Multivariate threshold autoregressive models in geodesy. (English) Zbl 1071.37519

Summary: Recently, the research in time series analysis has changed turning from linear to nonlinear modeling. Here, we are trying to show how a special case of such a large family of models (as threshold autoregressive ones are) may be applied within processing of continual GPS observations. Two components (north and east) of point position in a horizontal coordinate system are taken to obtain bivariate time series, which consequently are tested for nonlinearity and modelled using bivariate threshold autoregressive model. The whole procedure, of course, can easily be generalized to more than two-variate series.


37M10 Time series analysis of dynamical systems
86A30 Geodesy, mapping problems
62M10 Time series, auto-correlation, regression, etc. in statistics (GARCH)