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 test, and a modified version of Christoffersen's Markov chain test for independence, and analyse their properties when the financial time series exhibit periodic volatility. These approaches lead to different conclusions when interval forecasts of FTSE100 index futures returns generated by various GARCH(1,1) and periodic GARCH(1,1) models are evaluated.

The effect of (mis-specified) GARCH filters on the finite sample distribution of the BDS test

This paper considers the effect of using a GARCH filter on the properties of the BDS test statistic as well as a number of other issues relating to the application of the test. It is found that, for certain values of the user-adjustable parameters, the finite sample distribution of the test is far-removed from asymptotic normality. In particular, when data generated from some completely different model class are filtered through a GARCH model, the frequency of rejection of iid falls, often substantially. The implication of this result is that it might be inappropriate to use non-rejection of iid of the standardised residuals of a GARCH model as evidence that the GARCH model ‘fits’ the data.

Tests of non-linearity using LIFFE futures transactions price data

This paper presents and implements a number of tests for non-linear dependence and a test for chaos using transactions prices on three LIFFE futures contracts: the Short Sterling interest rate contract, the Long Gilt government bond contract, and the FTSE 100 stock index futures contract. While previous studies of high frequency futures market data use only those transactions which involve a price change, we use all of the transaction prices on these contracts whether they involve a price change or not. Our results indicate irrefutable evidence of non-linearity in two of the three contracts, although we find no evidence of a chaotic process in any of the series. We are also able to provide some indications of the effect of the duration of the trading day on the degree of non-linearity of the underlying contract. The trading day for the Long Gilt contract was extended in August 1994, and prior to this date there is no evidence of any structure in the return series. However, after the extension of the trading day we do find evidence of a non-linear return structure.

Palaeovegetation of China: a pollen data-based synthesis for the mid-Holocene and last glacial maximum.

Pollen data from China for 6000 and 18,000 14C yr bp were compiled and used to reconstruct palaeovegetation patterns, using complete taxon lists where possible and a biomization procedure that entailed the assignment of 645 pollen taxa to plant functional types. A set of 658 modern pollen samples spanning all biomes and regions provided a comprehensive test for this procedure and showed convincing agreement between reconstructed biomes and present natural vegetation types, both geographically and in terms of the elevation gradients in mountain regions of north-eastern and south-western China. The 6000 14C yr bp map confirms earlier studies in showing that the forest biomes in eastern China were systematically shifted northwards and extended westwards during the mid-Holocene. Tropical rain forest occurred on mainland China at sites characterized today by either tropical seasonal or broadleaved evergreen/warm mixed forest. Broadleaved evergreen/warm mixed forest occurred further north than today, and at higher elevation sites within the modern latitudinal range of this biome. The northern limit of temperate deciduous forest was shifted c. 800 km north relative to today. The 18,000 14C yr bp map shows that steppe and even desert vegetation extended to the modern coast of eastern China at the last glacial maximum, replacing today’s temperate deciduous forest. Tropical forests were excluded from China and broadleaved evergreen/warm mixed forest had retreated to tropical latitudes, while taiga extended southwards to c. 43°N.

Present-day and mid-Holocene biomes reconstructed from pollen and plant macrofossil data from the former Soviet Union and Mongolia

Fossil pollen data supplemented by tree macrofossil records were used to reconstruct the vegetation of the Former Soviet Union and Mongolia at 6000 years. Pollen spectra were assigned to biomes using the plant-functional-type method developed by Prentice et al. (1996). Surface pollen data and a modern vegetation map provided a test of the method. This is the first time such a broad-scale vegetation reconstruction for the greater part of northern Eurasia has been attempted with objective techniques. The new results confirm previous regional palaeoenvironmental studies of the mid-Holocene while providing a comprehensive synopsis and firmer conclusions. West of the Ural Mountains temperate deciduous forest extended both northward and southward from its modern range. The northern limits of cool mixed and cool conifer forests were also further north than present. Taiga was reduced in European Russia, but was extended into Yakutia where now there is cold deciduous forest. The northern limit of taiga was extended (as shown by increased Picea pollen percentages, and by tree macrofossil records north of the present-day forest limit) but tundra was still present in north-eastern Siberia. The boundary between forest and steppe in the continental interior did not shift substantially, and dry conditions similar to present existed in western Mongolia and north of the Aral Sea.

Advanced feature selection methods in multinominal dementia classification from structural MRI data

Recent studies showed that features extracted from brain MRIs can well discriminate Alzheimer’s disease from Mild Cognitive Impairment. This study provides an algorithm that sequentially applies advanced feature selection methods for findings the best subset of features in terms of binary classification accuracy. The classifiers that provided the highest accuracies, have been then used for solving a multi-class problem by the one-versus-one strategy. Although several approaches based on Regions of Interest (ROIs) extraction exist, the prediction power of features has not yet investigated by comparing filter and wrapper techniques. The findings of this work suggest that (i) the IntraCranial Volume (ICV) normalization can lead to overfitting and worst the accuracy prediction of test set and (ii) the combined use of a Random Forest-based filter with a Support Vector Machines-based wrapper, improves accuracy of binary classification.

Towards the computer-aided diagnosis of dementia based on the geometric and network connectivity of structural MRI data

We present an intuitive geometric approach for analysing the structure and fragility of T1-weighted structural MRI scans of human brains. Apart from computing characteristics like the surface area and volume of regions of the brain that consist of highly active voxels, we also employ Network Theory in order to test how close these regions are to breaking apart. This analysis is used in an attempt to automatically classify subjects into three categories: Alzheimer’s disease, mild cognitive impairment and healthy controls, for the CADDementia Challenge.

The impact of uncertain precipitation data on insurance loss estimates using a flood catastrophe model

Catastrophe risk models used by the insurance industry are likely subject to significant uncertainty, but due to their proprietary nature and strict licensing conditions they are not available for experimentation. In addition, even if such experiments were conducted, these would not be repeatable by other researchers because commercial confidentiality issues prevent the details of proprietary catastrophe model structures from being described in public domain documents. However, such experimentation is urgently required to improve decision making in both insurance and reinsurance markets. In this paper we therefore construct our own catastrophe risk model for flooding in Dublin, Ireland, in order to assess the impact of typical precipitation data uncertainty on loss predictions. As we consider only a city region rather than a whole territory and have access to detailed data and computing resources typically unavailable to industry modellers, our model is significantly more detailed than most commercial products. The model consists of four components, a stochastic rainfall module, a hydrological and hydraulic flood hazard module, a vulnerability module, and a financial loss module. Using these we undertake a series of simulations to test the impact of driving the stochastic event generator with four different rainfall data sets: ground gauge data, gauge-corrected rainfall radar, meteorological reanalysis data (European Centre for Medium-Range Weather Forecasts Reanalysis-Interim; ERA-Interim) and a satellite rainfall product (The Climate Prediction Center morphing method; CMORPH). Catastrophe models are unusual because they use the upper three components of the modelling chain to generate a large synthetic database of unobserved and severe loss-driving events for which estimated losses are calculated. We find the loss estimates to be more sensitive to uncertainties propagated from the driving precipitation data sets than to other uncertainties in the hazard and vulnerability modules, suggesting that the range of uncertainty within catastrophe model structures may be greater than commonly believed.

Case study on the maintenance of a construction monitoring using USN-based data acquisition

In recent years, there has been an increasing interest in the adoption of emerging ubiquitous sensor network (USN) technologies for instrumentation within a variety of sustainability systems. USN is emerging as a sensing paradigm that is being newly considered by the sustainability management field as an alternative to traditional tethered monitoring systems. Researchers have been discovering that USN is an exciting technology that should not be viewed simply as a substitute for traditional tethered monitoring systems. In this study, we investigate how a movement monitoring measurement system of a complex building is developed as a research environment for USN and related decision-supportive technologies. To address the apparent danger of building movement, agent-mediated communication concepts have been designed to autonomously manage large volumes of exchanged information. In this study, we additionally detail the design of the proposed system, including its principles, data processing algorithms, system architecture, and user interface specifics. Results of the test and case study demonstrate the effectiveness of the USN-based data acquisition system for real-time monitoring of movement operations.

Assessing the sensitivities of a distributed snow model to forcing data resolution

Highly heterogeneous mountain snow distributions strongly affect soil moisture patterns; local ecology; and, ultimately, the timing, magnitude, and chemistry of stream runoff. Capturing these vital heterogeneities in a physically based distributed snow model requires appropriately scaled model structures. This work looks at how model scale—particularly the resolutions at which the forcing processes are represented—affects simulated snow distributions and melt. The research area is in the Reynolds Creek Experimental Watershed in southwestern Idaho. In this region, where there is a negative correlation between snow accumulation and melt rates, overall scale degradation pushed simulated melt to earlier in the season. The processes mainly responsible for snow distribution heterogeneity in this region—wind speed, wind-affected snow accumulations, thermal radiation, and solar radiation—were also independently rescaled to test process-specific spatiotemporal sensitivities. It was found that in order to accurately simulate snowmelt in this catchment, the snow cover needed to be resolved to 100 m. Wind and wind-affected precipitation—the primary influence on snow distribution—required similar resolution. Thermal radiation scaled with the vegetation structure (~100 m), while solar radiation was adequately modeled with 100–250-m resolution. Spatiotemporal sensitivities to model scale were found that allowed for further reductions in computational costs through the winter months with limited losses in accuracy. It was also shown that these modeling-based scale breaks could be associated with physiographic and vegetation structures to aid a priori modeling decisions.

Memo test: standardisation of computerised assessment of auditory verbal short-term memory

Short-term memory (STM) impairments are prevalent in adults with acquired brain injuries. While there are several published tests to assess these impairments, the majority require speech production, e.g. digit span (Wechsler, 1987). This feature may make them unsuitable for people with aphasia and motor speech disorders because of word finding difficulties and speech demands respectively. If patients perceive the speech demands of the test to be high, the may not engage with testing. Furthermore, existing STM tests are mainly ‘pen-and-paper’ tests, which can jeopardise accuracy. To address these shortcomings, we designed and standardised a novel computerised test that does not require speech output and because of the computerised delivery it would enable clinicians identify STM impairments with greater precision than current tests. The matching listening span tasks, similar to the non-normed PALPA 13 (Kay, Lesser & Coltheart, 1992) is used to test short-term memory for serial order of spoken items. Sequences of digits are presented in pairs. The person hears the first sequence, followed by the second sequence and s/he decides whether the two sequences are the same or different. In the computerised test, the sequences are presented in live voice recordings on a portable computer through a software application (Molero Martin, Laird, Hwang & Salis 2013). We collected normative data from healthy older adults (N=22-24) using digits, real words (one- and two-syllables) and non-words (one- and two- syllables). Their performance was scored following two systems. The Highest Span system was the highest span length (e.g. 2-8) at which a participant correctly responded to over 7 out of 10 trials at the highest sequence length. Test re-test reliability was also tested in a subgroup of participants. The test will be available as free of charge for clinicians and researchers to use.

Sample size considerations in active-control non-inferiority trials with binary data based on the odds ratio

This paper presents an approximate closed form sample size formula for determining non-inferiority in active-control trials with binary data. We use the odds-ratio as the measure of the relative treatment effect, derive the sample size formula based on the score test and compare it with a second, well-known formula based on the Wald test. Both closed form formulae are compared with simulations based on the likelihood ratio test. Within the range of parameter values investigated, the score test closed form formula is reasonably accurate when non-inferiority margins are based on odds-ratios of about 0.5 or above and when the magnitude of the odds ratio under the alternative hypothesis lies between about 1 and 2.5. The accuracy generally decreases as the odds ratio under the alternative hypothesis moves upwards from 1. As the non-inferiority margin odds ratio decreases from 0.5, the score test closed form formula increasingly overestimates the sample size irrespective of the magnitude of the odds ratio under the alternative hypothesis. The Wald test closed form formula is also reasonably accurate in the cases where the score test closed form formula works well. Outside these scenarios, the Wald test closed form formula can either underestimate or overestimate the sample size, depending on the magnitude of the non-inferiority margin odds ratio and the odds ratio under the alternative hypothesis. Although neither approximation is accurate for all cases, both approaches lead to satisfactory sample size calculation for non-inferiority trials with binary data where the odds ratio is the parameter of interest.

Probabilistic downscaling of remote sensing data with applications for multi-scale biogeochemical flux modeling

Upscaling ecological information to larger scales in space and downscaling remote sensing observations or model simulations to finer scales remain grand challenges in Earth system science. Downscaling often involves inferring subgrid information from coarse-scale data, and such ill-posed problems are classically addressed using regularization. Here, we apply two-dimensional Tikhonov Regularization (2DTR) to simulate subgrid surface patterns for ecological applications. Specifically, we test the ability of 2DTR to simulate the spatial statistics of high-resolution (4 m) remote sensing observations of the normalized difference vegetation index (NDVI) in a tundra landscape. We find that the 2DTR approach as applied here can capture the major mode of spatial variability of the high-resolution information, but not multiple modes of spatial variability, and that the Lagrange multiplier (γ) used to impose the condition of smoothness across space is related to the range of the experimental semivariogram. We used observed and 2DTR-simulated maps of NDVI to estimate landscape-level leaf area index (LAI) and gross primary productivity (GPP). NDVI maps simulated using a γ value that approximates the range of observed NDVI result in a landscape-level GPP estimate that differs by ca 2% from those created using observed NDVI. Following findings that GPP per unit LAI is lower near vegetation patch edges, we simulated vegetation patch edges using multiple approaches and found that simulated GPP declined by up to 12% as a result. 2DTR can generate random landscapes rapidly and can be applied to disaggregate ecological information and compare of spatial observations against simulated landscapes.

Tests of sunspot number sequences: 3. Effects of regression procedures on the calibration of historic sunspot data

We use sunspot group observations from the Royal Greenwich Observatory (RGO) to investigate the effects of intercalibrating data from observers with different visual acuities. The tests are made by counting the number of groups RB above a variable cut-off threshold of observed total whole-spot area (uncorrected for foreshortening) to simulate what a lower acuity observer would have seen. The synthesised annual means of RB are then re-scaled to the full observed RGO group number RA using a variety of regression techniques. It is found that a very high correlation between RA and RB (rAB > 0.98) does not prevent large errors in the intercalibration (for example sunspot maximum values can be over 30 % too large even for such levels of rAB). In generating the backbone sunspot number (RBB), Svalgaard and Schatten (2015, this issue) force regression fits to pass through the scatter plot origin which generates unreliable fits (the residuals do not form a normal distribution) and causes sunspot cycle amplitudes to be exaggerated in the intercalibrated data. It is demonstrated that the use of Quantile-Quantile (“Q  Q”) plots to test for a normal distribution is a useful indicator of erroneous and misleading regression fits. Ordinary least squares linear fits, not forced to pass through the origin, are sometimes reliable (although the optimum method used is shown to be different when matching peak and average sunspot group numbers). However, other fits are only reliable if non-linear regression is used. From these results it is entirely possible that the inflation of solar cycle amplitudes in the backbone group sunspot number as one goes back in time, relative to related solar-terrestrial parameters, is entirely caused by the use of inappropriate and non-robust regression techniques to calibrate the sunspot data.

The Birmingham Urban Climate Laboratory: an open meteorological test bed and challenges of the smart city

Existing urban meteorological networks have an important role to play as test beds for inexpensive and more sustainable measurement techniques that are now becoming possible in our increasingly smart cities. The Birmingham Urban Climate Laboratory (BUCL) is a near-real-time, high-resolution urban meteorological network (UMN) of automatic weather stations and inexpensive, nonstandard air temperature sensors. The network has recently been implemented with an initial focus on monitoring urban heat, infrastructure, and health applications. A number of UMNs exist worldwide; however, BUCL is novel in its density, the low-cost nature of the sensors, and the use of proprietary Wi-Fi networks. This paper provides an overview of the logistical aspects of implementing a UMN test bed at such a density, including selecting appropriate urban sites; testing and calibrating low-cost, nonstandard equipment; implementing strict quality-assurance/quality-control mechanisms (including metadata); and utilizing preexisting Wi-Fi networks to transmit data. Also included are visualizations of data collected by the network, including data from the July 2013 U.K. heatwave as well as highlighting potential applications. The paper is an open invitation to use the facility as a test bed for evaluating models and/or other nonstandard observation techniques such as those generated via crowdsourcing techniques.