 Nowcasting U.S. Business Cycle Turning Points with Vector QuantizationAndrea Giusto () and Jeremy Piger Working Papers from Dalhousie University, Department of Economics Abstract: We propose a non-parametric classification algorithm known as Learning Vector Quantization (LVQ) for the purpose of identifying new U.S. business cycle turning points in real time. LVQ is widely used for classification in many other contexts, including pro- duction quality monitoring and voice recognition. The algorithm is well suited for real-time classification of economic data to expansion and recession regimes due to its ability to eas- ily incorporate missing data and a large number of economic indicators, both of which are features of the real-time environment. It is also computationally simple to implement as com- pared to popular parametric alternatives. We present Monte Carlo evidence demonstrating the potential advantages of the LVQ algorithm over a misspecified parametric statistical model. We then evaluate the real-time ability of the algorithm to quickly and accurately establish new business cycle turning points in the United States over the past five NBER recessions. The algorithm’s performance is competitive with commonly used alternatives. Keywords: turning point; classification; reference cycle; expansion; recession (search for similar items in EconPapers) Published in International Journal of Forecasting, 2017, pages 174-184 Downloads: (external link) Related works: Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text Persistent link: https://EconPapers.repec.org/RePEc:dal:wpaper:daleconwp2013-02 Access Statistics for this paper More papers in Working Papers from Dalhousie University, Department of Economics Contact information at EDIRC. |
Is your work missing from RePEc? Here is how to contribute.
Questions or problems? Check the EconPapers FAQ or send mail to .
EconPapers is hosted by the
School of Business at Örebro University.