nep-for New Economics Papers
on Forecasting
Issue of 2015‒10‒10
nine papers chosen by
Rob J Hyndman
Monash University

  1. Electric load forecasting with recency effect: A big data approach By Pu Wang; Bidong Liu; Tao Hong
  2. Forecasting Inflation with the Hybrid New Keynesian Phillips Curve: A Compact-Scale Global VAR Approach By Medel, Carlos A.
  3. Score Driven Exponentially Weighted Moving Averages and Value-at-Risk Forecasting By Lucas, André; Zhang, Xin
  4. The predictive content of business survey indicators: evidence from SIGE By Tatiana Cesaroni; Stefano Iezzi
  5. Inflation forecasts: Are market-based and survey-based measures informative? By Grothe, Magdalena; Meyler, Aidan
  6. A fast algorithm for finding the confidence set of large collections of models By Sylvain Barde
  7. Time-varying Multivariate Extension of the Linear Market Model for Developed and Emerging Markets By SERDAR NESL
  8. Systemic risk rankings and network centrality in the European banking sector By De Bruyckere, Valerie
  9. Explaining the Recent Slump in Investment: the Role of Expected Demand and Uncertainty By M. Bussière; L. Ferrara; J. Milovich

  1. By: Pu Wang; Bidong Liu; Tao Hong
    Abstract: Temperature plays a key role in driving electricity demand. We adopt "recency effect", a term originated from psychology, to denote the fact that electricity demand is affected by the temperatures of preceding hours. In the load forecasting literature, the temperature variables are often constructed in the form of lagged hourly temperatures and moving average temperatures. Over the past decades, computing power has been limiting the amount of temperature variables that can be used in a load forecasting model. In this paper, we present a comprehensive study on modeling recency effect through a big data approach. We take advantage of the modern computing power to answer a fundamental question: how many lagged hourly temperatures and/or moving average temperatures are needed in a regression model to fully capture recency effect without compromising the forecasting accuracy? Using the case study based on data from the load forecasting track of the Global Energy Forecasting Competition 2012, we first demonstrate that a model with recency effect outperforms its counterpart (a.k.a., Tao’s Vanilla Benchmark Model) in forecasting the load series at the top (aggregated) level by 18% to 21%. We then apply recency effect modeling to customize load forecasting models at low level of a geographic hierarchy, again showing the superiority over the benchmark model by 12% to 15% on average. Finally, we discuss four different implementations of the recency effect modeling by hour of a day.
    Keywords: Electric load forecasting; Regression; Recency effect; Big data approach; Global Energy Forecasting Competition
    JEL: C22 C32 C53 Q47
    Date: 2015–10–03
  2. By: Medel, Carlos A.
    Abstract: In this article, it is analysed the multihorizon predictive power of the Hybrid New Keynesian Phillips Curve (HNKPC) making use of a compact-scale Global VAR for the headline inflation of six developed countries with different inflationary experiences; covering from 2000.1 until 2014.12. The key element of this article is the use of direct measures of inflation expectations--Consensus Economics--embedded in a Global VAR environment, i.e. modelling cross-country interactions. The Global VAR point forecast is evaluated using the Mean Squared Forecast Error (MSFE) statistic and statistically compared with several benchmarks. These belong to traditional statistical modelling, such as autoregressions (AR), the exponential smoothing model (ES), and the random walk model (RW). One last economics-based benchmark is the closed economy univariate HNKPC. The results indicate that the Global VAR is a valid forecasting procedure especially for the short-run. The most accurate forecasts, however, are obtained with the AR and especially with the univariate HNKPC. In the long-run, the ES model also appears as a better alternative rather than the RW. The MSPE is obviously affected by the unanticipated effects of the financial crisis started in 2008. So, when considering an evaluation sample just before the crisis, the GVAR also appears as a valid alternative in the long-run. The most robust forecasting devices across countries and horizons result in the univariate HNKPC, giving a role for economic fundamentals when forecasting inflation.
    Keywords: New Keynesian Phillips Curve; inflation forecasts; out-of-sample comparisons; survey data; Global VAR; time-series models
    JEL: C22 C26 C53 E31 E37 E47
    Date: 2015–10–05
  3. By: Lucas, André (VU University Amsterdam and Tinbergen Institute); Zhang, Xin (Research Department, Central Bank of Sweden)
    Abstract: A simple methodology is presented for modeling time variation in volatilities and other higher-order moments using a recursive updating scheme similar to the familiar RiskMetricsTM approach. We update parameters using the score of the forecasting distribution. This allows the parameter dynamics to adapt automatically to any nonnormal data features and robusti es the subsequent estimates. The new approach nests several of the earlier extensions to the exponentially weighted moving average (EWMA) scheme. In addition, it can easily be extended to higher dimensions and alternative forecasting distributions. The method is applied to Value-at-Risk forecasting with (skewed) Student's t distributions and a time-varying degrees of freedom and/or skewness parameter. We show that the new method is competitive to or better than earlier methods in forecasting volatility of individual stock returns and exchange rate returns.
    Keywords: dynamic volatilities; dynamic higher-order moments; integrated generalized autoregressive score models; Exponentially Weighted Moving Average (EWMA); Value-at-Risk (VaR)
    JEL: C51 C52 C53 G15
    Date: 2015–09–01
  4. By: Tatiana Cesaroni (Bank of Italy); Stefano Iezzi (Bank of Italy)
    Abstract: Business survey indicators represent an important tool in economic analysis and forecasting practices. While there is wide consensus on the coincident properties of such data, there is mixed evidence on their ability to predict macroeconomic developments in the short term. In this study we extend the previous research on the predictive content of business surveys by examining the leading properties of the main business survey indicators of the Italian Survey on Inflation and Growth Expectations (SIGE). To this end, we provide a complete characterization of the business cycle properties of survey data (volatility, stationarity, turning points etc.) and we compare them with the national accounts reference series. We further analyse the ability of SIGE indicators to detect turning points using both discrete and continuous dynamic single equation models as compared with their benchmark (B)ARIMA models. Overall, the results indicate that SIGE business indicators are able to make detect early the turning points of their corresponding national account reference series. These findings are very important from a policy-making point of view.
    Keywords: Business cycle, business survey data, turning points, cyclical analysis, forecast accuracy, macroeconomic forecasts
    JEL: C32 E32
    Date: 2015–09
  5. By: Grothe, Magdalena; Meyler, Aidan
    Abstract: This paper analyses the predictive power of market-based and survey-based inflation expectations for actual inflation. We use the data on inflation swaps and the forecasts from the Survey of Professional Forecasters for the euro area and United States. The results show that both, market-based and survey-based measures have a non-negligible predictive power for inflation developments, as compared to statistical benchmark models. Therefore, for horizons of one and two years ahead, market-based and survey-based inflation expectations actually convey information on future inflation developments.
    Keywords: inflation expectations; inflation forecasting; inflation swap markets; market-based inflation expectations; Survey of Professional Forecasters; survey-based inflation expectations;
    JEL: E31 E37 G13
    Date: 2015
  6. By: Sylvain Barde
    Abstract: The paper proposes a new algorithm for finding the confidence set of a collection of forecasts or prediction models. Existing numerical implementations for finding the confidence set use an elimination approach where one starts with the full collection of models and successively eliminates the worst performing until the null of equal predictive ability is no longer rejected at a given confidence level. The intuition behind the proposed implementation lies in reversing the process: one starts with a collection of two models and as models are successively added to the collection both the model rankings and p-values are updated. The first benefit of this updating approach is a reduction of one polynomial order in both the time complexity and memory cost of finding the confidence set of a collection of M models, falling respectively from O (M3) to O (M2) and from O (M2) to O (M). This theoretical prediction is confirmed by a Monte Carlo benchmarking analysis of the algorithms. The second key benefit of the updating approach is that it intuitively allows for further models to be added at a later point in time, thus enabling collaborative efforts using the model confidence set procedure.
    Keywords: Model selection; model confidence set; bootstrapped statistics
    JEL: C12 C18 C52
    Date: 2015–09
  7. By: SERDAR NESL (Eskisehir Osmangazi University)
    Abstract: This paper aims to evaluate the effectiveness of a Linear Market Model (consistent with the Two-moment CAPM) which permits beta risk. This evaluation leads to our positing two extensions. The first extension is a time-varying Linear Market Model using state space model which permits for time-varying beta risk. The second is a multivariate extension of the time-varying Linear Market Model permitting the between country stock market correlation structure to be constant over time. The analysis utilises weekly data from several emerging and developed markets for periods both before and after the October 2008 financial crisis. The findings lend great credence to the hypothesis that utilising the multivariate time-varying Linear Market Model is better in terms of in-sample modelling and out-of-sample forecasting procedure for both emerging and developed markets.
    Keywords: CAPM, Market model, Time-varying systematic covariance risk, Multivariate state space model, Stock market Integration
    JEL: C19 C49 C58
  8. By: De Bruyckere, Valerie
    Abstract: This paper presents a methodology to calculate the Systemic Risk Ranking of financial institutions in the European banking sector using publicly available information. The pro- posed model makes use of the network structure of financial institutions by including the stock return series of all listed banks in the financial system. Furthermore, a wide set of common risk factors (macroeconomic risk factors, sovereign risk, financial risk and housing price risk) is included to allow these factors to affect the banks. The model uses Bayesian Model Averaging (BMA) of Locally Weighted Regression models (LOESS), i.e. BMA-LOESS. The network structure of the financial sector is analysed by computing measures of network centrality (degree, closeness and betweenness) and it is shown that this information can be used to provide measures of the systemic importance of institutions. Using data from 2005 (2nd quarter) to 2013 (3rd quarter), this paper provides further insight into the time-varying importance of risk factors and it is shown that the model produces superior conditional out-of-sample forecasts (i.e. projections) than a classical linear Bayesian multi-factor model. JEL Classification: C52, C58, G15, G21
    Keywords: bank stock returns, Bayesian model averaging, financial networks, locally weighted regression, systemic risk
    Date: 2015–09
  9. By: M. Bussière; L. Ferrara; J. Milovich
    Abstract: The recent weakness in business investment among advanced economies has revived interest in investment models and opened a debate on the main drivers of the “investment slump” and what the policy response should be – if any. In particular, it is essential to assess precisely whether the investment slump stems mostly from weak aggregate demand, financial constraints or uncertainty, as these different explanatory factors have different policy implications. This paper presents an empirical investigation of the main determinants of business investment for a panel of 22 advanced economies. The main contribution is that we present results from an augmented accelerator model using vintage forecast data as a measure of expected demand and show that this forward-looking variable goes a long way in explaining the weakness in investment since the Global Financial Crisis. Moreover, our results also underline the importance of uncertainty, whereas measures of capital cost seem to play a more modest role. Finally, we show that systematically over-optimistic GDP growth forecasts since 2008 have supported business investment to a large extent.
    Keywords: Business investment, aggregate demand, expectations, uncertainty, financial frictions, macroeconomic forecasts.
    JEL: C23 E22 D84
    Date: 2015

This nep-for issue is ©2015 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.