What can we learn from revisions to the Greenbook forecasts?

Although there have been many evaluations of the Federal Reserve’s Greenbook forecasts, we analyze them in a different dimension. We examine the revisions of these forecasts in the context of fixed event predictions to determine how new information is incorporated in the forecasting process. This analysis permits us to determine if there was an inefficient use of information in the sense that the forecast revision has predictive power for the forecast error. Research on forecast smoothing suggests that we might find a positive relationship between the forecast error and the forecast revision. Although we do find for some variables and horizons the Fed’s forecast errors are predictable from its forecast revisions, there is no evidence of forecast smoothing. Instead the revisions sometimes have a negative relationship with the forecast error, suggesting in these cases that the Fed may be over-responsive to new information.     

通货膨胀实时预测及菲利普斯曲线的适用性

本文从实时分析的视角,基于多种退势方法的产出缺口最终估计、准最终估计和实时估计序列,分别构建了四类预测模型对我国通货膨胀率进行预测,分析了产出缺口修正效应和滞后阶数变化效应对通胀预测的影响,并进一步考察了产出缺口在通胀预测中的作用及菲利普斯曲线在通胀预测中的适用性。研究结论表明,通胀率的实时预测效果要明显比基于最终数据的差,其中滞后阶数变化效应对实时预测精度的影响大于产出缺口修正效应;尤为重要的是,尽管在最终数据的预测分析中,产出缺口的引入能够提高通胀率的预测精度,但是在实时预测中,产出缺口没有提供有价值的信息,因此"产出—通胀"型菲利普斯曲线在我国通胀实时预测中并不适用。     

Dissecting models' forecasting performance

The fact that the predictive performance of models used in forecasting stock returns, exchange rates, and macroeconomic variables is not stable and varies over time has been widely documented in the forecasting literature. Under these circumstances excessive reliance on forecast evaluation metrics that ignores this instability in forecasting accuracy, like squared errors averaged over the whole forecast evaluation sample, masks important information regarding the temporal evolution of relative forecasting performance of competing models. In this paper we suggest an approach based on the combination of the Cumulated Sum of Squared Forecast Error Differential (CSSFED) of Welch and Goyal (2008) and the Bayesian change point analysis of Barry and Hartigan (1993) that tracks the contribution of forecast errors to the aggregate measures of forecast accuracy observation by observation. In doing so, it allows one to track the evolution of the relative forecasting performance over time. We illustrate the suggested approach by using forecasts of the GDP growth rate in Switzerland.     

Did rainfall shocks cause civil conflict in Sub-Saharan Africa? The implications of data revisions

In their seminal paper, Miguel et al. (2004) found that negative rainfall shocks (measured as negative year-on-year rainfall growth) had caused civil conflict in sub-Saharan Africa over the 1981–1999 period. Since then, the rainfall and conflict data they used had undergone multiple revisions. We show that rainfall shocks are no longer statistically significant for civil conflict when the revised data are used. This is true whether we employ a different functional form for rainfall, extend the sample to include more recent observations, use longer lags for rainfall shocks, employ dynamic panel regression, or panel regressions that take into account of cross-sectional dependence. Using rainfall shocks as instruments for growth, we also find that growth is insignificant for civil conflict if the revised data are used. Upon further investigation, we find that updates in the rainfall and conflict data for one or a few countries may alone cause rainfall shocks to lose statistical significance.     

Can rational stubbornness explain forecast biases?

This paper examines whether the rational jumpiness/stubbornness hypothesis can explain forecast biases. Using a dataset of professional GDP forecasts for the G7 countries over the period 1989–2010, we find evidence supporting the rational stubbornness hypothesis. Specifically, forecasters underreact more when large forecast revisions are highly indicative of low forecast ability. Underreaction is less likely when the size of forecast revisions is unrelated to ability. These findings are consistent with the hypothesis that forecasters choose to smooth GDP forecasts to maximize their perceived ability.     

Growth and inflation forecasts for Germany a panel-based assessment of accuracy and efficiency

We analyse forecasts of professional forecasters for Germany regarding the time span from 1970 to 2004. This novel panel data set renders it possible to assess the accuracy and efficiency of growth and inflation forecasts more efficiently than in previous studies. We argue that the forecasts are, on average, unbiased and weakly—but not strongly—efficient. Using model confidence sets suggested by Hansen et al. (2004), we find that, besides the effect of diverging forecasting dates, no other substantial differences in forecasting quality among forecasters exist. Nevertheless, on the basis of a direction-of-change analysis we argue that it is not always advisable to listen to the majority of forecasters.

Optimal monetary policy revisited: does considering US real-time data change things?

The primary goal of this article is to investigate whether properly modelling real-time data and optimal real-time decision-making of a monetary planner provides new insights into monetary policy behaviour and outcomes. This article extends a variant of the asymmetric preference model suggested by Ruge-Murcia to investigate the use of real-time data available to policymakers when making their decisions and revised data which more accurately measure economic performance, but is only available much later. In our extended model, the central banker targets a weighted average of revised and real-time inflation together with a weighted average of revised and real-time output. Moreover, we allow for an asymmetric central bank response to real-time data depending on whether the unemployment rate is high or low. Our model identifies several new potential sources of inflation bias due to data revisions. Our empirical results suggest that the Federal Reserve Bank focuses on targeting revised inflation during low unemployment periods, but it weighs heavily real-time inflation during high unemployment periods. The inflation bias due to data revisions is comparable in magnitude to the bias from asymmetric central banker preferences with the bias being somewhat larger during high unemployment.     

Forecasting revisions of German industrial production

Macroeconomic variables, such as industrial production or GDP, are regularly and sometimes substantially revised by the official statistical offices. Nevertheless, there are only few attempts in the previous literature to investigate whether it is possible to forecast these revisions systematically. In this article, it is illustrated how revisions of German industrial production can be forecasted with respect to both the direction and the level of the revision. We are the first to use a large data set for this purpose.     

On the estimation and forecasting of international migration: how relevant is heterogeneity across countries?

This paper performs a comparative analysis of estimation as well as of out-of-sample forecasting results of more than 20 estimators common in the panel data literature using the data on migration to Germany from 18 source countries in the period 1967–2001. Our results suggest that the choice of an estimation procedure has a substantial impact on the parameter estimates of the migration function. Out-of-sample forecasting results indicate the following: (1) the standard fixed effects estimators clearly outperforms the pooled OLS estimator, (2) both the fixed effects estimators and the hierarchical Bayes estimator exhibit the superior forecast performance, (3) the fixed effects estimators outperform GMM and other instrumental variables estimators, (4) forecasting performance of heterogenous estimators is mediocre in our data set.     

Professional forecasts of interest rates and exchange rates: Evidence from the Wall Street Journal’s panel of economists

We analyze economists’ forecasts of interest rates and exchange rates from the Wall Street Journal. We find that a majority of economists produced unbiased forecasts but that none predicted directions of changes more accurately than chance. Most economists’ forecast accuracy is statistically indistinguishable from a random walk model in forecasting the Treasury bill rate, but many are significantly worse in forecasting the Treasury bond rate and the exchange rate. We also find systematic forecast heterogeneity, support for strategic models predicting the industry employing the economist matters, and evidence that economists deviate less from the consensus as they age.     

能源经济与政策研究中的数据问题

近年来,能源经济与政策研究文献大幅增长,其中绝大多数属于经验研究或政策模拟分析,所使用的基础数据大多来源于政府部门或者国际组织发布的宏观统计资料或者在线数据库。目前有的研究存在较多基础数据问题,从而可能导致结论出现偏误。为厘清各统计量之间的逻辑关系、减少数据滥用或者误用的可能性、增强研究过程的透明度和研究结果的可比性,本文从经济学和国民经济核算等视角讨论了能源经济与政策研究中的数据问题。在开展能源经济研究时,需要明确界定系统的边界,明晰输入量和输出量,传统的发电煤耗法等线性加总方法可能会导致研究结论出现偏误,应用Divisia能源加总方法要更为精准。不同的数据源口径往往不同,来自统计部门的能源数据与经济数据可能并不完全匹配,国内外能源数据口径及其核算方法也存在较大差异。如果不注意这些差异,直接进行数据大小比较是不可取的,甚至可能会导致一些没有科学意义的争议。     

中国宏观经济总量的实时预报与短期预测——基于混频数据预测模型的实证研究

季度GDP的走势与波动不仅会影响政府的财政收支、企业的盈利和财务状况,甚至还会影响家庭和个人的收入与支出,是宏观经济总量预报、预测与分析的重中之重。传统的宏观经济总量预测模型是基于同频数据进行的,高频和超高频数据必需处理为低频数据,这不仅忽略了高频数据信息的变化,还影响了模型预报和预测的及时性,降低了模型的预测精度。本文将混合数据抽样模型(MIDAS)用于中国季度GDP的预报和预测,实证研究表明,出口是造成我国金融危机时期经济增长减速的主要因素,MIDAS模型在中国宏观经济总量的短期预测方面具有精确性的比较优势,在实时预报方面具有显著的可行性和时效性。     

Measuring the output gap in Switzerland with linear opinion pools

We use the recently proposed linear opinion pool methodology of Garratt et al. (2014) to construct real-time output gap estimates for Switzerland over the out-of-sample period from 2003:Q1 to 2015:Q4. The model space consists of a large number of bivariate VAR specifications for the output gap and inflation, with each VAR specification using a different estimate of the output gap, lag order, and structural break information. We find that the linear opinion pool performs rather poorly. Real-time estimates of the output gap are no more accurate than those from some simple benchmark models, no more robust to ex post revisions than the real-time estimates of the individual univariate output gaps, and do not produce more accurate forecasts of inflation. The key driver of ‘good’ forecast performance is structural break information. Once the same structural break information is conditioned upon in all prediction models, the gain from averaging over many different pools of models that utilize various output gap estimates or lag structures in the VAR specification is of negligible magnitude.     

Forecasting inflation with an uncertain output gap

The output gap is a crucial concept in the monetary policy framework, indicating demand pressure that generates inflation. However, its definition and estimation raise a number of theoretical and empirical questions. This paper evaluates a series of univariate and multivariate methods for extracting the output gap in Norway, and compares their value added in predicting inflation. We find that models including the output gap have better predictive power than models based on alternative indicators, and they forecast significantly better than simple benchmark models. Furthermore multivariate measures of the output gap perform better than the univariate gaps. Comments from two anonymous referees, Q. Farooq Akram, Tommy Sveen, Ken West, Fredrik Wulfsberg and seminar participants in Norges Bank are gratefully acknowledged. All mistakes remain our own. The views expressed are those of the authors and do not necessarily represent those of Norges Bank.