nep-for New Economics Papers
on Forecasting
Issue of 2020‒08‒10
seven papers chosen by
Rob J Hyndman
Monash University

  1. Forecasting Financial Vulnerability in the US: A Factor Model Approach By Hyeongwoo Kim; Wen Shi
  2. Nowcasting unemployment insurance claims in the time of COVID-19 By William D. Larson; Tara M. Sinclair
  3. Modelling and Forecasting Macroeconomic Downside Risk By Delle-Monache, Davide; De-Polis, Andrea; Petrella, Ivan
  4. Forecast Reconciliation: A geometric View with New Insights on Bias Correction By Anastasios Panagiotelis; Puwasala Gamakumara; George Athanasopoulos; Rob J Hyndman
  5. Forecasting Singapore GDP using the SPF data By Xie, Tian; Yu, Jun
  6. Predicting the global minimum variance portfolio By Reh, Laura; Krüger, Fabian; Liesenfeld, Roman
  7. A Macroeconometric Model for Kazakhstan By Nurdaulet Abilov; Alisher Tolepbergen; Klaus Weyerstrass

  1. By: Hyeongwoo Kim; Wen Shi
    Abstract: This paper presents a factor-based forecasting model for the financial market vulnerability, measured by changes in the Cleveland Financial Stress Index (CFSI). We estimate latent common factors via the method of the principal components from 170 monthly frequency macroeconomic data in order to out-of-sample forecast the CFSI. Our factor models outperform both the random walk and the autoregressive benchmark models in out-of-sample predictability at least for the short-term forecast horizons, which is a desirable feature since financial crises often come to a surprise realization. Interestingly, the first common factor, which plays a key role in predicting the financial vulnerability index, seems to be more closely related with real activity variables rather than nominal variables. We also present a binary choice version factor model that estimates the probability of the high stress regime successfully.
    Keywords: Financial Stress Index; Method of the Principal Component; Out-of-Sample Forecast; Relative Root Mean Square Prediction Error; Diebold-Mariano-West Statistic; Ordered Probit Model
    JEL: E44 E47 G01 G17
    Date: 2020–07
  2. By: William D. Larson; Tara M. Sinclair
    Abstract: Near term forecasts, also called nowcasts, are most challenging but also most important when the economy experiences an abrupt change. In this paper, we explore the performance of models with different information sets and data structures in order to best nowcast US initial unemployment claims in spring of 2020 in the midst of the COVID-19 pandemic. We show that the best model, particularly near the structural break in claims, is a state-level panel model that includes dummy variables to capture the variation in timing of state-of-emergency declarations. Autoregressive models perform poorly at first but catch up relatively quickly. Models including Google Trends are outperformed by alternative models in nearly all periods. Our results suggest that in times of structural change there may be simple approaches to exploit relevant information in the cross sectional dimension to improve forecasts.
    Keywords: panel forecasting, time series forecasting, forecast evaluation, structural breaks, Google Trends
    JEL: C53 E24 E27 J64 R23
    Date: 2020–07
  3. By: Delle-Monache, Davide (Bank of Italy); De-Polis, Andrea (University of Warwick); Petrella, Ivan (University of Warwick)
    Abstract: We investigate the relation between downside risk to the economy and the financial markets within a fully parametric model. We characterize the complete predictive distribution of GDP growth employing a Skew-t distribution with time- varying location, scale, and shape, for which we model both secular trends and cyclical changes. Episodes of downside risk are characterized by increasing negative asymmetry, which emerges as a clear feature of the data. Negatively skewed pre- dictive distributions arise ahead and during recessions, and tend to be anticipated by tightening of financial conditions. Indicators of excess leverage and household credit outstanding are found to be significant drivers of downside risk. Moreover, the Great Recession marks a significant shift in the unconditional distribution of GDP growth, which has featured a distinct negative skewness since then. The model delivers competitive out-of-sample (point and density) forecasts, improving upon standard benchmarks, especially due to financial conditions providing a strong signal of increasing downside risk.
    Keywords: business cycles ; financial conditions ; downside risk ; skewness ; score-driven models ;
    JEL: E37
    Date: 2020
  4. By: Anastasios Panagiotelis; Puwasala Gamakumara; George Athanasopoulos; Rob J Hyndman
    Abstract: A geometric interpretation is developed for so-called reconciliation methodologies used to forecast time series that adhere to known linear constraints. In particular, a general framework is established nesting many existing popular reconciliation methods within the class of projections. This interpretation facilitates the derivation of novel theoretical results. First, reconciliation via projection is guaranteed to improve forecast accuracy with respect to a class of loss functions based on a generalised distance metric. Second, the MinT method minimises expected loss for this same class of loss functions. Third, the geometric interpretation provides a new proof that forecast reconciliation using projections results in unbiased forecasts provided the initial base forecasts are also unbiased. Approaches for dealing with biased base forecasts are proposed. An extensive empirical study on Australian tourism flows demonstrates the theoretical results of the paper and shows that bias correction prior to reconciliation outperforms alternatives that only bias-correct or only reconcile forecasts.
    Date: 2020
  5. By: Xie, Tian (Shanghai University of Finance and Economics); Yu, Jun (School of Economics, Singapore Management University)
    Abstract: In this article, we use econometric methods, machine learning methods, and a hybrid method to forecast the GDP growth rate in Singapore based on the Survey of Professional Forecasters (SPF). We compare the performance of these methods with the sample median used by the Monetary Authority of Singapore (MAS). It is shown that the relationship between the actual GDP growth rates and the forecasts from individual professionals is highly nonlinear and non-additive, making it hard for all linear methods and the sample median to perform well. It is found that the hybrid method performs the best, reducing the mean squared forecast error (MSFE) by about 50% relative to that of the sample median.
    Date: 2020–07–14
  6. By: Reh, Laura; Krüger, Fabian; Liesenfeld, Roman
    Abstract: We propose a novel dynamic approach to forecast the weights of the global minimum variance portfolio (GMVP). The GMVP weights are the population coefficients of a linear regression of a benchmark return on a vector of return differences. This representation enables us to derive a consistent loss function from which we can infer the optimal GMVP weights without imposing any distributional assumptions on the returns. In order to capture time variation in the returns' conditional covariance structure, we model the portfolio weights through a recursive least squares (RLS) scheme as well as by generalized autoregressive score (GAS) type dynamics. Sparse parameterizations combined with targeting towards nonlinear shrinkage estimates of the long-run GMVP weights ensure scalability with respect to the number of assets. An empirical analysis of daily and monthly financial returns shows that the proposed models perform well in- and out-of-sample in comparison to existing approaches.
    Keywords: Consistent loss function,Elicitability,Forecasting,Generalized autoregressivescore,Nonlinear shrinkage,Recursive least squares
    JEL: C14 C32 C51 C53 C58 G11 G17
    Date: 2020
  7. By: Nurdaulet Abilov (NAC Analytica, Nazarbayev University); Alisher Tolepbergen (NAC Analytica, Nazarbayev University); Klaus Weyerstrass (Institute for Advanced Studies, Macroeconomics and Public Finance Group)
    Abstract: The paper builds a structural macroeconometric model for Kazakhstan to generate short-term and medium-term forecasts for main macroeconomic variables and conduct scenario analyses based on dynamic simulation of the model. Due to the poor quality of quarterly data on GDP and its expenditure components, they have been adjusted using volume indexes. The model consists of aggregate supply, aggregate demand, labor market, asset market, the central bank policy and government side equations. Most equations are estimated via econometric techniques and identities are explicitly introduced in line with economic theory. We combine all the regression equations into a single model and solve for the baseline scenario from 2003 to 2017. The simulation results show that the structural macroeconometric model approximates Kazakhstani economy reasonably well. Ex-ante forecasts under oil prices remaining around 50 and 60 US dollars per barrel are generated and compared with the baseline forecast of the National Bank of the Republic of Kazakhstan.
    Keywords: Macroeconometric model; Cowles Commission approach; Forecasting; Simulation.
    JEL: B32 E17 E27
    Date: 2018–12

This nep-for issue is ©2020 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.