Methods used to analyze one type of nonstationary stochastic processes?the
periodically correlated process?are considered. Two methods of one-step-forward
prediction of periodically correlated time series are examined. One-step-forward
predictions made in accordance with an autoregression model and a
model of an artificial neural network with one latent neuron layer
and with an adaptation mechanism of network parameters in a moving
time window were compared in terms of efficiency. The comparison
showed that, in the case of prediction for one time step for time
series of mean monthly water discharge, the simpler autoregression
model is more efficient.