Alternative modeling strategies for specifying subset VAR models are considered. It is shown that under certain conditions a testing procedure based on t-ratios is equivalent to sequentially eliminating lags that lead to the largest improvement in a prespecified model selection criterion. A...

In this paper we analyze the sources of German unemployment within a structural vector error correction model (SVECM) framework. For this purpose, we propose a method to estimate an exactly identified Subset SVECM, which is a SVECM with short run parameter restrictions. A cointegration analysis...