ABSTRACT
We present a method for the reconstruction of the dynamics of processes with discrete time. The time series from such a system is described by a stochastic recurrence equation, the continuous form of which is known as the Langevin equation. The deterministic f and stochastic g components of the stochastic equation are directly extracted from the measurement data with the assumption that the noise has finite moments and has a zero mean and a unit variance. No other information about the noise distribution is needed. This is contrary to the usual Langevin description, in which the additional assumption that the noise is Gaussian (δ-correlated) distributed as necessary. We test the method using one dimensional deterministic systems (the tent and logistic maps) with Gaussian and with Gumbel noise. In addition, results for human heart rate variability are presented as an example of the application of our method to real data. The differences between cardiological cases can be observed in the properties of the deterministic part f and of the reconstructed noise distribution.
Subject(s)
Algorithms , Data Interpretation, Statistical , Information Storage and Retrieval/methods , Models, Statistical , Stochastic Processes , Computer Simulation , Statistical DistributionsABSTRACT
Elderly people suicide or attempted suicide commands reflection. Some suicide-leading factors provide conspicuous risk markers. This retrospective analysis of 141 patients older than 65 yr, admitted in Lorient hospital emergency unit between 1986 and 1995, confirms the reality of risk factors, allowing to sketch a portrait of potential suicides so that preventive actions could be taken.
