A nonlinear analysis of the underlying dynamics of a biomedical time s
eries is proposed by means of a multi-dimensional testing of nonlinear
Markovian hypotheses in the observed time series. The observed dynami
cs of the original N-dimensional biomedical time series is tested agai
nst a hierarchy of null hypotheses corresponding to N-dimensional nonl
inear Markov processes of increasing order, whose conditional probabil
ity densities are estimated using neural networks. For each of the N t
ime series, a measure based on higher order cumulants quantifies the i
ndependence between the past of the N-dimensional time series, and its
value r steps ahead. This cumulant-based measure is used as a discrim
inating statistic for testing the null hypotheses. Experiments perform
ed on artificial and real world examples, including autoregressive mod
els, noisy chaos, and nonchaotic nonlinear processes, show the effecti
veness of the proposed approach in modeling multivariate systems, pred
icting multidimensional time series, and characterizing the structure
of biological systems. Electroencephalogram (EEG) time series and hear
t rate variability trends are tested as biomedical signal examples.