Research Papers

Specification Tests Robust to Multiple Instabilities

Job Market Paper

I develop in-sample and out-of-sample specification tests which are robust to multiple discrete shifts in the model coefficients. The tests apply to a wide class of models and only require the computation of a restricted Generalized Method of Moments (GMM) estimator. Simulations show that the proposed tests have good finite sample properties and are more powerful than tests assuming constant coefficients or a single break when the data-generating process exhibits multiple coefficient shifts. Using the proposed methodology, I document the presence of short-horizon predictability in the US equity premium during the 1946-2019 period using a set of financial variables studied in Goyal and Welch (2007). I find that one-month-ahead excess market returns are predictable from a larger set of predictors than typically found in the literature, once multiple shifts in predictability are taken into account. In contrast to previous studies, the test results are robust to minor changes in the sample considered. The path of the test statistics uncover evidence of heterogeneity in the location of predictability episodes across predictors. The findings explain why traditional tests often fail to uncover predictability in the full sample and why studies that split the sample at different dates often arrive at conflicting results regarding the predictive ability of a wide class of predictors.

Link coming soon

Has the Information Channel of Monetary Policy Disappeared? Revisiting the Empirical Evidence

with Barbara Rossi and Tatevik Sekhposyan

Does the Federal Reserve have an "information advantage'' in forecasting macroeconomic variables beyond what is known to private sector forecasters? And are market participants reacting only to monetary policy shocks or also to future information on the state of the economy that the Federal Reserve communicates in its announcements via an "information channel''? This paper investigates the evolution of the information channel over time. Although the information channel appears to be important historically, we find no empirical evidence of its presence in the recent years once instabilities are accounted for.

The paper has been briefly discussed in a VoxEU CEPR Policy Portal Column and the Brookings Hutchins Roundup. A working paper version of this article has been published as Federal Reserve Bank of San Francisco Working Paper (WP2020-08) and CEPR Discussion Paper 14456.

Read FRBSF Working Paper

Research Papers in Progress