nep-for New Economics Papers
on Forecasting
Issue of 2016‒10‒23
seven papers chosen by
Rob J Hyndman
Monash University

  1. Point, interval and density forecasts of exchange rates with time-varying parameter models By Abbate, Angela; Marcellino, Massimiliano
  2. Forecasting United States Presidential election 2016 using multiple regression models By Sinha, Pankaj; Nagarnaik, Ankit; Raj, Kislay; Suman, Vineeta
  3. Forecasting 2016 US Presidential Elections Using Factor Analysis and Regression Model By Sinha, Pankaj; Srinivas, Sandeep; Paul, Anik; Chaudhari, Gunjan
  4. Prediction Markets: Reality and Theory By Daniella Acker
  5. Optimal trading policies for wind energy producer By Zongjun Tan; Peter Tankov
  6. Have Standard VARs Remained Stable Since the Crisis? By Aastveit, Knut Are; Carriero, Andrea; Clark, Todd; Marcellino, Massimiliano
  7. Estimation and prediction of an Index of Financial Safety of Tunisia By Matkovskyy, Roman; Bouraoui, Taoufik; Hammami, Helmi

  1. By: Abbate, Angela; Marcellino, Massimiliano
    Abstract: We explore whether modelling parameter time variation improves the point, interval and density forecasts of nine major exchange rates vis-a-vis the US dollar over the period 1976-2015. We fi nd that modelling parameter time variation is needed for an accurate calibration of forecast confi dence intervals, and is better suited at long horizons and in high-volatility periods. The biggest forecast improvements are obtained by modelling time variation in the volatilities of the innovations, rather than in the slope parameters. We do not find evidence that parameter time variation helps to unravel exchange rate predictability by macroeconomic fundamentals. However, an economic evaluation of the diff erent forecast models reveals that controlling for parameter time variation and macroeconomic fundamentals leads to higher portfolios returns, and to higher utility values for investors.
    Date: 2016–10
  2. By: Sinha, Pankaj; Nagarnaik, Ankit; Raj, Kislay; Suman, Vineeta
    Abstract: The paper analyses economic and non-economic factors in order to develop a forecasting model for 2016 US Presidential election and predict it. The discussions on forthcoming US Presidential election mention that campaign fund amount and unemployment will be a deciding factor in the election, but our research indicates that campaign fund amount and unemployment are not significant factors for predicting the vote share of the incumbent party. But in case of non–incumbent major opposition party (challenger party) campaign fund amount does play a role. Apart from unemployment other economic factors such as inflation, exchange rate, interest rate, deficit/surplus, gold prices are also found to be insignificant. Growth of economy is found to be significant factor for non-incumbent major opposition party and not for incumbent party. The study also finds that non-economic factors such as June Gallup rating, Gallup index, average Gallup, power of period factor, military intervention, president running, percentage of white voters and youth voters voting for the party are significant factors for forecasting the vote share of either incumbent party or non-incumbent major opposition party/challenger party. The proposed models forecasts with 95% confidence interval that Democratic party is likely to get vote share of 48.11% with a standard error of ±2.18% and the non-incumbent Republican party is likely to get vote share of 40.26% with a standard error ±2.35%.
    Keywords: Regression model,US Presidential election,economic and non-economic variables,
    JEL: C2 C22 C4 C5
    Date: 2016–07–28
  3. By: Sinha, Pankaj; Srinivas, Sandeep; Paul, Anik; Chaudhari, Gunjan
    Abstract: The paper categorizes factors responsible for forecasting the outcome of U.S. presidential election 2016 using factor analysis, which groups the various economic and non-economic parameters based on the correlation among them. The major economic factor significant in 2016 US presidential election is the growth of the economy, and the ‘anti-incumbency factor that signifies how long the incumbent party has been controlling the White House is found to be an important non-economic factor likely to play a dominant role in the election. The dependent variables considered are the vote shares of the nominees of the incumbent and the non-incumbent majority party candidates. The forecast is calculated by running a regression of the significant factors, obtained through factor analysis technique, on the incumbent party vote share as well as on the non-incumbent party vote share. The proposed models forecast the vote share of Democrat candidate Mrs. Hillary Clinton to be 45.59% with a standard error of ±2.32% and that of Republican candidate Mr. Donald Trump to be 39.51% with a standard error of ±3.87%. Hence, the models built in the paper signal a comfortable margin of victory for the Presidential nominee of the incumbent party, Hillary Clinton. The study re-establishes the notion that the non-economic factors have a greater influence on the outcomes of election as compared to the economic factors, as some of the important economic factors such as inflation and unemployment rate failed to establish their significance.
    Keywords: Factor Analysis, 2016 U.S. Presidential Election, Forecasting, Economic and Non-economic variables
    JEL: C13 C18 C19 C3 C32 C4 C40
    Date: 2016–07–25
  4. By: Daniella Acker
    Abstract: Data on individual trades in prediction markets relating to the 2008 and 2012 US Presidential elections reveal that traders vary enormously in their behavior. This contrasts with the standard prediction-market models, which assume relatively homogeneous participants who differ only in their beliefs and wealth. We show that risk-lovers have particularly strong distortionary effects on market outcomes even when beliefs are symmetrically distributed around the truth. Simulations of a model which allows traders to have different motives and tastes for risk indicate that including such traders produce the market outcomes we observe, such as herding, persistent contrariness, a skewed profits' distribution and favorite-long-shot bias. The attraction of such markets to risk-lovers means that caution must be exercised when using prediction-market prices for forecasting
    Keywords: Prediction markets, risk-lovers, herding and contrariness, favorite-long shot bias.
    JEL: G10 G12 G14 G17
    Date: 2016–10–18
  5. By: Zongjun Tan; Peter Tankov
    Abstract: We study the optimal trading policies for a wind energy producer who aims to sell the future production in the open forward, spot, intraday and adjustment markets, and who has access to imperfect dynamically updated forecasts of the future production. We construct a stochastic model for the forecast evolution and determine the optimal trading policies which are updated dynamically as new forecast information becomes available. Our results allow to quantify the expected future gain of the wind producer and to determine the economic value of the forecasts.
    Date: 2016–09
  6. By: Aastveit, Knut Are; Carriero, Andrea; Clark, Todd; Marcellino, Massimiliano
    Abstract: Small or medium-scale VARs are commonly used in applied macroeconomics for forecasting and evaluating the shock transmission mechanism. This requires the VAR parameters to be stable over the evaluation and forecast sample, or to explicitly consider parameter time variation. The earlier literature focused on whether there were sizable parameter changes in the early 1980s, in either the conditional mean or variance parameters, and in the subsequent period until the beginning of the new century. In this paper we conduct a similar analysis but focus on the effects of the recent crisis. Using a range of techniques, we provide substantial evidence against parameter stability. The evolution of the unemployment rate seems particularly di erent relative to its past behavior. We then discuss and evaluate alternative methods to handle parameter instability in a forecasting context.
    Date: 2016–10
  7. By: Matkovskyy, Roman; Bouraoui, Taoufik; Hammami, Helmi
    Abstract: This paper analyses the strength of the financial system of Tunisia through the construction of an Index of Financial Safety (IFS). Over the period 2000Q1 – 2014Q3, the IFS is built using a wide range of financial and macroeconomic indicators. The empirical results show that it can capture the disturbances in Tunisian financial system with sufficient accuracy. The nonlinear autoregressive with exogenous input (NARX) model with Levenberg-Marquardt algorithm of training was selected to forecast changes in IFS, and provides significant results.
    Keywords: index of financial safety of a country; IFS; nonlinear autoregressive with exogenous input (NARX) model; neural networks
    JEL: C1 C45 C51 C53 G10 G17
    Date: 2015

This nep-for issue is ©2016 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.