A flexible extreme value mixture model

Extreme value theory is used to derive asymptotically motivated models for unusual or rare events, e.g. the upper or lower tails of a distribution. A new flexible extreme value mixture model is proposed combining a non-parametric kernel density estimator for the bulk of the distribution with an appropriate tail model. The complex uncertainties associated with threshold choice are accounted for and new insights into the impact of threshold choice on density and quantile estimates are obtained. Bayesian inference is used to account for all uncertainties and enables inclusion of expert prior information, potentially overcoming the inherent sparsity of extremal data. A simulation study and empirical application for determining normal ranges for physiological measurements for pre-term infants is used to demonstrate the performance of the proposed mixture model. The potential of the proposed model for overcoming the lack of consistency of likelihood based kernel bandwidth estimators when faced with heavy tailed distributions is also demonstrated.     

GARCH dependence in extreme value models with Bayesian inference

Extreme value methods are widely used in financial applications such as risk analysis, forecasting and pricing models. One of the challenges with their application in finance is accounting for the temporal dependence between the observations, for example the stylised fact that financial time series exhibit volatility clustering. Various approaches have been proposed to capture the dependence. Commonly a two-stage approach is taken, where the volatility dependence is removed using a volatility model like a GARCH (or one of its many incarnations) followed by application of standard extreme value models to the assumed independent residual innovations.This study examines an alternative one stage approach, which makes parameter estimation and accounting for the associated uncertainties more straightforward than the two-stage approach. The location and scale parameters of the extreme value distribution are defined to follow a conditional autoregressive heteroscedasticity process. Essentially, the model implements GARCH volatility via the extreme value model parameters. Bayesian inference is used and implemented via Markov chain Monte Carlo, to permit all sources of uncertainty to be accounted for. The model is applied to both simulated and empirical data to demonstrate performance in extrapolating the extreme quantiles and quantifying the associated uncertainty.     

Organization of design and development

This paper makesuse of the author's practical experience with innovation in engineering design to examine the organization of design and development. His approach is that of a designer, looking at the business environment and the role of product innovation and enhancement in mature and young industries. A human organization is regarded as a (designable) information system.     

The influence of tensile strain on differential gain and Augerrecombination in 1.5-μm multiple-quantum-well lasers

A systematic study has been undertaken including growth, characterization, and modeling of tensile-strained multiple-quantum-well (MQW) lasers with emission wavelengths in the neighborhood of 1.5 μm. The laser threshold increases between 0% and -0.5% mismatch, switching from TE to TM polarized emission at -0.5%, then decreases to -1.3 % mismatch, with TM polarized emission. The threshold current density has a much weaker dependence on inverse cavity length in the highly tensile-strained lasers than has previously been observed for lattice-matched and compressive lasers emitting in the same wavelength range. We present theoretical calculations which show that the observed differences are well explained, both qualitatively and quantitatively, by the calculated variation with strain of the optical confinement factor Γ and the differential gain at transparency, dg/dn (n_tr). More detailed comparison with experiment suggests that Auger recombination provides the dominant contribution to the threshold current density. Estimated Auger coefficients C are in good agreement with those previously obtained using other techniques     

Spatial multi-taper spectrum estimation for nuclear reactor modelling

Multi-taper univariate and cross-spectral analysis is used to investigate the structure of spatial variation in the temperatures measured across the surface of a nuclear reactor. The construction of the spatial tapers over the approximate circular reactor surface is described, along with derivation and sampling properties of the spectral estimates. It is shown how the analysis can be used to identify regular patterns in the temperature measurements, and the spatial transfer function between the reactor temperatures and fuel characteristics. The results are used to specify a parametric regression model for the temperature measurements.     

The storage complex considered as a system component

To permit further growth in the application of information systems, the lower level activities must be automated so that they cease to be a burden on the user. A synthesis of known hardware devices and software algorithms for dynamic storage allocation is advocated which can achieve acceptable efficiency at run time by using the explicitly defined data structure as a basis for store management and the prediction of store usage. The resultant automated storage complex also provides security against the propagation of consequential software failures. Consideration of the function of the individual storage devices which would be components of such a storage complex leads to some conclusions which may be useful for guiding the development of advanced storage devices.     

Water Supply and Demand Balances: Converting Uncertainty Into Headroom

This paper reports on research into the development of a standard procedure for calculating headroom. Headroom is a legitimate planning allowance to account for uncertainties in the supply/demand balance in a water-resource plan. Prior to this research, the UK water industry did not have an agreed method for calculating headroom, which resulted in inconsistencies in regulatory submissions. The research built on previous studies to define an approach that would be practical and easy to apply. A pragmatic methodology using a series of forms with clear guidelines was developed. The methodology has been applied in the 1998 supply/demand balance submissions to the regulatory authorities as part of the Asset Management Plan 3 periodic review.