On the Derivation of Monetary Policy Shocks: Should We Throw the VAR out with the Bath Water?
提出一种替代标准VAR的计量方法，通过使用实际可观测数据和市场预期来识别货币政策冲击。结果发现新方法虽能降低创新方差，但冲击和脉冲响应与标准VAR相似，无法明确判断优劣。
This paper considers an alternative econometric approach to the standard VAR methodology for identifying and estimating the effects of monetary policy shocks. The alternative approach makes more reasonable assumptions about economic agents' information set by: 1) restructuring the VAR variables according to what data are actually observable in each point in time, and 2) augmenting the VAR model with available measures of market participants' expectations of various economic variables, thus increasing the assumed information set. Should we throw the VAR out with the bath water? Unfortunately, the results of this paper are somewhat inconclusive. The expectations measures prove to be quite valuable--the variances of all innovations are reduced by at least one-half compared to the standard VAR innovations. Nevertheless, the innovations, monetary policy shocks, and impulse responses for both methods are fairly similar. Indeed, they are similar enough that the standard VAR approach cannot be rejected out of hand, but dissimilar enough that the standard approach cannot be validated.