REAL‐TIME FORECASTING OF INFLATION AND OUTPUT GROWTH WITH AUTOREGRESSIVE MODELS IN THE PRESENCE OF DATA REVISIONS

We examine how the accuracy of real‐time forecasts from models that include autoregressive terms can be improved by estimating the models on ‘lightly revised’ data instead of using data from the latest‐available vintage. The benefits of estimating autoregressive models on lightly revised data are related to the nature of the data revision process and the underlying process for the true values. Empirically, we find improvements in root mean square forecasting error of 2–4% when forecasting output growth and inflation with univariate models, and of 8% with multivariate models. We show that multiple‐vintage models, which explicitly model data revisions, require large estimation samples to deliver competitive forecasts. Copyright © 2012 John Wiley & Sons, Ltd.     

Density forecasting with Bayesian Vector Autoregressive models under macroeconomic data uncertainty

Macroeconomic data are subject to data revisions. Yet, the usual way of generating real-time density forecasts from Bayesian Vector Autoregressive (BVAR) models makes no allowance for data uncertainty from future data revisions. We develop methods of allowing for data uncertainty when forecasting with BVAR models with stochastic volatility. First, the BVAR forecasting model is estimated on real-time vintages. Second, the BVAR model is jointly estimated with a model of data revisions such that forecasts are conditioned on estimates of the ‘true’ values. We find that this second method generally improves upon conventional practice for density forecasting, especially for the United States.     

Real-time squared: A real-time data set for real-time GDP forecasting

This paper uses real-time data to mimic real-time GDP forecasting activity. Through automatic searches for the best indicators for predicting GDP one and four steps ahead, we compare the out-of-sample forecasting performance of adaptive models using different data vintages, and produce three main findings. First, despite data revisions, the forecasting performance of models with indicators is better, but this advantage tends to vanish over longer forecasting horizons. Second, the practice of using fully updated datasets at the time the forecast is made (i.e., taking the best available measures of today's economic situation) does not appear to bring any effective improvement in forecasting ability: the first GDP release is predicted equally well by models using real-time data as by models using the latest available data. Third, although the first release is a rational forecast of GDP data after all statistical revisions have taken place, the forecast based on the latest available GDP data (i.e. the “temporarily best” measures) may be improved by combining preliminary official releases with one-step-ahead forecasts.     

REAL‐TIME DATA AND FISCAL POLICY ANALYSIS: A SURVEY OF THE LITERATURE

This paper surveys the empirical research on fiscal policy analysis based on real‐time data. This literature can be broadly divided into four groups that focus on: (1) the statistical properties of revisions in fiscal data; (2) the political and institutional determinants of projection errors by governments; (3) the reaction of fiscal policies to the business cycle and (4) the use of real‐time fiscal data in structural vector autoregression (VAR) models. It emerges that, first, fiscal revisions are large and initial releases are biased estimates of final values. Secondly, strong fiscal rules and institutions lead to more accurate releases of fiscal data and smaller deviations of fiscal outcomes from government plans. Thirdly, the cyclical stance of fiscal policies is estimated to be more ‘counter‐cyclical’ when real‐time data are used instead of ex post data. Fourthly, real‐time data can be useful for the identification of fiscal shocks. Finally, it is shown that existing real‐time fiscal data sets cover only a limited number of countries and variables. For example, real‐time data for developing countries are generally unavailable. In addition, real‐time data on European countries are often missing, especially with respect to government revenues and expenditures. Therefore, more work is needed in this field.     

Forecasting data vintages

This article provides a discussion of Clements and Galvão’s paper “Forecasting with vector autoregressive models of data vintages: US output growth and inflation.” Clements and Galvão argue that a multiple-vintage VAR model can be useful for forecasting data that are subject to revisions. They draw a “distinction between forecasting future observations and revisions to past data,” which focuses forecasters’ attention on yet another real time data issue. This comment discusses the importance of taking data revisions into consideration, and compares the multiple-vintage VAR approach of Clements and Galvão to a state space approach.     

Modeling data revisions: Measurement error and dynamics of “true” values

Policy makers must base their decisions on preliminary and partially revised data of varying reliability. Realistic modeling of data revisions is required to guide decision makers in their assessment of current and future conditions. This paper provides a new framework with which to model data revisions.Recent empirical work suggests that measurement errors typically have much more complex dynamics than existing models of data revisions allow. This paper describes a state-space model that allows for richer dynamics in these measurement errors, including the noise, news and spillover effects documented in this literature. We also show how to relax the common assumption that “true” values are observed after a few revisions.The result is a unified and flexible framework that allows for more realistic data revision properties, and allows the use of standard methods for optimal real-time estimation of trends and cycles. We illustrate the application of this framework with real-time data on US real output growth.     

Data revisions to German national accounts: Are initial releases good nowcasts?

Data revisions to national accounts pose a serious challenge to policy decision making. Well-behaved revisions should be unbiased, small, and unpredictable. This article shows that revisions to German national accounts are biased, large, and predictable. Moreover, with use of filtering techniques designed to process data subject to revisions, the real-time forecasting performance of initial releases can be increased by up to 23%. For total real GDP growth, however, the initial release is an optimal forecast. Yet, given the results for disaggregated variables, the averaging out of biases and inefficiencies at the aggregate GDP level appears to be good luck rather than good forecasting.     

Predicting benchmarked US state employment data in real time

US payroll employment data come from a survey and are subject to revisions. While revisions are generally small at the national level, they can be large enough at the state level to alter assessments of current economic conditions. Users must therefore exercise caution in interpreting state employment data until they are “benchmarked” against administrative data 5–16 months after the reference period. This article develops a state-space model that predicts benchmarked state employment data in real time. The model has two distinct features: (1) an explicit model of the data revision process and (2) a dynamic factor model that incorporates real-time information from other state-level labor market indicators. We find that the model reduces the average size of benchmark revisions by about 11 percent. When we optimally average the model’s predictions with those of existing models, the model reduces the average size of the revisions by about 14 percent.     

Reducing revisions in hedonic house price indices by the use of nowcasts

National Statistical Institutes (NSIs) must balance between timeliness and accuracy of the indicators they publish. Because some of the house sales transactions are reported several months after they occur, many countries that include Israel, publish provisional house price indices (HPIs) that are subject to large revisions as further transactions are reported. This happens because the late-reported transactions behave differently from the transactions reported on time. In this paper, we propose a novel methodology to minimize the size of the revisions, with illustrations from Israel, but the method can be applied to other countries with appropriate modifications. The proposed methodology consists of nowcasting three types of variables at a subdistrict level and adding them as input data to an extended hedonic model used for the computation of the HPI: (1) the average characteristics of the late-reported transactions such as the average number of rooms and the area size of the sold apartments; (2) the average price of the late-reported transactions; and (3) the number of late-reported transactions. The three variables are nowcasted based on models fitted to data from previous months. Evaluation of our methodology shows more than 50% reduction in the magnitude of the revisions.     

On forecasting cointegrated seasonal time series

We analyze periodic and seasonal cointegration models for bivariate quarterly observed time series in an empirical forecasting study. We include both single equation and multiple equation methods for those two classes of models. A VAR model in first differences, with and without cointegration restrictions, and a VAR model in annual differences are also included in the analysis, where they serve as benchmark models. Our empirical results indicate that the VAR model in first differences without cointegration is best if one-step ahead forecasts are considered. For longer forecast horizons however, the VAR model in annual differences is better. When comparing periodic versus seasonal cointegration models, we find that the seasonal cointegration models tend to yield better forecasts. Finally, there is no clear indication that multiple equations methods improve on single equation methods.     

Green shoots and double dips in the euro area: A real time measure

In order to perform real-time business cycle inferences and forecasts of GDP growth rates in the euro area, we use an extension of the Markov-switching dynamic factor models that accounts for the features of the day-to-day monitoring of economic developments, such as ragged edges, mixed frequencies and data revisions. We provide examples that show the nonlinear nature of the relationships between data revisions, point forecasts and forecast uncertainty. Based on our empirical results, we think that the real-time probabilities of recession inferred from the model are an appropriate statistic for capturing what the press call green shoots, and for monitoring double-dip recessions.     

Are Weekly Inflation Forecasts Informative?*

Are weekly inflation forecasts informative? Although several central banks review and discuss monetary policy issues on a bi‐weekly basis, there have been no attempts by analysts to construct systematic estimates of core inflation that supports such a decision‐making schedule. The timeliness of news releases are recognized to be an important information source in real‐time estimation. We incorporate real‐time information from macroeconomic releases and revisions into our weekly updates of monthly Swiss core inflation using a common factor procedure. The weekly estimates for Swiss core inflation show that it is worthwhile to update the forecast at least twice a month.     

UK Overview

The ONS's annual re‐write of economic history means that the forecast for GDP starts from a higher level than previously thought. However, the revisions also show slightly weaker momentum coming into 2015 which, along with the run of softer data through the summer, have led us to push down our forecast for GDP growth in 2015 and 2016 from 2.6% and 2.8% respectively three months ago, to 2.5% and 2.6% now.     

Forecast combination for U.S. recessions with real-time data

This paper proposes the use of forecast combination to improve predictive accuracy in forecasting the U.S. business cycle index, as published by the Business Cycle Dating Committee of the NBER. It focuses on one-step ahead out-of-sample monthly forecast utilising the well-established coincident indicators and yield curve models, allowing for dynamics and real-time data revisions. Forecast combinations use log-score and quadratic-score based weights, which change over time. This paper finds that forecast accuracy improves when combining the probability forecasts of both the coincident indicators model and the yield curve model, compared to each model's own forecasting performance.     

The tourism forecasting competition

We evaluate the performances of various methods for forecasting tourism data. The data used include 366 monthly series, 427 quarterly series and 518 annual series, all supplied to us by either tourism bodies or academics who had used them in previous tourism forecasting studies. The forecasting methods implemented in the competition are univariate and multivariate time series approaches, and econometric models. This forecasting competition differs from previous competitions in several ways: (i) we concentrate on tourism data only; (ii) we include approaches with explanatory variables; (iii) we evaluate the forecast interval coverage as well as the point forecast accuracy; (iv) we observe the effect of temporal aggregation on the forecasting accuracy; and (v) we consider the mean absolute scaled error as an alternative forecasting accuracy measure. We find that pure time series approaches provide more accurate forecasts for tourism data than models with explanatory variables. For seasonal data we implement three fully automated pure time series algorithms that generate accurate point forecasts, and two of these also produce forecast coverage probabilities which are satisfactorily close to the nominal rates. For annual data we find that Naïve forecasts are hard to beat.     

Forecasting bulk prices of Bordeaux wines using leading indicators

Agricultural price forecasting has been being abandoned progressively by researchers ever since the development of large-scale agricultural futures markets. However, as with many other agricultural goods, there is no futures market for wine. This paper draws on the agricultural prices forecasting literature to develop a forecasting model for bulk wine prices. The price data include annual and monthly series for various wine types that are produced in the Bordeaux region. The predictors include several leading economic indicators of supply and demand shifts. The stock levels and quantities produced are found to have the highest predictive power. The preferred annual and monthly forecasting models outperform naive random walk forecasts by 27.1% and 3.4% respectively; their mean absolute percentage errors are 2.7% and 3.4% respectively. A simple trading strategy based on monthly forecasts is estimated to increase profits by 3.3% relative to a blind strategy that consists of always selling at the spot price.     

Stable seasonal pattern models for forecast revision: A comparative study

Many firms prepare forecasts at the beginning of each financial quarter that predict total sales over the upcoming quarter. Such forecasts may be used to make financial projections, or to plan manufacturing capacity and materials purchases. As weekly sales are recorded during the quarter, these quarterly forecasts are often revised, allowing plans and projections to be adjusted appropriately. A formal basis for these forecast revisions may be found in so-called stable seasonal pattern models, which are based on the observation that in many instances, the sales that accrue during a given period of a quarter follow a regular pattern. This paper discusses a number of stable seasonal pattern models – several from the literature, two that are novel – which have been evaluated for making forecast revisions at Sun Microsystems, Inc. Commonalities between the models are elucidated using a general theoretical framework, and a straightforward sample-based mechanism is described that affords great flexibility in the design and use of stable seasonal pattern models. The paper culminates in a detailed comparison of the performance of new and existing stable seasonal pattern models with respect to Sun's sales data.     

Characteristics and implications of Chinese macroeconomic data revisions

The research examining macroeconomic data for developed economies suggests that an understanding of the nature of data revisions is important both for the production of accurate macroeconomic forecasts and for forecast evaluation. This paper focuses on Chinese data, for which there has been substantial debate about data quality for some time. The key finding in this paper is that, while it is true that the Chinese macroeconomic data revisions are not well-behaved, they are not very different from similarly-timed U.S. macroeconomic data revisions. The positive bias in Chinese real GDP revisions is a result of the fast-growing service sector, which is notably hard to measure in real time. A better understanding of the revisions process is particularly helpful for studies of the forecast errors from surveys of forecasters, where the choice of the vintage for outcomes may have an impact on the estimated forecast errors.     

Predictions of annual earnings using quarterly earnings,annual earnings and dividend payout ratios

This study empirically examines two issues related to forecasting annual accounting earnings. The first issue studied is the improvement in forecasts of annual earnings that can be obtained by including information about dividend payout along with the past earnings series in forecasting models. The second issue deals with the comparative ability of quarterly earnings time series models and annual earnings time series models to predict annual earnings. The results of this study indicate that considerable improvement in predictive ability can be obtained by expanding the information set to include the dividend payout ratio series. The empirical analysis also indicates that time series models developed using annual earnings generate more accurate predictions of annual earnings than do models developed using quarterly earnings.     

Forecasting and stress testing credit card default using dynamic models

We present discrete time survival models of borrower default for credit cards that include behavioural data about credit card holders and macroeconomic conditions across the credit card lifetime. We find that dynamic models which include these behavioural and macroeconomic variables provide statistically significant improvements in model fit, which translate into better forecasts of default at both account and portfolio levels when applied to an out-of-sample data set. By simulating extreme economic conditions, we show how these models can be used to stress test credit card portfolios.