Vlasios Voudouris

Flexible Regression and Smoothing: Using GAMLSS in R

This book is about learning from data using the Generalized Additive Models for Location, Scale and Shape (GAMLSS). GAMLSS extends the Generalized Linear Models (GLMs) and Generalized Additive Models (GAMs) to accommodate large complex datasets, which are increasingly prevalent. In particular, the GAMLSS statistical framework enables flexible regression and smoothing models to be fitted to the data. The GAMLSS model assumes that the response variable has any parametric (continuous, discrete or mixed) distribution which might be heavy- or light-tailed, and positively or negatively skewed. In addition, all the parameters of the distribution (location, scale, shape) can be modelled as linear or smooth functions of explanatory variables.

Global energy policy and security

Energy Policy And Security Through The Lenses Of The Stochastic Portfolio Theory And The ACEGES Model.- Energy Security As A Subset Of National Security.- Challenges To Global Energy Policy And Supply Security.- Change In Energy Structure And Energy Security Under Climate Mitigation Scenarios.- Insights On Cooperative Electricity Consumption In Human Aggregates From A Thermodynamic Analysis: Implications For Energy Policies.- The UK Electricity System And Its Resilience.- The Macroeconomic Effects Of Energy Purchases.- EUs Dynamic Evaluation of Energy Efficiency: Combining Data Envelopment Analysis and Multicriteria Decision Making.- The Availability Of European Oil And Gas Resources.- Energy Security: Stochastic Analysis Of Oil Prices.- Green Energy Development in China: The Case of Clean Coal Technologies.- Chinas New Energy Security: A Swing of the Pendulum.- The Energy Efficiency Policy Initiatives and Energy Security: Experiences from India.- Impact of Shocks on Australian Coal Mining.- An Assessment of the Impacts of Government Energy Policy on Energy Technology Innovation and Security: The Case of Renewable Technologies in the US Electricity Sector.- An Overview of Energy Policy and Security in the Pacific Region.- The Evolution of the Spanish Energy System in the Context of Energy Security: Current Trends, Future Developments.- Energy, Development and Economic Growth in Colombia.

Oil scenarios for long-term business planning: Royal Dutch Shell and generative explanation, 1960-2010

Most executives know that overarching paints of plausible futures will profoundly affect the competitiveness and survival of their organisation. Initially from the perspective of Shell, this article discuses oil scenarios and their relevance for upstream investments. Scenarios are then incorporated into generative explanation and its principal instrument, namely agent-based computational laboratories, as the new standard of explanation of the past and the present and the new way to structure the uncertainties of the future. The key concept is that the future should not be regarded as ‘complicated’ but as ‘complex’, in that there are uncertainties about the driving forces that generate unanticipated futures, which cannot be explored analytically.

Collaborative geovisualization: object-field representations with semantic and uncertainty information

Techniques and issues for the characterisation of an object-field representation that includes notions of semantics and uncertainty are detailed. The purpose of this model is to allow users to capture objects in field with internally variable levels of uncertainty, to visualize users’ conceptualizations of those geographic domains, and to share their understanding with others using embedded semantics. Concepts from collaborative environments inform the development of this semantic-driven model as well as the importance of presenting all collaborators’ analysis in a way that enables them to fully communicate their views and understandings about the object and the field within it. First, a conceptual background is provided which briefly addresses collaborative environments and the concepts behind an object-field representation. Second, implementation of that model within a database is discussed. Finally, a LandCover example is presented as a way of illustrating the applicability of the semantic model.

Beyond Location and Dispersion Models: The Generalized Structural Time Series Model with Applications

In many settings of empirical interest, time variation in the distribution parameters is important for capturing the dynamic behaviour of time series processes. Although the fitting of heavy tail distributions has become easier due to computational advances, the joint and explicit modelling of time-varying conditional skewness and kurtosis is a challenging task. We propose a class of parameter-driven time series models referred to as the generalized structural time series (GEST) model. The GEST model extends Gaussian structural time series models by a) allowing the distribution of the dependent variable to come from any parametric distribution, including highly skewed and kurtotic distributions (and mixed distributions) and b) expanding the systematic part of parameter-driven time series models to allow the joint and explicit modelling of all the distribution parameters as structural terms and (smoothed) functions of independent variables. The paper makes an applied contribution in the development of a fast local estimation algorithm for the evaluation of a penalised likelihood function to update the distribution parameters over time \textit{without} the need for evaluation of a high-dimensional integral based on simulation methods.

Unconventional Oil: Will It Satisfy Future Global Oil Demand?

The role of unconventional resources (e.g., oil sands and extra-heavy oil) is anticipated to increase in the global oil market. Although we are facing a scarcity of conventional (low cost) oil resources, unconventional oil resources might manage (for a period of time) to supply constraints in terms of meeting expected increases in oil demand. Here, we use the ACEGES (Agent-based Computational Economics of the Global Energy System) model to investigate the potential impact of unconventional oil resources on the future evolution of the oil market on a global scale. The key assumption of the model is that technological improvements will allow unconventional oil production to increase at a rate similar to the rate of production of the conventional oil resources. An important observation from the ACEGES-based simulations is the significant shift of the peak production of oil (both conventional and unconventional) if and only if technological progress will allow upstream extraction rates for unconventional resources, similar to the historic extraction rates of conventional oil. Given the estimated potential of total oil resources, the ACEGES-based scenario suggests that the unconventional oil production may shift the peak year of total oil by 60 years or more, assuming favourable upstream investment plans and a continuous increase in the demand for crude oil products at a reasonable price. However, increased total oil production might not meet the unconstrained (high) growth rates of oil demand.

Forecasting Film Revenues Using GAMLSS

This paper utilises the GAMLSS framework for the statistical modelling of movie box-office revenues. The dominant modelling paradigm of the film industry, traditionally exemplified by the nobody knows principle is based upon the infinite variance of the Pareto distribution. Using GAMLSS we have the flexibility to model up to 4 parameters of any distribution in terms of the avail- able explanatory variates, including a predictor that has smooth non-parametric functions. We here show that total box-office revenue can be better modelled by distributions with finite variance contradicting the Paretian hypothesis. Moreover the final version of the paper will illustrate that the Box-Cox power exponential distribution gives models where the parameters vary smoothly with an important explanatory variable, leading to the substantive conclusion that the post-opening revenue can, in fact, be explained by the opening box-office

Energy Policy and Security Through the Lenses of Stochastic Portfolio Theory and the ACEGES Model

Purpose The chapter presents a new approach to address energy policy and security based upon the ACEGES (Agent-based Computational Economics of the Global Energy System) model and the SPT (stochastic portfolio theory).

Estimation of Nonparametric Density from Sparse Summary Information: Densities of Undiscovered Oil

Information on observable economic and financial variables is sometimes limited to summary form. Therefore, in many practical situations, it is desirable to restrict the flexibility of nonparametric density estimators to accommodate information about the summary data as well as any prior information about the nature of the problem. Our nonparametric estimator is easy to implement and has an explicit algebraic structure. The motivation for this letter is the generation of non-parametric densities from sparse summary data rather than from individual observations.

Estimation of Non-Parametric Regression Models: Production Profiles of Crude Oil

In many practical statistical situations, it is desirable to restrict the flexibility of nonparametric regression models to accommodate prior information. We propose an estimator for regression models with a smoothness penalty and constraints imposed by the nature of the problem. Our estimator is easy to implement and has an explicit algebraic structure. Alternative or additional constraints can be readily applied. We present production profiles of crude oil to demonstrate possible uses of the proposed estimator.