Font Size: 

Markov switching autoregressive models (MSARMs) are proposed here in order to tackle the non-linearity, non-Normality, non-stationarity, and long memory of time series in hydrology. Bayesian inference, model choice, and stochastic variable selection are performed numerically by Markov chain Monte Carlo algorithms. Hence, it is possible to efficiently fit the data, reconstruct the sequence of hidden states, restore the missing values, classify the observations into a few regimes, and select the covariates.The efficiency of MSARMs is demonstrated by applications to isotope signatures, turbidity measurements, and river temperature. Our proposal is very general and flexible and can be applied to any kind of environmental time series