IDEAS home Printed from https://ideas.repec.org/p/ekd/004912/5663.html
   My bibliography  Save this paper

Modeling Euro Area Industrial New Orders

Author

Listed:
  • Gabe de Bondt
  • Heinz C. Dieden
  • Sona Muzikarova
  • Istvan Vincze

Abstract

Following the discontinuation of statistics on industrial new orders by Eurostat since the observation period March 2012, this paper presents the ECB indicator for euro area industrial new orders. This indicator aims to fill the emerged gap on euro area industrial new orders for various breakdowns: total, total excluding heavy transport equipment, main industrial groupings, and domestic and non-domestic, broken down into euro area and non-euro area. Specific-to-general regression modeling approach Out-of-sample dynamic forecasting Real-time forecasting Granger causality tests Impulse responses from bivariate VAR Following the discontinuation of statistics on industrial new orders by Eurostat since the observation period March 2012, this paper presents the ECB indicator for euro area industrial new orders. This indicator aims to fill the emerged gap on euro area industrial new orders for various breakdowns: total, total excluding heavy transport equipment, main industrial groupings, and domestic and non-domestic, broken down into euro area and non-euro area. Despite the discontinuation at European level, a large number of euro area countries (currently about 80%) will continue with the data collection at a national level, reflecting the importance of industrial new orders statistics for their national conjunctural analysis. The ECB, in close cooperation with National Central Banks and National Statistical Institutes, has established regular monthly data transmissions of national data on industrial new orders to the ECB. In order to derive estimates for missing national data, a common modeling framework has been applied to the individual EU countries. The ECB indicator for euro area industrial new orders are compiled from national data as a weighted average, applying the weighting scheme as previously used by Eurostat with base year 2005. National data are seasonally and working-day adjusted; in cases in which only non-adjusted national data are available, the adjustment has been done by the ECB. For those national statistical institutes that have decided to continue the collection of industrial new orders, these national data are taken into account. For those countries that have discontinued the data collection, national data as derived from the estimation framework are used for the aggregation of euro area results. Correspondingly, the euro area aggregate series consist of official hard data formerly collected by Eurostat (up to March 2012); and from April 2012 onwards, aggregates obtained from the combination of national data and the outcome of the estimation framework. The ECB indicator for new orders is calculated once the incoming national data coverage reaches the Eurostat-set threshold of 60%. Regarding countries for which national data are received after the euro area database is updated for a new monthly observation, their estimates will be replaced by the national data and the euro area results will be recalculated and revised accordingly. The importance of modeling new orders particularly lies in the empirically backed tendency that new orders have shown to historically anticipate business cycle turning points. There is a long-standing tradition of new orders leading industrial production. For example, new orders are among the leading series used for the widely monitored OECD’s Composite Leading Indicator (CLI). Furthermore, new orders in manufacturing (specifically, the nondefense capital goods excluding aircraft orders sub-category) have historically exhibited high correlation with the US business cycle. Consistently, manufacturing new orders in capital goods have served as inputs to The Conference Board’s (TCB) Leading Economic Index (LEI) for both the U.S. and the euro area. Notwithstanding the link between industrial new orders and industrial production as well as the empirical evidence that the former pre-empts business cycle turning points, little formal academic literature exists about explicitly modeling industrial new orders and thereby could constitute a relevant underpinning for our modeling exercise. Our study therefore pioneers modeling industrial new orders in manufacturing as far as scale (euro area aggregate as well as all EU countries), scope (not only totals and totals excluding heavy transport equipment new orders but also breakdowns across main industrial groupings and source of origin), and by deploying a broad mix of qualitative as well as quantitative data. The model determinants are selected not only from business surveys on new orders from the European Commission’s harmonised business survey in manufacturing as well as from Markit’s survey among Purchasing Managers (PMI), but also from official statistics on industrial turnover. Emphasis is thus put on ensuring that the information from a broad mixture of soft and hard data is exploited, which should help in enhancing the robustness of the model-based proxy for new orders. Given the lack of formal academic consideration, as well as the small number of observations available for industrial new orders for euro area countries (in some cases starting in 2003 and ending in 2012) a specific-to-general modeling approach is preferred. The model is thus constructed by diagnostically building up on its simplest versions. Several criteria to accept the final model version are applied. Apart from statistical criteria (not only t-statistics, but also the white noise property of the model residuals), restrictions accounting for plausible economic properties (e.g. it is implausible that industrial new orders can consistently growth faster than sales) are also considered. The estimation results show for all countries that the model determinants significantly help in explaining industrial new orders month-on-month growth rates. In particular, turnover data and surveys on new orders matter for monthly new order growth and to a much lesser extent the variables considered to improve the model dynamics. This is evidenced by expected relationships (signified by the coefficient signs), recurring statistical significance, and by coefficients’ economically sound magnitude. Importantly, the model yields healthy residuals for the euro area aggregate and at the country-level. At the euro area aggregate level, the model explains about 50% of the variation in total new orders month-on-month growth rate with a corresponding standard error of regression at around 1.6 percentage points. The explanatory power varies between around 30% (capital goods) and 70% (intermediate goods) for the other breakdowns of new orders considered at the euro area aggregated level. These are promising outcomes for the inherently noisy monthly growth rates in industrial new orders. For example, the correlation between the in-sample estimated euro area total new order index level and the actual new order index level is 99% and an out-of-sample exercise, based on the model estimated for the euro area up to the end of 2002, shows that the correlation remains high at 97%. Out-of-sample and real-time forecasting, an alternative estimation method, focusing on three-month on three-month growth rates, and alternative specifications, all show that the estimates are robust. A real-time forecasting exercise shows that the model-based real-time outcome for the new order index is closer to the final official release than the index derived from the first releases of the monthly growth rate. Moving from the inherently noisy month-on-month growth rates in new orders to the three-month on three-month growth rates confirms the explanatory power of the basic model determinants, as they explain slightly above 90% of the new orders growth rates at this lower frequency, but at the cost of an incorrect behaviour of the model residuals. Moreover, the basic model estimates improve in a statistical and/or economic way neither by system estimation (Seemingly Unrelated Regression), by simplifying the way both surveys on new orders are considered, nor by adding a foreign indicator at the euro area aggregate or country-level. Finally, we apply a formal analysis to check whether the ECB indicator for euro area industrial new orders leads euro area industrial production, given the fact that analysts closely monitor industrial new orders, mainly because of their leading properties for the business cycle. For example, new orders for capital goods served as one of the inputs of TCB’s LEI for the euro area and TCB aims to replace the discontinued series with the ECB indicator on euro area industrial new orders. Our results, which are robust across sub-groupings of new orders as well as two different empirical methods (i.e. Granger causality tests and impulse responses from a bivariate vector autoregressive model), indeed show that euro area new orders lead industrial production. This finding implies that analysts may benefit from closely monitoring the ECB indicator for euro area new orders. Besides the leading content of new orders for production, monitoring of new orders is also useful in cross-checking developments in industrial production in real time. This is particularly appealing during periods of heightened uncertainty about the reliability of industrial production data, as illustrated by two real-time examples (2008/09 recession and 2011/12 recession). Another contribution of new orders in the conjunctural analysis of the euro area economy is that it provides – unlike production data – information on the origins of demand, i.e. domestic or foreign.

Suggested Citation

  • Gabe de Bondt & Heinz C. Dieden & Sona Muzikarova & Istvan Vincze, 2013. "Modeling Euro Area Industrial New Orders," EcoMod2013 5663, EcoMod.
  • Handle: RePEc:ekd:004912:5663
    as

    Download full text from publisher

    File URL: http://ecomod.net/system/files/EcoMod2013%20Modelling%20industrial%20new%20orders%20de%20Bondt%20Dieden%20Muzikarova%20Vincze.pdf
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Nicholson, R J & Tebbutt, S G, 1979. "Modelling of New Orders for Private Industrial Building," Journal of Industrial Economics, Wiley Blackwell, vol. 28(2), pages 147-160, December.
    2. Helmut Herwartz, 2010. "A note on model selection in (time series) regression models - general-to-specific or specific-to-general?," Applied Economics Letters, Taylor & Francis Journals, vol. 17(12), pages 1157-1160.
    3. S. S. Alexander & H. O. Stekler, 1959. "Forecasting Industrial Production--Leading Series versus Autoregression," Journal of Political Economy, University of Chicago Press, vol. 67(4), pages 402-402.
    4. Stock, James H. & Watson, Mark W., 1999. "Business cycle fluctuations in us macroeconomic time series," Handbook of Macroeconomics, in: J. B. Taylor & M. Woodford (ed.), Handbook of Macroeconomics, edition 1, volume 1, chapter 1, pages 3-64, Elsevier.
    5. Richard Etter & Michael Graff, 2003. "Estimating and Forecasting Production and Orders in Manufacturing Industry from Business Survey Data: Evidence from Switzerland, 1990-2003," Swiss Journal of Economics and Statistics (SJES), Swiss Society of Economics and Statistics (SSES), vol. 139(IV), pages 507-533, December.
    6. Garcia-Ferrer, Antonio & Bujosa-Brun, Marcos, 2000. "Forecasting OECD industrial turning points using unobserved components models with business survey data," International Journal of Forecasting, Elsevier, vol. 16(2), pages 207-227.
    7. Tatiana Cesaroni, 2011. "The cyclical behavior of the Italian business survey data," Empirical Economics, Springer, vol. 41(3), pages 747-768, December.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. de Bondt, Gabe J. & Dieden, Heinz C. & Muzikarova, Sona & Vincze, Istvan, 2014. "Modelling industrial new orders," Economic Modelling, Elsevier, vol. 41(C), pages 46-54.
    2. de Bondt, Gabe & Dieden, Heinz Christian & Muzikarova, Sona & Vincze, Istvan, 2014. "Modelling industrial new orders for the euro area," Statistics Paper Series 6, European Central Bank.
    3. de Bondt, Gabe & Dieden, Heinz Christian & Muzikarova, Sona & Vincze, Istvan, 2013. "Introducing the ECB indicator on euro area industrial new orders," Occasional Paper Series 149, European Central Bank.
    4. de Bondt, Gabe & Dieden, Heinz Christian & Muzikarova, Sona & Vincze, Istvan, 2013. "Introducing the ECB indicator on euro area industrial new orders," Occasional Paper Series 149, European Central Bank.
    5. Sharon McCaw, 2007. "Stylised facts about New Zealand business cycles," Reserve Bank of New Zealand Discussion Paper Series DP2007/04, Reserve Bank of New Zealand.
    6. Popoyan, Lilit & Napoletano, Mauro & Roventini, Andrea, 2017. "Taming macroeconomic instability: Monetary and macro-prudential policy interactions in an agent-based model," Journal of Economic Behavior & Organization, Elsevier, vol. 134(C), pages 117-140.
    7. Lamperti, Francesco & Bosetti, Valentina & Roventini, Andrea & Tavoni, Massimo & Treibich, Tania, 2021. "Three green financial policies to address climate risks," Journal of Financial Stability, Elsevier, vol. 54(C).
    8. Marco Del Negro & Michele Lenza & Giorgio E. Primiceri & Andrea Tambalotti, 2020. "What's Up with the Phillips Curve?," Brookings Papers on Economic Activity, Economic Studies Program, The Brookings Institution, vol. 51(1 (Spring), pages 301-373.
    9. repec:hal:spmain:info:hdl:2441/5bnglqth5987gaq6dhju3psjn3 is not listed on IDEAS
    10. Francesco Lamperti & Giovanni Dosi & Mauro Napoletano & Andrea Roventini & Alessandro Sapio, 2018. "And then he wasn't a she : Climate change and green transitions in an agent-based integrated assessment model," Working Papers hal-03443464, HAL.
    11. Paulo Soares Esteves & Gabriela Lopes de Castro, 2004. "Quarterly Series for the Portuguese Economy: 1977-2003," Economic Bulletin and Financial Stability Report Articles and Banco de Portugal Economic Studies, Banco de Portugal, Economics and Research Department.
    12. Javier J. Pérez & Jesús Rodríguez López & Carlos Usabiaga, 2002. "Análisis Dinámico de la Relación entre Ciclo Económico y Ciclo del Desempleo en Andalucía en Comparación con el Resto de España," Economic Working Papers at Centro de Estudios Andaluces E2002/07, Centro de Estudios Andaluces.
    13. Frank Westerhoff & Martin Hohnisch, 2010. "Consumer sentiment and countercyclical fiscal policies," International Review of Applied Economics, Taylor & Francis Journals, vol. 24(5), pages 609-618.
    14. Raven E. Saks & Abigail Wozniak, 2011. "Labor Reallocation over the Business Cycle: New Evidence from Internal Migration," Journal of Labor Economics, University of Chicago Press, vol. 29(4), pages 697-739.
    15. Jean-Marc Robin & Costas Meghir & Christian Dustmann & Jerome Adda, 2013. "Career Progression, Economic Downturns, and Skills," 2013 Meeting Papers 993, Society for Economic Dynamics.
    16. repec:spo:wpmain:info:hdl:2441/3l2vounfl99nvqsr0k24sn3k5l is not listed on IDEAS
    17. Giorgio Fagiolo & Mauro Napoletano & Andrea Roventini, 2008. "Are output growth-rate distributions fat-tailed? some evidence from OECD countries," Journal of Applied Econometrics, John Wiley & Sons, Ltd., vol. 23(5), pages 639-669.
    18. Hall, Viv B & Thomson, Peter, 2022. "A boosted HP filter for business cycle analysis: evidence from New Zealand’s small open economy," Working Paper Series 9473, Victoria University of Wellington, School of Economics and Finance.
    19. Rahman, Pk. Md. Motiur & Yamagata, Tatsufumi, 2004. "Business Cycles and Seasonal Cycles in Bangladesh," IDE Discussion Papers 1, Institute of Developing Economies, Japan External Trade Organization(JETRO).
    20. Benhabib, Jess & Liu, Xuewen & Wang, Pengfei, 2016. "Endogenous information acquisition and countercyclical uncertainty," Journal of Economic Theory, Elsevier, vol. 165(C), pages 601-642.
    21. Kala Krishna & Cemile Yavas, 2004. "Lumpy consumer durables, market power, and endogenous business cycles," Canadian Journal of Economics, Canadian Economics Association, vol. 37(2), pages 375-391, May.
    22. Ang, Andrew & Piazzesi, Monika & Wei, Min, 2006. "What does the yield curve tell us about GDP growth?," Journal of Econometrics, Elsevier, vol. 131(1-2), pages 359-403.

    More about this item

    Keywords

    Euro Area and all EU countries ; Business cycles; Forecasting; nowcasting;
    All these keywords.

    NEP fields

    This paper has been announced in the following NEP Reports:

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:ekd:004912:5663. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Theresa Leary (email available below). General contact details of provider: https://edirc.repec.org/data/ecomoea.html .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.