I am a student at School of Mathematics and Statistics and also at the Faculty of Business and Economics, University of Melbourne. My main research interest is in the application of Mathematics in Economics and Finance. However, I am new and thus open to every possibility. I am currently working on a road pricing project, which involves both stochastic modelling and market design. This summer, my supervisor Dr Laleh Tafakori and I will research on a state space model to improve the current forecasting of Realised Variance in financial markets.
Forecasting of Realised Variance Measure
Modelling- and forecasting-realised volatility plays an indispensable role for option pricing, portfolio allocation and risk management. The existing models for realised volatility may perform well in-sample but in general their out-of-sample forecasts are often biased. We aim to build a model for realised volatility with improved forecasting performance by accounting for the fact that that multivariate realised covariances are only estimates of the true variance and by introducing time varying parameters. With its more accurate forecasting, our model holds the promise to empirically more accurate pricing models and improved financial decision-making. In estimating the model parameters, we will apply the standardised self-perturbed Kalman Filter, which performs very well in estimating state space models in terms of accuracy and efficiency. After that, we will report the forecasting performance of the competing models and look at the improvement in model fit of this new approach using other benchmark models.