National Repository of Grey Literature 12 records found  1 - 10next  jump to record: Search took 0.02 seconds. 
Divergence mezi modely a daty pri hypotetickém a empirickém kvantování
Vajda, Igor ; van der Meulen, Edward
It is shown that the hypothetical quantization generates classical Pearson-type statistical criteria while the empirical quantization generates criteria asymptotically equivalent to the classical spacings-type statistical criteria. Asymptotic properties of the empirically generated criteria are derived and optimality of the quadratic criterion is proved.
Zobecněná informační kriteria pro optimální Bayesovské rozhodování
Morales, D. ; Vajda, Igor
Upper and lower levels of Byes decision errors and risk achieved under given lelvels of generalized information are evaluated. Quadratic information is shown to be optimal error and risk characteristic in infinite class of the most common generalized information measures including the measure of Shannon.
Výpočet těsných mezí pro divergenceí
Harremoes, P. ; Vajda, Igor
The paper presents a general method for evaluation of the joint range of pairs of f-divergences. This range provides tight maxima and minima for one f-divergence for given value of the other. Applications in information theory, identification and detection are mentioned.
Odhady založené na modifikované mocninné divergenci: Chování v modelech polohy
Frýdlová, Iva
Maximum subdivergence estimators and minimum superdivergence estimators are extensively studied using mainly simulation. Snesitivity of the subdivergence estimators to the so-called escort parameters was discovered.
Několik aplikací divergenčního kriteria ve spojitých rodinách
Broniatowski, M. ; Vajda, Igor
Power subdivergence, power superdivergence, power pseudodistance and Renyi pseudodistance are introduced as statistical point estimation criteria.Basic theory of the corresponding four types of estimators including the Fisher consistency and influence curves is presented. Explicit formulas are obtained for estimators of location and scale used in the research of diploma and PhD students.
O eficientnosti rozhodování o statistických modelech založeném na f-divergencích empirických distribucí
Vajda, Igor
Limit theorems for divergence statistics under hypotheses and local alternatives needed for testing the goodness-of-fit. New results about the Pitman and Bahadur efficiency of divergence statistics.
Zobecnění Devrouye-Lugosiho teorému
Berlinet, A. ; Vajda, Igor
Estimation of distributions of stochastic models is studied and adaptive selection of a better of two estimates is considered. Devroye and Lugosi's recent book on this topic established a theorem on the total variation error of a selection rule proposed by them. We extended this theorem to arbitrary metric divergence errors, and also to more general alternative selection rules.
Asymptotické vlastnosti intervalových statistik
Vajda, Igor ; van der Meulen, E. C.
This is a continuation of our previous paper dealing with simple spacings. Here we deal with arbitrary m-spacings. We introduce new spacings statistics measuring divergence of hypothetical and empirical distributions. It is proved that they are asymptotically equivalent with all spacings statistics known from the literature. General asymptotic equivalence of this type is a new result with interesting applications.
Zobecněná informační kriteria pro optimální bayesovské rozhodování
Vajda, Igor ; Morales, D.
Probability of error and risk of Bayesian idetifier of state or Bayesian detector of important phenomena are characterized by means of classical Shannonian information criteria and their more recent generalizations.
Bregmanovy vzdálenosti v exponenciálních rodinách pravděpodobnostních distribucí
Vajda, Igor ; Stummer, W.
The paper presents explicit formulas for general exponential probability distributions

National Repository of Grey Literature : 12 records found   1 - 10next  jump to record:
Interested in being notified about new results for this query?
Subscribe to the RSS feed.