1 / 10

publication of quarterly national accounts within 70 days after the end of reference period

publication of quarterly national accounts within 70 days after the end of reference period. Improvements in releases of short term indicators. flash estimates in 45 days. State of the art in European statistics:. Key targets:. Need timelier information about National accounts.

Download Presentation

publication of quarterly national accounts within 70 days after the end of reference period

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. publication of quarterly national accounts within 70 days after the end of reference period Improvements in releases of short term indicators flash estimates in 45 days State of the art in European statistics: Key targets: Need timelier information about National accounts BRIDGE MODELS National account data High frequency data

  2. High frequency data Nationalaccounts variables BRIDGE MODELS One bridge equation for each NA variable (Semi-structural ARDL equations + indicators) The whole set of regressors (lagged endogenous and exogenous variables) should be known over the projection period (“Nowcast”) No need of BridgeModels for weather forecasts!!

  3. Area wide data High frequency real data National Data Larger information set Limited information set Aggregate or Disaggregate? Comparing Forecasting performance Area wide aggregate Bridge equation Disaggregate Bridge Models Benchmark models (aggregate and disaggregate).

  4. Univariate model Collective consumption Retail sales, cons. conf, UR Private consumption Bus. Surveys (exp. orders), constr. components Gross fixed capital formation Exports of goods and services Trade variables, real exch. Rates, IP, surveys Forecasts Imports of goods and services IP, business surveys GDP SUPPLY SIDE DEMAND SIDE GDP, surveys Changes in stocks ________________________________________________________________ (GDP+Imports) GDP= CON + COC + INV + EXP - IMP + VSP Benchmark and Bridge models

  5. How to forecast euro area GDP Aggregate supply-side equation 1)ForecastGDPFor France, Germany and Italy 2) Run a regression of Euro area GDP growth rate on countries GDP growth rates 3) Apply coefficients estimated in 2) to GDP forecasts in 1) to get a euro area GDP forecast Euro Area GDP

  6. Horse race Area wide aggregate Bridge equation Disaggregate Bridge Models Benchmark models (aggregate and disaggregate).

  7. RMSE OF THE EURO AREA GDP FORECASTS (1999.1-2001.2) Area-wide models Aggregation of national-models ARIMA 0.32 ARIMA 0.33 AR(5) model 0.35 AR(5) models 0.32 Structural equation 0.37 VAR 0.34 Aggregate supply-side equation 0.34 BM supply-side equations 0.12 BM demand-side equations 0.25 BM average of supply and demand 0.14 Forecasts comparison

  8. Forecasts comparison RMSE OF SINGLE-COUNTRY GDP FORECASTS (1999.1-2001.2) Germany France Italy ARIMA 0.60 0.30 0.31 AR(5) 0.60 0.28 0.35 0.60 VAR 0.34 0.36 BM supply-side 0.32 0.15 0.16 BM demand-side 0.36 0.45 0.67 BM average 0.20 0.28 0.31

  9. CONCLUSIONS • Bridge models always better than benchmark models • Forecasts with national data perform better than the aggregate bridge model

More Related