Evaluating multivariate volatility forecasts : how effective are statistical and economic loss functions?

Multivariate volatility forecasts are an important input in many financial applications, in particular portfolio optimisation problems. Given the number of models available and the range of loss functions to discriminate between them, it is obvious that selecting the optimal forecasting model is challenging. The aim of this thesis is to thoroughly investigate how effective many commonly used statistical (MSE and QLIKE) and economic (portfolio variance and portfolio utility) loss functions are at discriminating between competing multivariate volatility forecasts. An analytical investigation of the loss functions is performed to determine whether they identify the correct forecast as the best forecast. This is followed by an extensive simulation study examines the ability of the loss functions to consistently rank forecasts, and their statistical power within tests of predictive ability. For the tests of predictive ability, the model confidence set (MCS) approach of Hansen, Lunde and Nason (2003, 2011) is employed. As well, an empirical study investigates whether simulation findings hold in a realistic setting. In light of these earlier studies, a major empirical study seeks to identify the set of superior multivariate volatility forecasting models from 43 models that use either daily squared returns or realised volatility to generate forecasts. This study also assesses how the choice of volatility proxy affects the ability of the statistical loss functions to discriminate between forecasts. Analysis of the loss functions shows that QLIKE, MSE and portfolio variance can discriminate between multivariate volatility forecasts, while portfolio utility cannot. An examination of the effective loss functions shows that they all can identify the correct forecast at a point in time, however, their ability to discriminate between competing forecasts does vary. That is, QLIKE is identified as the most effective loss function, followed by portfolio variance which is then followed by MSE. The major empirical analysis reports that the optimal set of multivariate volatility forecasting models includes forecasts generated from daily squared returns and realised volatility. Furthermore, it finds that the volatility proxy affects the statistical loss functions’ ability to discriminate between forecasts in tests of predictive ability. These findings deepen our understanding of how to choose between competing multivariate volatility forecasts.

The value of smart metering household electricity consumption

Smart metering presents opportunities for business model creation. However the viability of many potential business models in a smart metering scenario may be dictated by privacy regulation and data sharing arrangements. An understanding by businesses of customers’ preferences for the visualisation of their electricity consumption and the degree to which they are willing to share it, is valuable. We present results from two interviews exploring data visualisation and willingness to share personal electricity consumption information. Participants displayed a high willingness to share and a preference for access to additional information when visualising their electricity consumption.

Integrating electrical vehicles to demand side response scheme in Queensland Australia

Depleting fossil fuel resources and increased accumulation of greenhouse gas emissions are increasingly making electrical vehicles (EV) attractive option for the transportation sector. However uncontrolled random charging and discharging of EVs may aggravate the problems of an already stressed system during the peak demand and cause voltage problems during low demand. This paper develops a demand side response scheme for properly integrating EVs in the Electrical Network. The scheme enacted upon information on electricity market conditions regularly released by the Australian Energy Market Operator (AEMO) on the internet. The scheme adopts Internet relays and solid state switches to cycle charging and discharging of EVs. Due to the pending time-of-use and real-price programs, financial benefits will represent driving incentives to consumers to implement the scheme. A wide-scale dissemination of the scheme is expected to mitigate excessive peaks on the electrical network with all associated technical, economic and social benefits.

Semi-parametric forecasting of realized volatility

Forecasts generated by time series models traditionally place greater weight on more recent observations. This paper develops an alternative semi-parametric method for forecasting that does not rely on this convention and applies it to the problem of forecasting asset return volatility. In this approach, a forecast is a weighted average of historical volatility, with the greatest weight given to periods that exhibit similar market conditions to the time at which the forecast is being formed. Weighting is determined by comparing short-term trends in volatility across time (as a measure of market conditions) by means of a multivariate kernel scheme. It is found that the semi-parametric method produces forecasts that are significantly more accurate than a number of competing approaches at both short and long forecast horizons.

Forecasting volatility and correlation : the role of option implied measures

Forecasts of volatility and correlation are important inputs into many practical financial problems. Broadly speaking, there are two ways of generating forecasts of these variables. Firstly, time-series models apply a statistical weighting scheme to historical measurements of the variable of interest. The alternative methodology extracts forecasts from the market traded value of option contracts. An efficient options market should be able to produce superior forecasts as it utilises a larger information set of not only historical information but also the market equilibrium expectation of options market participants. While much research has been conducted into the relative merits of these approaches, this thesis extends the literature along several lines through three empirical studies. Firstly, it is demonstrated that there exist statistically significant benefits to taking the volatility risk premium into account for the implied volatility for the purposes of univariate volatility forecasting. Secondly, high-frequency option implied measures are shown to lead to superior forecasts of the intraday stochastic component of intraday volatility and that these then lead on to superior forecasts of intraday total volatility. Finally, the use of realised and option implied measures of equicorrelation are shown to dominate measures based on daily returns.

Beyond demand management : the value of sharing electricity information

Technologies such as smart meters and electricity feedback are becoming an increasingly compelling focus for HCI researchers in light of rising power prices and peak demand. We argue, however, that a pre-occupation with the goal of demand management has limited the scope of design for these technologies. In this paper we present our work-in-progress investigating the potential value of socially sharing electricity information as a means of broadening the scope of design for these devices. This paper outlines some preliminary findings gathered from a design workshop and a series of qualitative interviews with householders in Brisbane, Australia, regarding their attitudes towards electricity feedback and sharing consumption information. Preliminary findings suggest that; (1) the social sharing of electricity feedback information has the potential to be of value in better informing consumption decisions, however; (2) the potential for sharing may be constrained by attitudes towards privacy, trust and the possibility of misinformation being shared. We conclude by outlining ideas for our future research on this topic and invite comments on these ideas.

On the efficacy of techniques for evaluating multivariate volatility forecasts

The performance of techniques for evaluating multivariate volatility forecasts are not yet as well understood as their univariate counterparts. This paper aims to evaluate the efficacy of a range of traditional statistical-based methods for multivariate forecast evaluation together with methods based on underlying considerations of economic theory. It is found that a statistical-based method based on likelihood theory and an economic loss function based on portfolio variance are the most effective means of identifying optimal forecasts of conditional covariance matrices.

A method for systematically pooling data in very early stage construction price forecasting

Client owners usually need an estimate or forecast of their likely building costs in advance of detailed design in order to confirm the financial feasibility of their projects. Because of their timing in the project life cycle, these early stage forecasts are characterized by the minimal amount of information available concerning the new (target) project to the point that often only its size and type are known. One approach is to use the mean contract sum of a sample, or base group, of previous projects of a similar type and size to the project for which the estimate is needed. Bernoulli’s law of large numbers implies that this base group should be as large as possible. However, increasing the size of the base group inevitably involves including projects that are less and less similar to the target project. Deciding on the optimal number of base group projects is known as the homogeneity or pooling problem. A method of solving the homogeneity problem is described involving the use of closed form equations to compare three different sampling arrangements of previous projects for their simulated forecasting ability by a cross-validation method, where a series of targets are extracted, with replacement, from the groups and compared with the mean value of the projects in the base groups. The procedure is then demonstrated with 450 Hong Kong projects (with different project types: Residential, Commercial centre, Car parking, Social community centre, School, Office, Hotel, Industrial, University and Hospital) clustered into base groups according to their type and size.

Comparing the availability, price, variety and quality of fruits and vegetables across retail outlets and by area level socioeconomic position

Abstract Objective: To explore whether area-level socioeconomic position or the form of retail stream (conventional versus farmers’ market) are associated with differences in the price, availability, variety and quality of a range of fresh fruit and vegetables. Design: A multi-site cross-sectional pilot study of farmers’ markets, supermarkets and independent fruit and vegetable retailers. Each was surveyed to assess the price, availability, variety and quality of 15 fruit and 18 vegetable items. Setting: Retail outlets were located in South-East Queensland. Subjects: Fifteen retail outlets were surveyed (five of each retail stream). Results: Average basket prices were not significantly different across the socioeconomic spectrum however prices in low socioeconomic areas were cheapest. Availability, variety, and quality did not differ across levels of socioeconomic position however the areas with the most socioeconomic disadvantage scored poorest for quality and variety. Supermarkets had significantly better fruit and vegetable availability than farmers’ markets however price, variety and quality scores were not different across retail streams. Results demonstrate a trend to fruit and vegetable prices being more expensive at farmers’ markets, with the price of the Fruit basket being significantly greater at the organic farmer’s market compared with the non-organic farmers’ markets. Conclusions: Neither area-level socioeconomic position nor the form of retail stream was significantly associated with differences in the availability, price, variety and quality of fruit and vegetables, except for availability which was higher in supermarkets than farmers’ markets. Further research is needed to determine what role farmers’ markets can play in affecting fruit and vegetable intake.

Occupant comfort, the housing industry and electricity infrastructure : understanding the synergies

Despite increasingly stringent energy performance regulations for new homes, southeast Queensland has a high and growing penetration of, and reliance on, air conditioners to provide thermal comfort to housing inhabitants. This reliance impacts on electricity infrastructure investment which is the key driving force behind rising electricity prices. This paper reports initial findings of a research project that seeks to better understand three key issues: (i) how families manage their thermal comfort in summer and how well their homes limit overheating; (ii) the extent to which the homes have been constructed according to the building approval documentation; and (iii) the impact that these issues have on urban design, especially in relation to electricity infrastructure in urban developments.