An interpolation algorithm for multivariate ARMA processes

Abstract

Soltani and Mohammadpour (2009) presented an algorithm for the best linear interpolator of unrecorded innovations in discrete time multivariate second order stationary processes. In this paper, we develop an interpolation procedure for multivariate ARMA processes, using the interpolation of the underlying innovations. In this case, the coefficients of the model and the past and future multivariate data are the inputs of the algorithm. We also obtain a closed form expression for the best linear interpolator of single value for MA(1) and AR(1) time series models.