Identifiability of the parameters is an important precondition for consistent estimation of models designed to describe empirical phenomena. Nevertheless, many estimation exercises proceed without a preliminary investigation into the identifiability of its models. As a consequence, the estimates...

For much of the last four decades, leading analysts have used large Keynesian macroeconomic models to prepare macroeconomic forecasts. More recently, VAR models have become a popular alternative. Despite their usefulness in preparing unconditional forecasts, VAR models are unsuitable for policy...