Person
Elmar Mertens
Contributing Author
Elmar Mertens is a contributing author.
-
-
Working Papers
-
Working Paper
What is the Predictive Value of SPF Point and Density Forecasts?
11.28.2022 | WP 22-37This paper presents a new approach to combining the information in point and density forecasts from the Survey of Professional Forecasters (SPF) and assesses the incremental value of the density forecasts. Our starting point is a model, developed in companion work, that constructs quarterly term structures of expectations and uncertainty from SPF point forecasts for quarterly fixed horizons and annual fixed events. We then employ entropic tilting to bring the density forecast information contained in the SPF’s probability bins to bear on the model estimates. In a novel application of entropic tilting, we let the resulting predictive densities exactly replicate the SPF’s probability bins. Our empirical analysis of SPF forecasts of GDP growth and inflation shows that tilting to the SPF’s probability bins can visibly affect our model-based predictive distributions. Yet in historical evaluations, tilting does not offer consistent benefits to forecast accuracy relative to the model-based densities that are centered on the SPF’s point forecasts and reflect the historical behavior of SPF forecast errors. That said, there can be periods in which tilting to the bin information helps forecast accuracy. -
Working Paper
Constructing Fan Charts from the Ragged Edge of SPF Forecasts
11.23.2022 | WP 22-36We develop a model that permits the estimation of a term structure of both expectations and forecast uncertainty for application to professional forecasts such as the Survey of Professional Forecasters (SPF). Our approach exactly replicates a given data set of predictions from the SPF (or a similar forecast source) without measurement error. Our model captures fixed horizon and fixed-event forecasts, and can accommodate changes in the maximal forecast horizon available from the SPF. The model casts a decomposition of multi-period forecast errors into a sequence of forecast updates that may be partially unobserved, resulting in a multivariate unobserved components model. In our empirical analysis, we provide quarterly term structures of expectations and uncertainty bands. Our preferred specification features stochastic volatility in forecast updates, which improves forecast performance and yields model estimates of forecast uncertainty that vary over time. We conclude by constructing SPF-based fan charts for calendar-year forecasts like those published by the Federal Reserve. -
Working Paper
Measuring Uncertainty and Its Effects in the COVID-19 Era
01.04.2022 | WP 20-32RWe measure the effects of the COVID-19 outbreak on uncertainty, and we assess the consequences of the uncertainty for key economic variables. We use a large, heteroskedastic vector autoregression (VAR) in which the error volatilities share two common factors, interpreted as macro and financial uncertainty. Macro and financial uncertainty are allowed to contemporaneously affect the macroeconomy and financial conditions, with changes in the common component of the volatilities providing contemporaneous identifying information on uncertainty. The model includes additional latent volatility states in order to accommodate outliers in volatility, to reduce the influence of extreme observations from the COVID period. Our estimates yield large increases in macroeconomic and financial uncertainty since the onset of the COVID-19 period. These increases have contributed to the downturn in economic and financial conditions, but the contributions of uncertainty are small compared to the overall movements in many macroeconomic and financial indicators. That implies that the downturn is driven more by other dimensions of the COVID crisis than shocks to aggregate uncertainty (as measured by our method). -
Working Paper
Addressing COVID-19 Outliers in BVARs with Stochastic Volatility
08.09.2021 | WP 21-02RThe COVID-19 pandemic has led to enormous movements in economic data that strongly affect parameters and forecasts obtained from standard VARs. One way to address these issues is to model extreme observations as random shifts in the stochastic volatility (SV) of VAR residuals. Specifically, we propose VAR models with outlier-augmented SV that combine transitory and persistent changes in volatility. The resulting density forecasts for the COVID-19 period are much less sensitive to outliers in the data than standard VARs. Evaluating forecast performance over the last few decades, we find that outlier-augmented SV schemes do at least as well as a conventional SV model. Predictive Bayes factors indicate that our outlier-augmented SV model provides the best data fit for the period since the pandemic’s outbreak, as well as for earlier subsamples of relatively high volatility. -
Working Paper
Forecasting with Shadow-Rate VARs
03.29.2021 | WP 21-09Interest rate data are an important element of macroeconomic forecasting. Projections of future interest rates are not only an important product themselves, but also typically matter for forecasting other macroeconomic and financial variables. A popular class of forecasting models is linear vector autoregressions (VARs) that include shorter- and longer-term interest rates. However, in a number of economies, at least shorter-term interest rates have now been stuck for years at or near their effective lower bound (ELB), with longer-term rates drifting toward the constraint as well. In such an environment, linear forecasting models that ignore the ELB constraint on nominal interest rates appear inept. To handle the ELB on interest rates, we model observed rates as censored observations of a latent shadow-rate process in an otherwise standard VAR setup. The shadow rates are assumed to be equal to observed rates when above the ELB. Point and density forecasts for interest rates (short term and long term) constructed from a shadow-rate VAR for the US since 2009 are superior to predictions from a standard VAR that ignores the ELB. For other indicators of financial conditions and measures of economic activity and inflation, the accuracy of forecasts from our shadow-rate specification is on par with a standard VAR that ignores the ELB. -
Working Paper
Addressing COVID-19 Outliers in BVARs with Stochastic Volatility
02.02.2021 | WP 21-02Incoming data in 2020 posed sizable challenges for the use of VARs in economic analysis: Enormous movements in a number of series have had strong effects on parameters and forecasts constructed with standard VAR methods. We propose the use of VAR models with time-varying volatility that include a treatment of the COVID extremes as outlier observations. Typical VARs with time-varying volatility assume changes in uncertainty to be highly persistent. Instead, we adopt an outlier-adjusted stochastic volatility (SV) model for VAR residuals that combines transitory and persistent changes in volatility. In addition, we consider the treatment of outliers as missing data. Evaluating forecast performance over the last few decades in quasi-real time, we find that the outlier-augmented SV scheme does at least as well as a conventional SV model, while both outperform standard homoskedastic VARs. Point forecasts made in 2020 from heteroskedastic VARs are much less sensitive to outliers in the data, and the outlier-adjusted SV model generates more reasonable gauges of forecast uncertainty than a standard SV model. At least pre-COVID, a close alternative to the outlier-adjusted model is an SV model with t-distributed shocks. Treating outliers as missing data also generates better-behaved forecasts than the conventional SV model. However, since uncertainty about the incidence of outliers is ignored in that approach, it leads to strikingly tight predictive densities. -
Working Paper
Measuring Uncertainty and Its Effects in the COVID-19 Era
10.23.2020 | WP 20-32We measure the effects of the COVID-19 outbreak on macroeconomic and financial uncertainty, and we assess the consequences of the latter for key economic variables. We use a large, heteroskedastic vector autoregression (VAR) in which the error volatilities share two common factors, interpreted as macro and financial uncertainty, in addition to idiosyncratic components. Macro and financial uncertainty are allowed to contemporaneously affect the macroeconomy and financial conditions, with changes in the common component of the volatilities providing contemporaneous identifying information on uncertainty. We also consider an extended version of the model, based on a latent state approach to accommodating outliers in volatility, to reduce the influence of extreme observations from the COVID period. The estimates we obtain yield very large increases in macroeconomic and financial uncertainty over the course of the COVID-19 period. These increases have contributed to the downturn in economic and financial conditions, but with both models, the contributions of uncertainty are small compared to the overall movements in many macroeconomic and financial indicators. That implies that the downturn is driven more by other dimensions of the COVID crisis than shocks to aggregate uncertainty (as measured by our method). -
Working Paper
Modeling Time-Varying Uncertainty of Multiple-Horizon Forecast Errors
05.08.2018 | WP 17-15RWe estimate uncertainty measures for point forecasts obtained from survey data, pooling information embedded in observed forecast errors for different forecast horizons. To track time-varying uncertainty in the associated forecast errors, we derive a multiple-horizon specification of stochastic volatility. We apply our method to forecasts for various macroeconomic variables from the Survey of Professional Forecasters. Compared to constant variance approaches, our stochastic volatility model improves the accuracy of uncertainty measures for survey forecasts. Our method can also be applied to other surveys like the Blue Chip Consensus, or the Federal Open Market Committee’s Summary of Economic Projections. -
Working Paper
Modeling Time-Varying Uncertainty of Multiple-Horizon Forecast Errors
09.01.2017 | WP 17-15We develop uncertainty measures for point forecasts from surveys such as the Survey of Professional Forecasters, Blue Chip, or the Federal Open Market Committee’s Summary of Economic Projections. At a given point of time, these surveys provide forecasts for macroeconomic variables at multiple horizons. To track time-varying uncertainty in the associated forecast errors, we derive a multiple-horizon specification of stochastic volatility. Compared to constant-variance approaches, our stochastic-volatility model improves the accuracy of uncertainty measures for survey forecasts.
-
-
-
-