz
Publications - 121
Citations - 1116
Milan Stehlík is an academic researcher from Johannes Kepler University of Linz. The author has contributed to research in topics: Estimator & Optimal design. The author has an hindex of 17, co-authored 112 publications receiving 955 citations. Previous affiliations of Milan Stehlík include Federico Santa María Technical University & Comenius University in Bratislava.
Papers
More filters
Journal ArticleDOI
“SPOCU”: scaled polynomial constant unit activation function
TL;DR: A general novel methodology, scaled polynomial constant unit activation function “SPOCU,” is introduced and shown to work satisfactorily on a variety of problems, and it is shown that SPOCU can overcome already introduced activation functions with good properties on generic problems.
Journal ArticleDOI
The harmonic moment tail index estimator: asymptotic distribution and robustness
TL;DR: In this article, the harmonic moment tail index estimator is derived for distributions with regularly varying tails and a tuning parameter allows for regulating the trade-off between robustness and efficiency.
Journal ArticleDOI
On the favorable estimation for fitting heavy tailed data
TL;DR: This paper derives the exact distribution of the likelihood ratio tests of homogeneity and simple hypothesis on the tail index of a two-parameter Pareto model and discusses some problems that one can encounter when misemploying the log-normal assumption based methods supported by the Basel II framework.
Journal ArticleDOI
On robust testing for normality in chemometrics
TL;DR: In this article, the authors illustrate the need for robust normality testing in chemometrics with several examples, review a class of robustified omnibus Jarque-Bera tests and propose a new class of Robustified directed Lin-Mudholkar tests.
Journal ArticleDOI
Equidistant and D-optimal designs for parameters of Ornstein–Uhlenbeck process ☆
TL;DR: In this article, the authors provided a thorough study of small sample and asymptotical comparisons of the e±ciencies of equidistant designs with taking into account both the parameters of trend µ; as well as the parameter of covariance function r of Ornstein-Uhlenbeck process.