1 / 8

Background

Task Force on Seasonal Adjustment of Quarterly National Accounts Second meeting Item 7 Calendar adjustment: Issues note Martin Eiglsperger Frankfurt, 23-24 April 2007. 2. Background.

Télécharger la présentation

Background

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Task Force on Seasonal Adjustment of Quarterly National AccountsSecond meetingItem 7 Calendar adjustment: Issues noteMartin EiglspergerFrankfurt, 23-24 April 2007

  2. 2 Background • Mandate: “Review and specify further the practices for working-day adjustment and the treatment of irregular factors …” • Provision of only calendar adjusted series for GDP and Value Added • Main topic of the next Task Force meeting

  3. 3 Calendar effects (1) Definition and role • Some calendar effects impact year by year in the same period to a similar extent → by definition: part of the seasonal component • Non-seasonal calendar effects:typically due to the varying number of working or trading days, due to moving holidays (e.g. Easter) and due to leap years • Many country-specific issues, e.g. calendar constellations in other countries might have an impact, e.g., on tourism or on retail trade

  4. 4 Calendar effects (2) Calendar adjustment • CMFB recommendation: Regression analysis • Regressors: • number of working or trading days, possiblydistinguishing between certain days in the week • dummies identifying periods affected by moving holiday, leap years etc. • Modification of working-day regressors?→ e.g. deviation of the no. of working days from their long-term average or no. of Mondays + Tuesdays + … + Fridays – 5/2 (no. of Saturdays + Sundays) …

  5. 5 Calendar effects (3) Calendar adjustment (continued) • Calculation of the no. of working or trading days requires detailed knowledge about country-specific public holidays and compensation practices, if public holidays fall on weekend days (relevant, e.g., in BE, IE, ES and the UK) • Check reliability and meaningfulness of results: • Significance and sign of the coefficient estimates? • Seasonal pattern in calendar factors? • Coefficient estimates: robust, time-depend?

  6. 6 Irregular effects • One-off outliers, temporary effects and level shifts should remain visible in the seasonal adjusted series, since they are not part of the seasonal component • However, there are effects which already have appeared in the past, e.g. due to cold winters or certain bridge day constellations • Shall a series be adjusted for such effects? • Can such effects be estimated reliably?

  7. 7 Outline of future work • Discuss and agree on definitions • Stock-taking of calendar regressors used • Monthly vs. quarterly regression analysis • References for further elaboration of recommendations: existing recommendations and draft of Eurostat seasonal adjustment guidelines • Practical advise on calendar adjustment with X-12, TRAMO/SEATS and DEMETRA • Discuss implementation of the provision of purely calendar-adjusted QNA series

  8. 8 Proposed way forward • Set up small expert / drafting group • Prepare review and proposals for July Task Force meeting

More Related