We propose an estimation strategy that accounts for two major problems raised in the empirical literature testing for … problems. Second, we apply nonlinear-nonstationary parametric and non-parametric estimation techniques to estimate the pairwise …

This paper considers forecast averaging when the same model is used but estimation is carried out over different … estimation windows. It develops theoretical results for random walks when their drift and/or volatility are subject to one or … more structural breaks. It is shown that compared to using forecasts based on a single estimation window, averaging over …

maximum likelihood estimation of the parameters in the model, we use an expectation maximization algorithm based on the state …