|
on Forecasting |
| By: | Riza Demirer (Department of Economics and Finance, Southern Illinois University Edwardsville, Edwardsville, USA); Rangan Gupta (Department of Economics, University of Pretoria, Pretoria, South Africa); Christian Pierdzioch (Department of Economics, Helmut Schmidt University, Holstenhofweg 85, Hamburg, Germany) |
| Abstract: | We study the incremental in- and out-of-sample predictive value of time-varying risk aversion for realized volatility of gold-price returns via extended heterogeneous autoregressive realized volatility (HAR-RV) models. Our findings suggest that time varying risk aversion possesses predictive value for gold volatility both in- and out-of-sample. The predictive power of risk aversion is robust to the inclusion of realized higher-moments, jumps, gold returns, leverage effect as well as the aggregate market volatility in the forecasting model. Interestingly, risk aversion is found to absorb in sample the predictive power of stock-market volatility at a short forecasting horizon, while out-of-sample results show that risk aversion adds to predictive value at a medium and long forecast horizon. Additional tests suggest that the short-run (long-run) out-of-sample predictive value of risk aversion is beneficial for investors who are more concerned about over-predicting (under-predicting) gold market volatility. Overall, our findings show that time-varying risk aversion captures information useful for predicting (bad, good) realized volatility not already contained in the other predictors, and allows more accurate out-of-sample forecasts to be computed at a medium and long forecast horizon. |
| Keywords: | Gold-price returns, Realized volatility, Forecasting |
| Date: | 2018–12 |
| URL: | http://d.repec.org/n?u=RePEc:pre:wpaper:201881&r=for |
| By: | Luca Di Bonaventura; Mario Forni; Francesco Pattarin |
| Abstract: | We present a comparative analysis of the forecasting performance of two dynamic factor models, the Stock and Watson (2002a, b) model and the Forni, Hallin, Lippi and Reichlin (2005) model, based on vintage data. Our dataset that contains 107 monthly US “first release” macroeconomic and financial vintage time series, spanning the 1996:12 to 2017:6 period with monthly periodicity, extracted from the Bloomberg database. We compute real-time one-month-ahead forecasts with both models for four key macroeconomic variables: the month-on-month change in industrial production, the unemployment rate, the core consumer price index and the ISM Purchasing Managers’ Index. First, we find that both the Stock and Watson and the Forni, Hallin, Lippi and Reichlin models outperform simple autoregressions for industrial production, unemployment rate and consumer prices, but that only the first model does so for the PMI. Second, we find that neither models always outperform the other. While Forni, Hallin, Lippi and Reichlin’s beats Stock and Watson’s in forecasting industrial production and consumer prices, the opposite happens for the unemployment rate and the PMI. |
| Keywords: | Dynamic factor models, Forecasting, Forecasting Performance, Vintage data, First release data |
| JEL: | C01 C32 C52 C53 E27 E37 |
| Date: | 2018–11 |
| URL: | http://d.repec.org/n?u=RePEc:mod:recent:138&r=for |
| By: | Nava, Noemi; Di Matteo, Tiziana; Aste, Tomaso |
| Abstract: | We introduce a multistep-ahead forecasting methodology that combines empirical mode decomposition (EMD) and support vector regression (SVR). This methodology is based on the idea that the forecasting task is simplified by using as input for SVR the time series decomposed with EMD. The outcomes of this methodology are compared with benchmark models commonly used in the literature. The results demonstrate that the combination of EMD and SVR can outperform benchmark models significantly, predicting the Standard & Poor’s 500 Index from 30 s to 25 min ahead. The high-frequency components better forecast short-term horizons, whereas the low-frequency components better forecast long-term horizons. |
| Keywords: | empirical mode decomposition; support vector regression; forecasting |
| JEL: | G1 G2 |
| Date: | 2018–02–05 |
| URL: | http://d.repec.org/n?u=RePEc:ehl:lserod:91028&r=for |
| By: | Lansing, Kevin J. (Federal Reserve Bank of San Francisco); LeRoy, Stephen F. (UC Santa Barbara); Ma, Jun (Northeastern University) |
| Abstract: | We use a consumption based asset pricing model to show that the predictability of excess returns on risky assets can arise from only two sources: (1) stochastic volatility of model variables, or (2) departures from rational expectations that give rise to predictable investor forecast errors and market inefficiency. From an empirical perspective, we investigate whether 1-month ahead excess returns on stocks can be predicted using measures of consumer sentiment and excess return momentum, while controlling directly and indirectly for the presence of stochastic volatility. A variable that interacts the 12-month sentiment change with recent return momentum is a robust predictor of excess stock returns both in-sample and out-of-sample. The predictive power of this variable derives mainly from periods when sentiment has been declining and return momentum is negative, forecasting a further decline in the excess stock return. We show that the sentiment-momentum variable is positively correlated with fluctuations in Google searches for the term “stock market,” suggesting that the sentiment-momentum variable helps to predict excess returns because it captures shifts in investor attention, particularly during stock market declines. |
| JEL: | E44 G12 |
| Date: | 2018–12–03 |
| URL: | http://d.repec.org/n?u=RePEc:fip:fedfwp:2018-14&r=for |
| By: | David Turner; Thomas Chalaux; Hermes Morgavi |
| Abstract: | This paper describes a method for parameterising fan charts around GDP growth forecasts of the major OECD economies as well as the aggregate OECD. The degree of uncertainty – reflecting the overall spread of the fan chart – is based on past forecast errors, but the skew – reflecting whether risks are tilted to the downside – is derived from a probit model-based assessment of the probability of a future downturn. This approach is applied to each of the G7 countries separately, with combinations of variables found to be useful in predicting future downturns at different horizons up to 8 quarters: at short horizons of 2-4 quarters, a flattening or inverted yield curve slope, recent sharp falls in house prices, share prices or credit; at longer horizons of 6-8 quarters, sustained strong growth in house prices, share prices and credit; and at all horizons, a tight labour market and rapid growth in OECD-wide (or in some cases euro-wide) house prices, share prices or credit. The in-sample fit of the probit models appears reasonably good for all G7 countries. The predicted probabilities from the probit models provide a graduated assessment of downturn risk, which is reflected in the degree of skew in the fan chart. Fan charts computed on an out-of-sample basis around pre-crisis OECD forecasts published in June 2008 encompass the extreme outturns associated with the Global Financial Crisis for five of the G7 countries. A weakness of the approach is that, although it predicts a clear majority of past downturns, it will not predict atypical downturns. For example, in the current conjuncture, it is unlikely that current concerns about risks associated with Brexit, an escalation of trade tensions or spillovers from emerging markets would be picked up by the models. At the same time, a severe downturn triggered by such atypical events might be more severe if more typical risk factors are also high. |
| Keywords: | downturn, economic forecasts, fan charts, recession, risk, uncertainty |
| JEL: | E01 E17 E58 E65 E66 |
| Date: | 2018–12–11 |
| URL: | http://d.repec.org/n?u=RePEc:oec:ecoaaa:1521-en&r=for |
| By: | J. Cerda-Hern\'andez; A. Sikov |
| Abstract: | In this article, we have modeled mortality rates of Peruvian female and male populations during the period of 1950-2017 using the Lee-Carter (LC) model. The stochastic mortality model was introduced by Lee and Carter (1992) and has been used by many authors for fitting and forecasting the human mortality rates. The Singular Value Decomposition (SVD) approach is used for estimation of the parameters of the LC model. Utilizing the best fitted auto regressive integrated moving average (ARIMA) model we forecast the values of the time dependent parameter of the LC model for the next thirty years. The forecasted values of life expectancy at different age group with $95\%$ confidence intervals are also reported for the next thirty years. In this research we use the data, obtained from the Peruvian National Institute of Statistics (INEI). |
| Date: | 2018–11 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:1811.09622&r=for |
| By: | Jaime Martinez-Martin (OECD); Elena Rusticelli (OECD) |
| Abstract: | This paper builds an innovative composite world trade cycle index (WTI) by means of a dynamic factor model to monitor and perform short-term forecasts in real time of world trade growth of both goods and (usually neglected) services. The selection of trade indicator series is made using a multidimensional approach, including Bayesian model averaging techniques, dynamic correlations and Granger non-causality tests in a linear VAR framework. To overcome real-time forecasting challenges, the dynamic factor model is extended to account for mixed frequencies, to deal with asynchronous data publication and to include hard and survey data along with leading indicators. Nonlinearities are addressed with a Markov switching model. Simulations analysis in pseudo real-time suggests that: i) the global trade index is a useful tool to track and forecast world trade in real time; ii) the model is able to infer global trade cycles precisely and better than the few competing alternatives; and iii) global trade finance conditions seem to lead the trade cycle, in line with the theoretical literature. |
| Keywords: | bayesian model averaging, cycles, dynamic factor models, goods trade, granger non-causality, leading indicators, markov switching models, Real-time forecasting, services trade, VAR models, world trade |
| JEL: | C2 E27 E32 |
| Date: | 2018–12–13 |
| URL: | http://d.repec.org/n?u=RePEc:oec:ecoaaa:1524-en&r=for |