Dating Business Cycles: A Methodological Contribution with an Application to the Euro Area

Abstract

This paper proposes a dating algorithm based on an appropriately defined Markov chain that enforces alternation of peaks and troughs, and duration constraints concerning the phases and the full cycle. The algorithm, which implements Harding and Pagan's non-parametric dating methodology, allows an assessment of the uncertainty of the estimated turning points caused by filtering and can be used to construct indices of business cycle diffusion, aiming at assessing how widespread are cyclical movements throughout the economy. Its adaptation to the notion of a deviation cycle and the imposition of depth constraints are also discussed. We illustrate the algorithm with reference to the issue of dating the euro-area business cycle and analysing its characteristics, both from the classical and the growth cycle perspectives.

Short-Term Forecasting for Empirical Economists. A Survey of the Recently Proposed Algorithms

“…6 Standard bridge equation models can be extended in two ways. First, the process used to transform left-hand and right-hand variables into the same frequency usually discards a lot of potentially useful information and makes the detection of the actual relation between the variables di¢ cult.…”

The Decline in German Output Volatility: A Bayesian Analysis

“…The resulting tension index is plotted in the top panel of Figure 2 together with the business cycle peaks and troughs as identified by Artis et al (2004) using a business cycle dating procedure based on absolute declines and rises of Hodrick-Prescott filtered GDP. Observe that the h t series tends to pass between phases of general expansions and general contractions in which g t tends to outstrip and fall short of g * t , respectively.…”

Structural Time Series Models for Business Cycle Analysis

“…Usually two phases, recessions and expansions, are considered, that are delimited by peaks and troughs in economic activity. Dating is carried out by an algorithm, such as that due to Bry and Boschan (1971), or that proposed by Artis et al (2004), which aims at estimating the location of turning points, enforcing the alternation of peaks and troughs and minimum duration ties for the phases and the full cycle. Downturns and upturns have to be persistent to qualify as cycle phases; thus, they need to fulfill minimum duration constraints, such as at least two quarters for each phase; moreover, to separate it from seasonality, a complete sequence, recession-expansion or expansion-recession, i.e.…”

“…Figure 5 plots the recession frequencies, i.e., the relative number of times each quarter was classified as a recessionary period. For this purpose 5000 draws from the conditional distribution of µ|y were extracted; each quarter was classified as recession or expansion according to the Artis et al (2004) Markov chain dating algorithm. There is a close agreement with the NBER chronology, which is not based on GDP alone, and the last recession, which started in March 2001 and ended in October 2001, was really mild in terms of GDP; in fact, the recession frequency is only in one quarter greater than 0.5.…”