Euro-indicators Working Group

Similar documents
Euro-indicators Working Group

Introduction to Forecasting

Business Cycle Dating Committee of the Centre for Economic Policy Research. 1. The CEPR Business Cycle Dating Committee

NOWCASTING REPORT. Updated: August 17, 2018

GAMINGRE 8/1/ of 7

NOWCASTING REPORT. Updated: September 23, 2016

NOWCASTING REPORT. Updated: October 21, 2016

NOWCASTING REPORT. Updated: July 20, 2018

NOWCASTING REPORT. Updated: February 22, 2019

NOWCASTING REPORT. Updated: September 7, 2018

NOWCASTING REPORT. Updated: January 4, 2019

NOWCASTING REPORT. Updated: September 14, 2018

A look into the factor model black box Publication lags and the role of hard and soft data in forecasting GDP

NOWCASTING REPORT. Updated: November 30, 2018

Time Series Analysis

NOWCASTING REPORT. Updated: May 5, 2017

Advances in econometric tools to complement official statistics in the field of Principal European Economic Indicators

Short-term forecasts of GDP from dynamic factor models

A system for a real-time monitoring of the euro area economy

Volume 38, Issue 2. Nowcasting the New Turkish GDP

TIGER: Tracking Indexes for the Global Economic Recovery By Eswar Prasad, Karim Foda, and Ethan Wu

Forecasting the Canadian Dollar Exchange Rate Wissam Saleh & Pablo Navarro

Technical note on seasonal adjustment for M0

TIGER: Tracking Indexes for the Global Economic Recovery By Eswar Prasad and Karim Foda

Nowcasting Norwegian GDP

NOWCASTING REPORT. Updated: May 20, 2016

ESRI Research Note Nowcasting and the Need for Timely Estimates of Movements in Irish Output

GDP forecast errors Satish Ranchhod

ANALYSIS AND DEVELOPMENT OF PROCEDURES TO UPDATE THE KANSAS INDEX OF LEADING ECONOMIC INDICATORS RUSLAN VOLODYMYROVYCH LUKATCH

NOWCASTING REPORT. Updated: April 15, 2016

Technical note on seasonal adjustment for Capital goods imports

NOWCASTING THE NEW TURKISH GDP

Approximating Fixed-Horizon Forecasts Using Fixed-Event Forecasts

Inflation Report April June 2012

The Central Bank of Iceland forecasting record

THE APPLICATION OF GREY SYSTEM THEORY TO EXCHANGE RATE PREDICTION IN THE POST-CRISIS ERA

EUROINDICATORS WORKING GROUP THE IMPACT OF THE SEASONAL ADJUSTMENT PROCESS OF BUSINESS TENDENCY SURVEYS ON TURNING POINTS DATING

Time series and Forecasting

Warwick Business School Forecasting System. Summary. Ana Galvao, Anthony Garratt and James Mitchell November, 2014

GROSS DOMESTIC PRODUCT FOR NIGERIA

FaMIDAS: A Mixed Frequency Factor Model with MIDAS structure

Short-Term Job Growth Impacts of Hurricane Harvey on the Gulf Coast and Texas

Lecture Prepared By: Mohammad Kamrul Arefin Lecturer, School of Business, North South University

Handbook on Rapid Estimates

Dates and Prices ICAEW - Manchester In Centre Programme Prices

Approximating fixed-horizon forecasts using fixed-event forecasts

Sluggish Economy Puts Pinch on Manufacturing Technology Orders

Forecasting using R. Rob J Hyndman. 1.3 Seasonality and trends. Forecasting using R 1

Lucrezia Reichlin London Business School & Now-Casting Economics Ltd and Silvia Miranda Agrippino, Now-Casting Economics Ltd

Financial Factors in Economic Fluctuations. Lawrence Christiano Roberto Motto Massimo Rostagno

International Seminar on Early Warning and Business Cycle Indicators. 14 to 16 December 2009 Scheveningen, The Netherlands

CIMA Professional 2018

PANEL DISCUSSION: THE ROLE OF POTENTIAL OUTPUT IN POLICYMAKING

CIMA Professional 2018

Lecture Prepared By: Mohammad Kamrul Arefin Lecturer, School of Business, North South University

Multivariate Regression Model Results

Time Series and Forecasting

Time Series and Forecasting

NSP Electric - Minnesota Annual Report Peak Demand and Annual Electric Consumption Forecast

Time Series Analysis of Currency in Circulation in Nigeria

The Case of Japan. ESRI CEPREMAP Joint Workshop November 13, Bank of Japan

Table 01A. End of Period End of Period End of Period Period Average Period Average Period Average

Design of a Weather-Normalization Forecasting Model

The TransPacific agreement A good thing for VietNam?

Long-term Water Quality Monitoring in Estero Bay

To understand the behavior of NR prices across key markets, during , with focus on:

CITY OF MESQUITE Quarterly Investment Report Overview Quarter Ending September 30, 2018

CIMA Professional

Nowcasting at the Italian Fiscal Council Libero Monteforte Parliamentary Budget Office (PBO)

CIMA Professional

Animal Spirits, Fundamental Factors and Business Cycle Fluctuations

Abstract. Keywords: Factor Models, Forecasting, Large Cross-Sections, Missing data, EM algorithm.

CITY OF MESQUITE Quarterly Investment Report Overview Quarter Ending June 30, 2018

Suan Sunandha Rajabhat University

A FUZZY TIME SERIES-MARKOV CHAIN MODEL WITH AN APPLICATION TO FORECAST THE EXCHANGE RATE BETWEEN THE TAIWAN AND US DOLLAR.

D Agostino, Antonello; McQuinn, Kieran and O Brien, Derry European Central Bank, Central Bank of Ireland, Central Bank of Ireland

E C O N O M I C R E V I E W

Public Library Use and Economic Hard Times: Analysis of Recent Data

Asitha Kodippili. Deepthika Senaratne. Department of Mathematics and Computer Science,Fayetteville State University, USA.

Forecasting. Copyright 2015 Pearson Education, Inc.

Operations Management

ACCA Interactive Timetable & Fees

ACCA Interactive Timetable & Fees

Average 175, , , , , , ,046 YTD Total 1,098,649 1,509,593 1,868,795 1,418, ,169 1,977,225 2,065,321

Average 175, , , , , , ,940 YTD Total 944,460 1,284,944 1,635,177 1,183, ,954 1,744,134 1,565,640

EXAMINATIONS OF THE ROYAL STATISTICAL SOCIETY

STATISTICAL FORECASTING and SEASONALITY (M. E. Ippolito; )

Factor Mimicking Portfolios

ACCA Interactive Timetable & Fees

Nowcasting gross domestic product in Japan using professional forecasters information

Fresh perspectives on unobservable variables: Data decomposition of the Kalman smoother

REPORT ON LABOUR FORECASTING FOR CONSTRUCTION

ACCA Interactive Timetable & Fees

Nowcasting. Domenico Giannone Université Libre de Bruxelles and CEPR

ACCA Interactive Timetable & Fees

Investment in Austria: a view from the WIFO Investitionstest

ACCA Interactive Timetable & Fees

Program. The. provide the. coefficientss. (b) References. y Watson. probability (1991), "A. Stock. Arouba, Diebold conditions" based on monthly

Lecture 2. Business Cycle Measurement. Randall Romero Aguilar, PhD II Semestre 2017 Last updated: August 18, 2017

Record date Payment date PID element Non-PID element. 08 Sep Oct p p. 01 Dec Jan p 9.85p

Transcription:

Euro-indicators Working Group Luxembourg, 9 th & 10 th June 2011

Item 9.4 of the Agenda New developments in EuroMIND estimates Rosa Ruggeri Cannata Doc 309/11

What is EuroMIND? EuroMIND is a Monthly INDicator of economic conditions. It provides an estimate of GDP based on the temporal disaggregation of the quarterly National Accounts estimates, within a set of linked medium-size dynamic factor models for a set of coincident indicators It delivers a timely assessment of the state of the euro area economy It combines methodological pertinence and practical relevance

EuroMIND is by construction consistent with the official National Accounts estimates compiled by Eurostat It has desirable properties both for the historical disaggregation of GDP and its main components, and for nowcasting the level of economic activity by sector and expenditure components There are two main versions of EuroMIND for the euro area, differing for the inclusion or not of survey variables (Frale et al. 2008, 2009) (EuroMIND and EuroMIND-S) Now we also have a backdated version EuroMIND-B and a decomposition of EuroMIND into potential output and output gap, EuroMIND-G

Methodology (1) We carry out the disaggregation of the chain-linked quarterly value added from the output side (Agriculture, Industry, Construction, Trade, Financial services, Other services) and from the expenditure side (Final consumption, Gross capital formation, Exports, Imports) We adopt a dynamic factor model at the monthly level, taking the temporal aggregation constraint into account. The multivariate models are cast in the state space form and computational efficiency is achieved by implementing univariate filtering and smoothing procedures

Methodology (2) The chained-linked total GDP results via a multistep procedure that exploits the additivity of the volume measures expressed at the prices of the previous year The final estimate is obtained by combining the two estimates (output side and expenditure side) with weights reflecting their relative precision

EuroMIND and the business cycle The availability of a monthly indicator disaggregated into branches of activity such as EuroMIND is particularly relevant to monitor the business cycle in real time EuroMIND allows to follow in real time the evolution of the different elements of the euro area economy: sectors and demand components

Information set Quarterly Value Added are available from the beginning of 1995 in SA and WDA terms and refer to the euro Area Since December 2006 we have estimated EuroMIND once at month, right after the publication of the Industrial Production index (around the 15th). A mixed frequency model is used to disaggregate the quarterly NA values in sample and to compute the monthly values out of sample up to time t-2 The information set includes National Account data, monthly "hard" indicators (industrial production, employment, hours worked etc.) and, for EuroMIND-S, Business and Consumer surveys data

EuroMIND: the information set by sector Output side: For Industry (CDE) and Construction (F), a core indicator is represented by the index of industrial production. For the remaining branches (services), the monthly variables tend to be less directly related to the economic content of value added Expenditure size: for Final consumption expenditures some indicators of demand are available together with the production of consumer goods. For Gross capital formation a core indicator is the production index (both for industry and constructions), plus some specific variables for constructions. As far as the External Balance is concerned, the monthly volume index of Imports and Exports is provided by Eurostat, although some delay

Extension of the information set: business survey data Unfortunately financial indicators, such as spread, interest and exchange rates..., never resulted statistically significant. In order to catch sentiments and expectations of economic agents we complete this set of variables with the business survey data on Consumers, Business, Building and Services Survey data represent a very timely piece of economic information which originates from the quantification of qualitative survey questions, asking firms and consumers opinions on the state of the economy.

Use of business survey data In the U.S. survey data are not listed among the set of series that enter the Conference Board and the Stock and Watson (1989) indices of coincident indicators and they are not monitored by the NBER experts when dating the US business cycle Survey series are featured in the Eurocoin indicator for the euro area produced by the CEPR and in Euro- Sting, the short term indicator of the Euro area growth produced recently by the Spanish central bank

EuroMIND-S Business Survey data gave useful results to improve the model in terms of nowcast and short term forecast ability (FMMP(2010)-Survey Data as Coincident or Leading Indicator, JoF 29) The original model has been extended with more than one common factor and a smoother common component (IZAR) which allows for low-frequency cycles and fits survey data features

EuroMind-S: last 12 releases Billions of euro, chain linked volumes, reference year 2000 635 630 625 620 615 Apr-10 May-10 Jun-10 Jul-10 Aug-10 Sep-10 610 Oct-10 Nov-10 Dec-10 Jan-11 Feb-11 Mar-11 605 Jan-09 Feb-09 Mar-09 Apr-09 May-09 Jun-09 Jul-09 Aug-09 Sep-09 Oct-09 Nov-09 Dec-09 Jan-10 Feb-10 Mar-10 Apr-10 May-10 Jun-10 Jul-10 Aug-10 Sep-10 Oct-10 Nov-10 Dec-10 Jan-11 Feb-11

EuroMIND-S perfomance An application to the valued added for Industry, comparing the extended model versus the original EuroMIND formulation in terms of forecast ability has been developed. The issue of data revisions and news content in each block of series, survey and hard data, was also analyzed Evidence for a better performance of a model including both hard and survey data was found. Information from surveys was related to the lack of hard data (in line with the literature, e.g. Giannone et al. (2009) for the US)

Growth rates: comparison among indicators ------------------------------------------------- 2010 --------------------------------------------------------- ----- 2011 ----- Jan Feb Mar Apr May Jun Jul Aug Sept Oct Nov Dec Jan Feb ------------------------------------------ variations over previous period ------------------------------------------------ Quarterly GDP - - 0.40 - - 1.00 - - 0.35 - - 0.28 - - EuroMind 0.10 0.09 0.42 0.34 0.42 0.20 0.04 0.04-0.03 0.18 0.12 0.07 0.27 - EuroMind-S 0.07 0.15 0.39 0.34 0.40 0.22 0.02 0.05 0.00 0.15 0.15 0.04 0.31 0.22 ---------------------------------- variations over same period of previous year ---------------------------------------- Quarterly GDP - - 0.83 - - 2.00 - - 1.96 - - 2.05 - - EuroMind -0.03 0.75 1.64 1.73 2.03 2.07 1.95 1.86 1.84 1.98 2.02 2.01 2.18 - EuroMind-S -0.05 0.79 1.62 1.71 2.01 2.10 1.94 1.87 1.85 1.98 2.03 2.00 2.24 2.31

Other extensions of EuroMIND EuroMIND-B(ackcast): tracking the business cycle in the euro area since the early 70s EuroMIND-G(ap): real time estimates of the output gap based on EuroMIND

EuroMIND-B(ackcast) QNA: available from the first quarter of 1995 (introduction of ESA95). Accordingly, EuroMIND estimated since 1996 Recently, Eurostat has produced a database of the main European economic indicators, backdated up to 1971 based on backcasting techniques. This in turn enabled the backcalculation of EuroMIND from 1995 backward The production of a long indicator, measured at the monthly frequency, and based on a rigorous statistical methodology, is clearly a great improvement in the direction of creating a relevant statistical information base for an economic policy at the European level

EuroMIND-B and turning points detection EuroMIND-B may play an important role also for the analysis of the business cycle in the Euro area. Estimates of the turning points and of the recession probabilities of the classical cycle for the Euro area Results show three major recessionary patterns: in the 70, in the 90 plus the last recession They confirm the inception of the last recession in Feb. 2008, characterized by the largest steepness and duration

EuroMIND-G(ap) During the recent economic and financial crises, the discussion about potential output and long run growth dynamics has regained new interest among policy makers and Institutions the usual decomposition of a time series such as GDP into the trend and the cycle component has assumed an important economic interpretation EuroMInd-G provides the decomposition of EuroMInd into potential output and the output gap

EuroMIND-G: methodology (1) EuroMInd-G is based on model based decomposition of both the common cyclical trend and the GDP idiosyncratic component into a low-pass and a high-pass component The decomposition is thus embedded into the dynamic factor model and enables the extraction of the unobserved potential and gap series using standard optimal signal extraction principles The components can be estimated and their reliability assessed by applying the Kalman filter and smoother to a modified state space model

EuroMIND-G: methodology (2) The model depends on an integer m (chosen a priori) defining the order of the decomposition of the white noise disturbances driving the common and the idiosyncratic trends And on a non negative scalar λ (chosen a priori) which represents the smoothness parameter and, together with m, defines uniquely the decomposition The variances low-pass and high-pass disturbances are proportional, and depend on λ; as λ increases, the smoothness of the low pass component also increases, since a larger portion of high frequency variation is removed

EuroMIND-G: methodology (3) For given values of λ and m, the decomposition defines a new potential output disturbance that uses only the low frequencies whereas the remainder will contribute to the high pass component The spectral density of the disturbances of the low pass component has two poles at the frequency π; on the contrary, the spectral density of the high pass component has two poles at the zero frequency The role of the smoothness parameter can be related to the notion of a cut off frequency

Application The cut off period has be set to correspond to eight years (96 monthly observations) The related value of the smoothness parameter is λ = 870693, corresponding to a low-pass component retaining all the potential output fluctuations with a periodicity greater than 8 years In finite samples the estimator of the low pass and high pass components is computed by the Kalman filter and smoother applied to the state space model with measurement equation modified so as to incorporate the band-pass decomposition of GDP. The state-space form is modified so as to account for temporal aggregation of the GDP series

Results The main advantage of performing a model based decomposition is that the no special treatment of the end values is necessary, since the optimal estimates of the components are automatically provided by the Kalman filter and smoother associated to the model featuring the band-pass components Results are very encouraging: the estimated cycle capture quite well the swings in the economy as results of consecutive phases of recessions and expansion It is visible how the European economy has entered period of severe slowdown in the economy around 1974, 1980, 1992 and finally in 2008

660 640 620 600 580 560 540 520 500 480 EuroMind the Gap Billions of euro, chain-linked volumes, reference year 2000 20 15 10 5 0-5 -10 EuroMind Cycle -15 Trend -20 EuroMind the Gap Jan-95 Jan-96 Jan-97 Jan-98 Jan-99 Jan-00 Jan-01 Jan-02 Jan-03 Jan-04 Jan-05 Jan-06 Jan-07 Jan-08 Jan-09 Jan-10 Jan-95 Jan-96 Jan-97 Jan-98 Jan-99 Jan-00 Jan-01 Jan-02 Jan-03 Jan-04 Jan-05 Jan-06 Jan-07 Jan-08 Jan-09 Jan-10

Thank you for your attention