Using multiple imputation to simulate time series
Sebastian Cano, Jordi Camps Andreu · WSEAS international conference on Applied Computer and Applied Computational Science · 2010
Multiple Imputation is a Markov chain Monte Carlo technique developed to work out missing data problems. This paper proposes a different point of view to use this technique with time series. The authors' idea consists on an endogenous construction of the database to avoid noise in the simulations and reach the right convergence of the limit distribution of the chain. New computer code was designed to carry out all the simulations.