Transcript D4.2b
International Seminar on Timeliness, Methodology and Comparability of Rapid Estimates of Economic Trends Ottawa, 27-29 May 2009 Geert Bruinooge Deputy Director-General Statistics Netherlands SESSION 4; Extrapolation, modelling, econometric and sampling techniques used in the preparations of rapid estimates The professionalism of statisticians is judged by their capacity to combine a high degree of reliability with satisfactory rapidity free quote from: “Understanding NATIONAL ACCOUNTS”, OECD Quote: “I want to know today, what happened yesterday” Central banker, February 2009 Different approaches • Rapid indicators of monthly GDP • Economic models forecasting main economic variables • Surveys • Composite indicators • Separate indicators for parts of economy Monthly estimates of GDP • Use of well established statistical methods • New rapid estimates for white spots • International effort to provide common methodology and framework Economic models forecasting main economic variables • Forecasts may prove wrong – Exogenous data may contain errors – Model may be subject to error – Model may fail due to structural break in economic development • Forecasts may jeopardize public trust in NSI’s • NSI’s shouldn’t forecast but stop at now casts Surveys • Surveys are useful for information on the present and near future state of the economy • Representative surveys with low sampling variability are costly and lack timeliness • Many NSI’s have to use data registers and administrations (VAT, wage tax) Composite indicators • Composite indicators present already available data in consistent and coherent way • Composite indicators consist of coincident, leading and lagging indicators • Careful selection of variables Separate indicators • Separate indicators linked to specific characteristics of countries • Examples: – – – – – – – Freight (by container, by air, by road) Mobile call minutes Visitor arrivals New cars registration Floor area under construction Production of cement ATM cash withdrawals, electronic payments • Careful selection of indicators based on sharp criteria Concluding remarks • • • • • Different approaches Promising results Much work to be done “Proof of the pudding is in the eating” International comparability