The European Statistics Awards for Nowcasting: A New Approach to Engage with the Scientific Community and to Foster Improved Timeliness of Official Statistics

Author:

Zając Agnieszka1,Karlberg Martin1ORCID,Museux Jean-Marc1

Affiliation:

1. Eurostat, European Commission, Luxembourg

Abstract

The European Statistics Awards Programme is a multiannual program for engaging with, and tapping into the potential of, the research and innovation community at large. This is achieved through competitions with pecuniary prizes for the best performers. One of the strands within that program offers awards for the accurate nowcasting of monthly time series of interest to policymakers. This paper presents the design of the nowcasting competition as well as the performance of the best entries of the first annual round. In terms of accuracy, the competition has generated promising results—which do however need further fine-tuning before being possible to deploy in statistical production. The competitions feature a particular prize for submissions having a potential for scaling up to regular statistical production—and in response to this, teams have submitted ample documentation (including code). The awards program should also generate experience that the official statistics community can learn from. This paper demonstrates how the multi-annual nature of the program has allowed various design changes to be implemented for the last nowcasting round. The main work now lies ahead: the paper outlines the plans for further developing the most promising competition contributions, potentially leading to new Eurostat experimental statistics products.

Publisher

SAGE Publications

Reference37 articles.

1. Ascheri A., Museux J.M., Wirthmann A., Giannakouris K., Karlberg M., Baldacci E. 2022. “Innovation in the European Statistical System: Recent Achievements and Challenges Ahead.”Statistical Journal of the IAOS 38 (3): 805–813. DOI: https://doi.org/10.3233/SJI-220053.

2. Bollerslev T. 1986. “Generalized Autoregressive Conditional Heteroskedasticity.”Journal of Econometrics 31 (3): 307–327. DOI: https://doi.org/10.1016/0304-4076(86)90063-1.

3. Chen J. C., Dunn A., Hood K., Driessen A., Batch A. 2022. “Off to the Races: A Comparison of Machine Learning and Alternative Data for Predicting Economic Indicators.” In Big Data for Twenty-First Century Economic Statistics, edited by K. G. Abraham, Jarmin R. S., Moyer B. C., Shapiro M. D., 373–402. Cambridge, MA: National Bureau of Economic Research. https://www.nber.org/books-and-chapters/big-data-twenty-first-century-economic-statistics/races-comparison-machine-learning-and-alternative-data-predicting-economic-indicators (accessed March 2024).

4. Cleveland R. B., Cleveland W. S., McRae J. E., Terpenning I. 1990. “STL: A Seasonal-Trend Decomposition Procedure Based on Loess.”Journal of Official Statistics 6 (1): 3–33. https://www.scb.se/contentassets/ca21efb41fee47d293bbee5bf7be7fb3/stl-a-seasonal-trend-decomposition-procedure-based-on-loess.pdf (accessed October 2023).

5. D’Elia E. 2014. “Predictions vs. Preliminary Sample Estimates: The Case of Eurozone Quarterly GDP.”Journal of Official Statistics 30 (3): 499–520. DOI: https://doi.org/10.2478/JOS-2014-0031.

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3