PREDICTION OF MISSING OBSERVATIONS BY A CONTROL METHOD

Vyacheslav M. Abramov (Australia) and Fima C. Klebaner (Australia)

Received April 30, 2007

Abstract

Consider a time series with missing observations but a known final point. Using control theory ideas we estimate/predict these missing observations. We obtain recurrence equations which minimize sum of squares of a control sequence. An advantage of this method is in easily computable formulae and flexibility of its application to different structures of missing data.

Keywords and phrases: missing observations, autoregressive models, control method, prediction.