Modeling Astronomical Time Series with Stochastic Differential Equations

摘要

A serious limit of many methodologies of data analysis used in astronomical applications is that they are based on statistical techniques developed for predictive and/or exploratory purposes. In many situations, this makes difficult to establish a meaningful link between experimental data and theoretical models. Only techniques of data analysis developed in a specific physical context can be expected to provide useful results. This is especially true for the analysis of the light curves where many techniques have been directly "imported" from Statistics often with unsatisfactory, if not insignificant, results. Here, we show that the methodologies of analysis developed in the context of the Stochastic Dynamics appear much more useful and, in particular, that modeling the experimental time series by means of the stochastic differential equations (SDE) represents a valuable tool of analysis.