Fengbin Lu

This paper proposes a new time-varying parameter distributed lag (DL) model. In contrast to the existing methods, which assume parameters to be random walks or regime shifts, our method allows time-varying coefficients of lagged explanatory variables to be conditional on past information. Furthermore, a test for constant-parameter DL model is introduced. The model is then applied to examine time-varying causal effect of inventory on crude oil price and forecast weekly crude oil price. Time-varying causal effect of US commercial crude oil inventory on crude oil price return is presented. In particular, the causal effect of inventory is occasionally positive, which is contrary to some previous research. It's also shown that the proposed model yields the best in and out-of-sample performances compared to seven alternative models including RW, ARMA, VAR, DL, autoregressive-distributed lag (ADL), time-varying parameter ADL (TVP-ADL) and DCB (dynamic conditional beta) models.

Stock e-exchange prices forecasting is an important financial problem that is receiving increasing attention. This study proposes a novel three-stage nonlinear ensemble model. In the proposed model, three different types of neural-network based models, i.e. Elman network, generalized regression neural network (GRNN) and wavelet neural network (WNN) are constructed by three non-overlapping training sets and are further optimized by improved particle swarm optimization (IPSO). Finally, a neural-network-based nonlinear meta-model is generated by learning three neural-network based models through support vector machines (SVM) neural network. The superiority of the proposed approach lies in its flexibility to account for potentially complex nonlinear relationships. Three daily stock indices time series are used for validating the forecasting model. Empirical results suggest the ensemble ANNs-PSO-GA approach can significantly improve the prediction performance over other individual models and linear combination models listed in this study.