A mixed-frequency smooth measure for business conditions
- PDF / 1,775,735 Bytes
- 26 Pages / 439.37 x 666.142 pts Page_size
- 11 Downloads / 186 Views
A mixed-frequency smooth measure for business conditions Yi-Ting Chen1 Received: 6 January 2020 / Accepted: 3 September 2020 © Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract We propose measuring business conditions via estimating a smooth function of time that serves as a common factor for explaining the comovement of economic indicators across the occurred business cycles. This smooth measure is useful for reducing the noises in assessing the state of business conditions, and can be easily established using mixed-frequency indicators and updated in real time. We also conduct an empirical study to show its usefulness in real data. Keywords Business conditions · Coincident indices · Mixed frequency · Smooth measure JEL Classification C32 · C51 · E32
1 Introduction Measuring an economy’s business conditions is essential for academic, policy-making and other reasons. Conventionally, practitioners often measure business conditions using a coincident index which is a simple weighted average of monthly economic indicators. The Conference Board coincident index is a representative measure for the U.S. economy generated from four monthly indicators (the industrial production, the real personal disposable income, the real manufacturing and trade sales and the number of employees on non-farm payrolls) and regularly released at the monthly frequency. In econometrics, the state of business conditions is widely considered as a common factor that explains the comovement of various economic indicators across
Electronic supplementary material The online version of this article (https://doi.org/10.1007/s00181020-01937-w) contains supplementary material, which is available to authorized users.
B 1
Yi-Ting Chen [email protected] Department of Finance, Center for Research in Econometric Theory and Applications, National Taiwan University, No. 1, Sec. 4, Roosevelt Rd., Taipei 10617, Taiwan
123
Y.-T. Chen
non-periodically recurrent business cycles. By this notion, researchers also proposed formal methods for establishing coincident indices. In particular, Stock and Watson (1989, 1991) established a coincident index by estimating the common factor of a state-space model based on the aforementioned four monthly indicators. Stock and Watson (1999a, 2002) proposed a diffusion index which is a principal-component estimator for the leading factor of a large set of monthly indicators; see also Bai and Ng (2008) for a related review. Researchers are also interested in measuring business conditions using mixedfrequency indicators. Like Stock and Watson (1989, 1991), Aruoba, Diebold and Scotti (2009, ADS) conducted a state-space model to estimate the common factor based on a small set of indicators. However, ADS allowed the indicators to be observed at mixed frequencies; see also Mariano and Murasawa (2003, 2010) for related studies. The use of mixed-frequency indicators reasonably reflects the fact that the state of business conditions influences not only monthly indicators but also other highfrequency (like weekly
Data Loading...
