Search results for "Statistics"
showing 10 items of 7671 documents
On the autocorrelation function of Rice processes for unsymmetrical doppler power spectral densities
2010
In this paper, we derive an analytical expression for the ACF of Rice processes in the general case of unsymmetrical Doppler power spectral densities. This expression, which is obtained based on the multidimensional Gaussian distribution approach, is shown to cover the ACF of Rayleigh processes as a special case. Various numerical examples are presented to illustrate the impact of the channel parameters on the ACF. Computer simulations, considering the von Mises distribution for the angle of arrivals, are also performed to check the validity of the analytical result. Finally, the analysis of the covariance spectrum is addressed.
Arm Space Decomposition as a Strategy for Tackling Large Scale Multi-armed Bandit Problems
2013
Recent multi-armed bandit based optimization schemes provide near-optimal balancing of arm exploration against arm exploitation, allowing the optimal arm to be identified with probability arbitrarily close to unity. However, the convergence speed drops dramatically as the number of bandit arms grows large, simply because singling out the optimal arm requires experimentation with all of the available arms. Furthermore, effective exploration and exploitation typically demands computational resources that grow linearly with the number of arms. Although the former problem can be remedied to some degree when prior knowledge about arm correlation is available, the latter problem persists. In this…
An Improved Method for Estimating the Time ACF of a Sum of Complex Plane Waves
2010
Time averaging is a well-known technique for evaluating the temporal autocorrelation function (ACF) from a sample function of a stochastic process. For stochastic processes that can be modelled as a sum of plane waves, it is shown that the ACF obtained by time averaging can be expressed as a sum of auto-terms (ATs) and cross-terms (CTs). The ATs result from the autocorrelation of the individual plane waves, while the CTs are due to the cross-correlation between different plane wave components. The CTs cause an estimation error of the ACF. This estimation error increases as the observation time decreases. For the practically important case that the observation time interval is limited, we pr…
Modelling Systemic Cojumps with Hawkes Factor Models
2013
Instabilities in the price dynamics of a large number of financial assets are a clear sign of systemic events. By investigating a set of 20 high cap stocks traded at the Italian Stock Exchange, we find that there is a large number of high frequency cojumps. We show that the dynamics of these jumps is described neither by a multivariate Poisson nor by a multivariate Hawkes model. We introduce a Hawkes one factor model which is able to capture simultaneously the time clustering of jumps and the high synchronization of jumps across assets.
Sliding mode exponential H<inf>&#x221E;</inf> synchronization of Markovian jumping master-slave systems with time-delays and nonlinea…
2011
This paper investigates the problem of exponential H ∞ synchronization for a class of master-slave systems with both discrete and distributed time-delays, norm-bounded nonlinear uncertainties and Markovian switching parameters. Using an appropriate Lyapunov-Krasovskii functional, some delay-dependent sufficient conditions and a synchronization law which include the master-slave parameters are established for designing a delay-dependent mode-dependent sliding mode exponential H ∞ synchronization control law in terms of linear matrix inequalities. The controller guarantees the H ∞ synchronization of the two coupled master and slave systems regardless of their initial states. A numerical examp…
Stochastic Response on Non-Linear Systems under Parametric Non-Gaussian Agencies
1992
The probabilistic response characterization of non-linear systems subjected to non-normal delta correlated parametric excitation is obtained. In order to do this an extension of both Ito’s differential rule and the Fokker-Planck equation is presented, enabling one to account for the effect of the non-normal input. The validity of the approach reported here is confirmed by results obtained by means of a Monte Carlo simulation.
Solvability of the divergence equation implies John via Poincaré inequality
2014
Abstract Let Ω ⊂ R 2 be a bounded simply connected domain. We show that, for a fixed (every) p ∈ ( 1 , ∞ ) , the divergence equation div v = f is solvable in W 0 1 , p ( Ω ) 2 for every f ∈ L 0 p ( Ω ) , if and only if Ω is a John domain, if and only if the weighted Poincare inequality ∫ Ω | u ( x ) − u Ω | q d x ≤ C ∫ Ω | ∇ u ( x ) | q dist ( x , ∂ Ω ) q d x holds for some (every) q ∈ [ 1 , ∞ ) . This gives a positive answer to a question raised by Russ (2013) in the case of bounded simply connected domains. In higher dimensions similar results are proved under some additional assumptions on the domain in question.
Stochastic linearization for the response of MDOF systems subjected to external and parametric Gaussian excitations
1991
The stochastic linearization approach is examined for the most general case of non zero-mean response of non-linear MDOF systems subjected to parametric and external Gaussian white excitations. It is shown that, for these systems too, stochastic linearization and Gaussian closure are two equivalent approaches if the former is applied to the coefficients of the Ito differential rule. Moreover, an extension of the Atalik-Utku approach to non zero-mean response systems allows to obtain simple formulations for the linearized drift coefficients. Some applications show the good accuracy of the method.
Comment améliorer la prévision des ventes pour le marketing ? Les apports de la théorie du chaos
2013
La littérature en marketing constate un décalage entre les avancées réalisées par les chercheurs qui développent de nouvelles méthodes de prévision des ventes, et l'usage massif de méthodes traditionnelles reposant sur l'hypothèse de linéarité des processus analysés. Cette recherche expose la contribution potentielle de la théorie du chaos à l'amélioration de la prévision des ventes. Une illustration de ces apports est proposée avec une application à la prévision des ventes de consoles de jeux vidéo au Japon. Les résultats mettent en évidence la capacité de la méthode proposée à détecter la présence de chaos dans la série et montrent la possibilité de préciser l'horizon de prévisibilité des…
How many longitudinal covariate measurements are needed for risk prediction?
2014
Abstract Objective In epidemiologic follow-up studies, many key covariates, such as smoking, use of medication, blood pressure, and cholesterol, are time varying. Because of practical and financial limitations, time-varying covariates cannot be measured continuously, but only at certain prespecified time points. We study how the number of these longitudinal measurements can be chosen cost-efficiently by evaluating the usefulness of the measurements for risk prediction. Study Design and Setting The usefulness is addressed by measuring the improvement in model discrimination between models using different amounts of longitudinal information. We use simulated follow-up data and the data from t…