Evaluating multivariate volatility forecasts

On the efficacy of techniques for evaluating multivariate volatility forecasts

The performance of techniques for evaluating univariate volatility forecasts are well understood. In the multivariate setting however, the efficacy of the evaluation techniques is not developed. Multivariate forecasts are often evaluated within an economic application such as portfolio optimisation context. This paper aims to evaluate the efficacy of such techniques, along with traditional stat...

Master Thesis Evaluating Switching GARCH Volatility Forecasts During the Recent Financial Crisis

Joint forecasts of Dow Jones stocks under general multivariate loss function

When forecasts are assessed by a general loss (cost-of-error) function, the optimal point forecast is not, in general, the conditional mean, and depends on the conditional volatility – which, for stock returns, is time-varying. Our aim is to provide forecasts of daily returns of 30 DJIA stocks under a general multivariate loss function. The paper’s contributions are as follows. We discuss what ...

Evaluating interval forecasts of high-frequency financial data

A number of methods of evaluating the validity of interval forecasts of financial data are analysed, and illustrated using intraday FTSE100 index futures returns. Some existing interval forecast evaluation techniques, such as the Markov chain approach of Christoffersen (1998), are shown to be inappropriate in the presence of periodic heteroscedasticity. Instead, we consider a regression-based t...

The economic value of volatility forecasts: A conditional approach∗

This paper provides an investigation of the economic value of multivariate volatility forecasting ability using a testing framework in which the quality of competing methods is assessed from a conditional investment perspective. In doing this we are able to provide a novel means by which the benefits of using a particular set of volatility forecasts can be assessed. The results associated with ...