No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Understanding the quality of early estimates of Gross Domestic Product
Abstract
There has been considerable attention paid in recent months to Office for National Statistics early estimates of Gross Domestic Product (GDP). These estimates provide a timely indication of the evolution of the economic cycle, and there has been particular interest in their reliability, given the potential for theestimates to be revised.This article describes the context in which the offi cial estimates of GDP are produced, and examines the reason for revisions to early estimates. It goes on to discuss how these revisions can best be analysed over different maturities of the estimates and points out some potential pitfalls. Based on this discussion, itoffers guidance on the best approach to understanding the revisions cycle and for interpreting the published information on revisions.The article then presents the results of analysis of a new real time database for GDP growth in the UK, which contains a time series of estimates back to 1961. Over the period since the mid-1990s, revisions have been much smaller than previously, perhaps reflecting the relative stability of the economy over this time.The article concludes by discussing the issues surrounding the use of bias adjustments for GDP.
... Real-time data is a collection of different vintages of GDP which shows the actual data available to users at specific points in time. I use the real-time data set referenced in Brown, Buccellato, Chamberlin, Dey-Chowdhury and Youll (2009) which shows a snapshot of UK GDP taken from monthly ONS publications from 1961 to the current day. The dataset allows us to see how revisions have affected the measured path of the economy over time. ...
It is now widely accepted that early vintages of GDP data are likely to undergo a series of revisions as more information becomes available to National Statistics Institutions. This, however, creates a trade-off between timeliness and accuracy for data users such as monetary policy-makers. This article investigates the importance of data revisions for the operation of monetary policy in the UK. I find data revisions have been smaller in the last decade and early data vintages provide a relatively good signal of data released at a later date. There is though evidence of cyclicality and structural breaks in the data revision process which should caution data users against assuming data revisions are predictable. I also look at the role of the output gap in the practical implementation of monetary policy through the Taylor rule. While revisions to GDP data account for some of the mismeasurement of the output gap, I conclude that it is a relatively small culprit. The main cause of output gap revisions is due to the difficulty in estimating the level of potential output towards the end of the sample where statistical filter methods are generally unreliable.
The paper examines the asymmetries in size, value and momentum premiums over the economic cycles in the UK and their macroeconomic determinants. Using Markov switching approach we find clear evidence of cyclical variations of the three premiums, most noticeably variations in size premium. We associate Markov switching regime 1 with economic upturn and regime 2 with economic downturn. The macroeconomic indicators prompting such cyclicality the most are growth in industrial production, term structure, credit spread and money supply. Using forecast returns from our model and a trading strategy that alternates between size/style/momentum portfolios and risk-free rate, we show that exploiting cyclicality in premiums proves particularly profitable for portfolios featuring small cap stocks in recessions.
This paper reviews the performance of several statistical techniques in nowcasting preliminary estimates of UK GDP, particularly during the re-cent depression. Traditional bridging equations, MIDAS regressions and factor models are all considered. While there are various theoretical differences and perceived advantages for each technique, replicated real-time out-of-sample testing shows that, in practice, there is in fact little to choose between methods in terms of end-of-period nowcasting accuracy. The analysis also reveals that none of the aforementioned statistical models can consistently beat a consensus of professional economists in nowcasting preliminary GDP estimates. This inability of statistical models to beat the consensus may reect several factors, one of which is the revisions and re-appraisal of trends in-herent in UK GDP statistics. The suggestion is that such changes impact on observed relationships between GDP and indicator variables such as business surveys, which impairs nowcasting performance. Indeed, using a synthetic series based purely on observed preliminary GDP estimates, which introduces stability to the target variable series, the nowcasting ac-curacy of regressions including closely-watched PMI data is improved by 25-40 percentage points relative to a naive benchmark.
This paper presents a statistical analysis of revisions in quarterly gross domestic product (GDP) of the Group of Twenty countries (G-20) since 2000. The main objective is to assess whether the reliability of early estimates of quarterly GDP has been weakened from the turmoil of the 2008 financial crisis. The results indicate that larger and more downward revisions were observed during the years 2008 and 2009 than in previous years.
This article presents new estimates of publicly funded healthcare outputs, inputs and productivity for the period 1995 to 2008. These update the estimates published in Total Public Service Output and Productivity in June 2009 (ONS 2009a) by incorporating new methods to improve the measurement of output and input volumes and give the first results for 2008.
Real time data are snapshots of unrevised data available at different points in time. This article provides a literature review on how real time databases can be used to better understand the nature of revisions to economic data, and are also a fairer basis on which to evaluate forecasts and policy–decisions made in the past.
True values of key macroeconomic variables are unobservable and can only be estimated. A key question for the Monetary Policy Committee is how best to take account of the resultant uncertainty in its economic assessment. Official estimates of economic variables are produced by the Office for National Statistics (ONS), and some private sector organisations publish surveys of business activity that may also give clues as to the underlying state of the economy. This article presents a simple methodology for deriving 'best guesses' of the true values of economic variables by weighting together official estimates and information from business surveys.
Economic statistics are often only an approximation of the underlying reality they are attempting to measure. Official statistics, especially in timely first releases, can be subject to significant uncertainty and revision. In this speech, Marian Bell, a member of the Monetary Policy Committee, looks at the various ways in which data uncertainty might arise and discusses how policymakers should respond. A particular difficulty for statisticians can be the allocation of movements in nominal variables to changes in prices and volumes. Such uncertainty is high when the structure of the economy and relative prices change significantly. In such circumstances, looking at a money value measure of activity may be informative. Moreover, estimated levels of real activity appear more prone to revision than growth rates, so we should be wary of conventional, mechanical estimates of the output gap, which rely heavily on information on the level of activity. Ms Bell concludes that revisions to data stemming either from more information or methodological improvements will inevitably lead us to reassess our view of the underlying truth. Improvements to statistics are to be welcomed, and understanding the nature of data uncertainty and revisions should inform our judgements about the state of the world.
Most macroeconomic data are uncertain - they are estimates rather than perfect measures. One symptom of that uncertainty is the propensity of statistical agencies to revise their estimates in light of new information or methodological advances. While revisions should move estimates closer to the "truth," the potential for early estimates to be revised poses challenges for forecasting and economic analysis. Over the past few years, Bank staff have undertaken a range of research into how best to deal with the ensuing uncertainty. The results of that research have been used for some time as part of the toolkit available to staff when briefing the Monetary Policy Committee. This article describes some further developments in that research effort aimed at refining the staff's toolkit.
The Bank's Monetary Policy Committee analyses a wide variety of data to inform its monetary policy decisions. One of the main questions raised by new data is how much weight should be placed on initial estimates that are likely to get revised. Economic policy decisions must take account of possible revisions to the data that are used to inform the assessment of the current state of the economy. In attempting to improve our understanding of how data are revised, we have constructed a real-time database that contains successive sets of data for a number of different series. This article discusses the construction of the database for the major components of the expenditure side of gross domestic product (GDP) in the UK National Accounts.
Outlines the new system for recording and quantifying GDP(O) revisions, presents initial results and planned future developments.Revisions are an inevitable consequence of the need for timely estimates of economic growth and are a well-understood part of the statistical process used to compile these estimates. The Office for National Statistics (ONS) has recently done much work to improve understanding of the causes of revisions to the early estimates of gross domestic product (GDP) as measured by the output, or production, approach (GDP(O)). Linked to this work has been the development of a system for recording and quantifying GDP(O) revisions. This is a significant step forward and puts ONS at the forefront of this area of work. This article outlines the new system, presents some initial results and gives details of planned future developments. Economic & Labour Market Review (2007) 1, 36–42; doi:10.1057/palgrave.elmr.1410155
Stability and statistics', speech to the North Wales Business Club
- R Lomax
Lomax R (2004) 'Stability and statistics', speech to the North Wales Business Club,
Tuesday 23 November 2004
Revisions to quarterly GDP growth and its components', Economic and Labour Market Review
- J Murphy
Murphy J (2009) 'Revisions to quarterly GDP growth and its components', Economic
and Labour Market Review April 2009
Dealing with potential bias in early estimates of GDP, Economic and Labour Market Review
Youll (2008) Dealing with potential bias in early estimates of GDP, Economic and
Labour Market Review July 2008