nep-for New Economics Papers
on Forecasting
Issue of 2018‒04‒02
seven papers chosen by
Rob J Hyndman
Monash University

  1. Forecasting economic time series using score-driven dynamic models with mixed-data sampling By Paolo Gorgi; Siem Jan (S.J.) Koopman; Mengheng Li
  2. Forecasting with Bayesian Vector Autoregressions with Time Variation in the Mean By Marta Banbura; Andries van Vlodrop
  3. An Equilibrium Model of the Market for Bitcoin Mining By Julien Prat; Benjamin Walter
  4. Forecasts in Times of Crises By Theo S. Eicher; David J. Kuenzel; Chris Papageorgiou; Charis Christofides
  5. Mortgages: estimating default correlation and forecasting default risk By Neumann, Tobias
  6. State Correlation and Forecasting: A Bayesian Approach Using Unobserved Components Models By Luis Uzeda
  7. How Well Do Economists Forecast Recessions? By Zidong An; João Tovar Jalles; Prakash Loungani

  1. By: Paolo Gorgi (VU Amsterdam); Siem Jan (S.J.) Koopman (VU Amsterdam; Tinbergen Institute, The Netherlands); Mengheng Li (VU Amsterdam)
    Abstract: We introduce a mixed-frequency score-driven dynamic model for multiple time series where the score contributions from high-frequency variables are transformed by means of a mixed-data sampling weighting scheme. The resulting dynamic model delivers a flexible and easy-to-implement framework for the forecasting of a low-frequency time series variable through the use of timely information from high-frequency variables. We aim to verify in-sample and out-of-sample performances of the model in an empirical study on the forecasting of U.S.~headline inflation. In particular, we forecast monthly inflation using daily oil prices and quarterly inflation using effective federal funds rates. The forecasting results and other findings are promising. Our proposed score-driven dynamic model with mixed-data sampling weighting outperforms competing models in terms of point and density forecasts.
    Keywords: Factor model; GAS model; Inflation forecasting; MIDAS; Score-driven model; Weighted maximum likelihood
    JEL: C42
    Date: 2018–03–21
  2. By: Marta Banbura (European Central Bank, Germany); Andries van Vlodrop (VU Amsterdam, the Netherlands)
    Abstract: We develop a vector autoregressive model with time variation in the mean and the variance. The unobserved time-varying mean is assumed to follow a random walk and we also link it to long-term Consensus forecasts, similar in spirit to so called democratic priors. The changes in variance are modelled via stochastic volatility. The proposed Gibbs sampler allows the researcher to use a large cross-sectional dimension in a feasible amount of computational time. The slowly changing mean can account for a number of secular developments such as changing inflation expectations, slowing productivity growth or demographics. We show the good forecasting performance of the model relative to popular alternatives, including standard Bayesian VARs with Minnesota priors, VARs with democratic priors and standard time-varying parameter VARs for the euro area, the United States and Japan. In particular, incorporating survey forecast information helps to reduce the uncertainty about the unconditional mean and along with the time variation improves the long-run forecasting performance of the VAR models.
    Keywords: Consensus forecasts; forecast evaluation; large cross-sections; state space models.
    JEL: C11 C32 C53 E37
    Date: 2018–03–21
  3. By: Julien Prat; Benjamin Walter
    Abstract: We propose a model which uses the Bitcoin/US dollar exchange rate to predict the computing power of the Bitcoin network. We show that free entry places an upper-bound on mining revenues and we devise a structural framework to measure its value. Calibrating the model’s parameters allows us to accurately forecast the evolution of the network computing power over time. We establish the accuracy of the model through out-of-sample tests and investigation of the entry rule.
    Keywords: Bitcoin, blockchain, miners, industry dynamics
    JEL: D41 L10
    Date: 2018
  4. By: Theo S. Eicher; David J. Kuenzel; Chris Papageorgiou; Charis Christofides
    Abstract: Financial crises pose unique challenges for forecast accuracy. Using the IMF’s Monitoring of Fund Arrangement (MONA) database, we conduct the most comprehensive evaluation of IMF forecasts to date for countries in times of crises. We examine 29 macroeconomic variables in terms of bias, efficiency, and information content to find that IMF forecasts add substantial informational value as they consistently outperform naive forecast approaches. However, we also document that there is room for improvement: two thirds of the key macroeconomic variables that we examine are forecast inefficiently and 6 variables (growth of nominal GDP, public investment, private investment, the current account, net transfers, and government expenditures) exhibit significant forecast bias. Forecasts for low-income countries are the main drivers of forecast bias and inefficiency, reflecting perhaps larger shocks and lower data quality. When we decompose the forecast errors into their sources, we find that forecast errors for private consumption growth are the key contributor to GDP growth forecast errors. Similarly, forecast errors for non-interest expenditure growth and tax revenue growth are crucial determinants of the forecast errors in the growth of fiscal budgets. Forecast errors for balance of payments growth are significantly influenced by forecast errors in goods import growth. The results highlight which macroeconomic aggregates require further attention in future forecast models for countries in crises.
    Date: 2018–03–09
  5. By: Neumann, Tobias (Bank of England)
    Abstract: Default correlation is a key driver of credit risk. In the Basel regulatory framework it is measured by the asset value correlation parameter. Though past studies suggest that the parameter is over-calibrated for mortgages — generally the largest asset class on banks’ balance sheets — they do not take into account bias arising from small samples or non-Gaussian risk factors. Adjusting for these biases using a non-Gaussian, non-linear state space model I find that the Basel calibration is appropriate for UK and US mortgages. This model also forecasts mortgage default rates accurately and parsimoniously. The model generates value-at-risk estimates for future mortgage default rates, which can be used to inform stress-testing and macroprudential policy.
    Keywords: Mortgages; bank regulation; credit risk; default correlation; state space model; Basel Committee; stress testing; macroprudential policy
    JEL: G11 G17 G21 G28
    Date: 2018–02–09
  6. By: Luis Uzeda
    Abstract: Implications for signal extraction from specifying unobserved components (UC) models with correlated or orthogonal innovations have been well investigated. In contrast, the forecasting implications of specifying UC models with different state correlation structures are less well understood. This paper attempts to address this gap in light of the recent resurgence of studies adopting UC models for forecasting purposes. Four correlation structures for errors are entertained: orthogonal, correlated, perfectly correlated innovations, and a new approach that combines features from two contrasting cases, namely, orthogonal and perfectly correlated innovations. Parameter space restrictions associated with different correlation structures and their connection with forecasting are discussed within a Bayesian framework. As perfectly correlated innovations reduce the covariance matrix rank, a Markov Chain Monte Carlo sampler, which builds upon properties of Toeplitz matrices and recent advances in precision-based algorithms, is developed. Our results for several measures of U.S. inflation indicate that the correlation structure between state variables has important implications for forecasting performance as well as estimates of trend inflation.
    Keywords: Econometric and statistical methods, Inflation and prices
    JEL: C C1 C11 C15 C5 C51 C53
    Date: 2018
  7. By: Zidong An; João Tovar Jalles; Prakash Loungani
    Abstract: We describe the evolution of forecasts in the run-up to recessions. The GDP forecasts cover 63 countries for the years 1992 to 2014. The main finding is that, while forecasters are generally aware that recession years will be different from other years, they miss the magnitude of the recession by a wide margin until the year is almost over. Forecasts during non-recession years are revised slowly; in recession years, the pace of revision picks up but not sufficiently to avoid large forecast errors. Our second finding is that forecasts of the private sector and the official sector are virtually identical; thus, both are equally good at missing recessions. Strong booms are also missed, providing suggestive evidence for Nordhaus’ (1987) view that behavioral factors—the reluctance to absorb either good or bad news—play a role in the evolution of forecasts.
    Date: 2018–03–05

This nep-for issue is ©2018 by Rob J Hyndman. It is provided as is without any express or implied warranty. It may be freely redistributed in whole or in part for any purpose. If distributed in part, please include this notice.
General information on the NEP project can be found at For comments please write to the director of NEP, Marco Novarese at <>. Put “NEP” in the subject, otherwise your mail may be rejected.
NEP’s infrastructure is sponsored by the School of Economics and Finance of Massey University in New Zealand.