Intuitive and Reliable Estimates of the Output Gap from a Beveridge-Nelson Filter

Abstract

BIS Working Papers are written by members of the Monetary and Economic Department of the Bank for International Settlements, and from time to time by other economists, and are published by the Bank. The papers are on subjects of topical interest and are technical in character. The views expressed in them are those of their authors and not necessarily the views of the BIS. This publication is available on the BIS website (www.bis.org).

Is Business Cycle Asymmetry Intrinsic in Industrialized Economies?

“…We note that it would be difficult to detect structural breaks in real time and allowing for breaks as done in our benchmark example was only feasible from an ex-post basis. To address this, we use dynamic demeaning as in Kamber et al (2018). In particular, we demean the data using a backward-looking rolling 40-quarter average growth rate.…”

“…For example, in an earlier version of this study, Morley (2014) estimated the output gap for a set of 13 economies in the Asia and Pacific, many with very short sample periods and extreme outliers. In terms of imposing tighter priors on characteristics such as the smoothness of trend, see the approaches outlined in Harvey et al (2007) for UC models and Kamber et al (2018) for AR models. However, given the strong evidence for a volatile stochastic trend in Morley et al (2017) and in Table A.4 in the supplemental online Appendix 1, we avoid imposing smoothness priors as it could potentially lead to spurious cycles.…”

Reconciling output gaps: Unobserved components model and Hodrick–Prescott filter

“…In contrast, the corresponding estimate from the correlated UC model of Morley et al (2003) is close to zero. To reconcile the differences, Kamber, Morley, and Wong (2016) investigate how one can generate large cyclical components using the Beveridge-Nelson decomposition, which typically gives small and noisy cycles. They find that by setting the noise-to-signal ratio to be large, instead of estimating it from the data, the cycles obtained are large and the timing of troughs matches the chronology dated by the National Bureau of Economic Research (NBER).…”

A Factor Model Analysis of the Australian Economy and the Effects of Inflation Targeting

“…In both cases, we use 1,000 replications, as recommended by Kilian. 26 We check the robustness of our results to consideration of a FAVARX model with an output gap measure based on Kamber et al (2018) instead of output growth. This model can be used to make inferences about the effects of monetary policy shocks under the assumption that the long-run effect on output is exactly zero.…”