Transformation and Estimation of the Two-Way Error Components Models with Double MA(1) Disturbances
摘要
This paper considers the problem of transforming and estimating a two-way error components model with double MA(1) disturbances. A first transformation is proposed, which yields a simple generalized least-squares estimator for this model. A second transformation is then used to derive an analytic expression for the best linear unbiased predictor for the i-th cross-sectional unit, h periods ahead. Some intensive Monte Carlo experiments are then used to examine the performance of the proposed approach.