|
on Forecasting |
| By: | Edoardo Otranto |
| Abstract: | Forecasting volatility in a multivariate framework has received many contributions in the recent literature, but problems in estimation are still frequently encountered when dealing with a large set of time series. The Dynamic Conditional Correlation (DCC) modeling is probably the most used approach; it has the advantage of separating the estimation of the volatility of each time series (with great flexibility, using single univariate models) and the correlation part (with the strong constraint imposing the same dynamics to all the correlations). We propose a modification to the DCC model, providing different dynamics for each correlation, simply hypothesizing a dependence on the volatility structure of each time series. This new model implies adding only two parameters with respect to the original DCC model. Its performance is evaluated in terms of out-of-sample forecasts with respect to the DCC models and other multivariate GARCH models. The results on four data sets seem to favor the new model. |
| Keywords: | Dynamic conditional correlation; GARCH distance; Multivariate |
| JEL: | C32 C53 G10 |
| Date: | 2009 |
| URL: | http://d.repec.org/n?u=RePEc:cns:cnscwp:200917&r=for |
| By: | Massimiliano Caporin (Università di Padova); Juliusz Pres (Szczecin University of Technology) |
| Abstract: | The modelling of wind speed is a traditional topic in meteorological research, where the main interest is on the short-term forecast of wind speed intensity and direction. More recently, this theme has received some interest in the quantitative finance literature for its relationship with electricity production by wind farms. In fact, electricity producers are interested in long-range forecasts and simulation of wind speed for two main reasons: to evaluate the profitability of building a wind farm in a given location and to offset the risks associated with the variability of wind speed for an already operating wind farm. In this paper, we contribute to the increasing literature regarding environmental finance by comparing three approaches that are capable of forecasting and simulating the long run evolution of wind speed intensity (direction is not a concern, given that the recent turbines can rotate to follow wind direction): the Auto Regressive Gamma process, the Gamma Auto Regressive process, and the ARFIMA-FIGARCH model. We provide both in-sample and out-of-sample comparisons of the models, as well as some examples for the pricing of wind speed derivatives using a model-based Monte Carlo simulation approach. |
| Keywords: | Gamma Auto Regressive, Auto Regressive Gamma, ARFIMA-FIGARCH, wind speed modelling, wind speed simulation |
| JEL: | C22 C53 G13 G22 |
| Date: | 2010–01 |
| URL: | http://d.repec.org/n?u=RePEc:pad:wpaper:0106&r=for |
| By: | Su, Dongwei; He, Xingxing |
| Abstract: | This paper combines artificial neural networks (ANN), fuzzy optimization and time-series econometric models in one unified framework to form a hybrid intelligent early warning system (EWS) for predicting economic crises. Using quarterly data on 12 macroeconomic and financial variables for the Chinese economy during 1999 and 2008, the paper finds that the hybrid model possesses strong predictive power and the likelihood of economic crises in China during 2009 and 2010 remains high. |
| Keywords: | Computational intelligence; artificial neural networks; fuzzy optimization; early warning system; economic crises |
| JEL: | C53 E17 |
| Date: | 2010–01–11 |
| URL: | http://d.repec.org/n?u=RePEc:pra:mprapa:19962&r=for |
| By: | Fabian Garavito |
| Abstract: | I document how the organizational form of a mutual fund affects its investment strategies. I show that centralized funds tilt their portfolios to hard information companies whereas decentralized funds tilt their portfolios to soft information companies. I also show that the investments of decentralized (centralized) mutual funds in soft (hard) information companies outperform those of centralized (decentralized) funds. Moreover, decentralized funds show ability to forecast soft information companies' future returns and a disability at forecasting hard information companies' future returns. On the other hand, centralized funds do not seem to be able to forecast the returns of hard information companies, but they show disability at forecasting hard information companies' future returns. The results corroborate the main predictions of Stein (2002). The results also shed light on the increase in demand for large stocks and the positive relationship between performance of portfolio concentration documented in the literature. |
| Date: | 2009–08 |
| URL: | http://d.repec.org/n?u=RePEc:fmg:fmgdps:dp638&r=for |