Neural Computation, Vol 10, 731-747, Copyright © 1998 by The MIT Press
Nonlinear Time-Series Prediction with Missing and Noisy Data
Volker Tresp and Reimar Hofmann
We derive solutions for the problem of missing and noisy data in nonlinear
time-series prediction from a probabilistic point of view. We discuss
different approximations to the solutions -- in particular, approximations
that require either stochastic simulation or the substitution of a single
estimate for the missing data. We show experimentally that commonly used
heuristics can lead to suboptimal solutions. We show how error bars for the
predictions can be derived and how our results can be applied to
K-step prediction. We verify our solutions using two
chaotic time series and the sunspot data set. In particular, we show that
for K-step prediction, stochastic simulation is superior
to simply iterating the predictor.
