Multivariate FIAPARCH modelling of financial markets with dynamic correlations in times of crisis

This paper applies the vector AR-DCC-FIAPARCH model to eight national stock market indices' daily returns from 1988 to 2010, taking into account the structural breaks of each time series linked to the Asian and the recent Global financial crisis. We find significant cross effects, as well as long range volatility dependence, asymmetric volatility response to positive and negative shocks, and the power of returns that best fits the volatility pattern. One of the main findings of the model analysis is the higher dynamic correlations of the stock markets after a crisis event, which means increased contagion effects between the markets. The fact that during the crisis the conditional correlations remain on a high level indicates a continuous herding behaviour during these periods of increased market volatility. Finally, during the recent Global financial crisis the correlations remain on a much higher level than during the Asian financial crisis.

Spatial correlations between beta-amyloid (Abeta) deposits and blood vessels in early-onset Alzheimer's disease

In cases of late-onset Alzheimer’s disease (AD), there is a spatial correlation between the classsic ‘cored’ type of Beta-amyloid (Abeta) deposit and the large vertically penetrating arterioles in the cerebral cortex suggesting that blood vessels are involved in the pathogenesis of the classic deposits. In this chapter, the spatial correlations between the diffuse, primitive, and classic Abeta deposits and blood vessels were studied in 10 cases of early-onset AD in the age range 40 – 65 years. Sections of frontal cortex were immunostained with antibodies against Abeta?and with collagen IV to reveal the Abeta deposits and blood vessel profiles. In the early-onset cases as a whole, all types of Abeta? deposit and blood vessel profiles were distributed in clusters. There was a positive spatial correlation between the clusters of the diffuse Abeta deposits and the larger (>10µm) and smaller diameter (<10?m) blood vessel profiles in one and three cases respectively. The primitive and classic Abeta deposits were spatially correlated with larger and smaller blood vessels both in three and four cases respectively. Spatial correlations between the Abeta deposits and blood vessels may be more prevalent in cases expressing amyloid precursor protein (APP) than presenilin 1 (PSEN1) mutations. Apolipoprotein E (Apo E) genotype of the patient did not appear to influence the spatial correlation with blood vessel profiles. The data suggest that the larger diameter blood vessels are less important in the pathogenesis of the classic Abeta deposits in early-onset compared with late-onset AD.

Modelling conditional probability distributions for periodic variables

Most of the common techniques for estimating conditional probability densities are inappropriate for applications involving periodic variables. In this paper we introduce two novel techniques for tackling such problems, and investigate their performance using synthetic data. We then apply these techniques to the problem of extracting the distribution of wind vector directions from radar scatterometer data gathered by a remote-sensing satellite.

Modelling conditional probability distributions for periodic variables

Most of the common techniques for estimating conditional probability densities are inappropriate for applications involving periodic variables. In this paper we apply two novel techniques to the problem of extracting the distribution of wind vector directions from radar catterometer data gathered by a remote-sensing satellite.

Modelling conditional probability distributions for periodic variables

Most conventional techniques for estimating conditional probability densities are inappropriate for applications involving periodic variables. In this paper we introduce three related techniques for tackling such problems, and investigate their performance using synthetic data. We then apply these techniques to the problem of extracting the distribution of wind vector directions from radar scatterometer data gathered by a remote-sensing satellite.

Estimating conditional probability densities for periodic variables

Most of the common techniques for estimating conditional probability densities are inappropriate for applications involving periodic variables. In this paper we introduce three novel techniques for tackling such problems, and investigate their performance using synthetic data. We then apply these techniques to the problem of extracting the distribution of wind vector directions from radar scatterometer data gathered by a remote-sensing satellite.

Estimating conditional volatility with neural networks

It is well known that one of the obstacles to effective forecasting of exchange rates is heteroscedasticity (non-stationary conditional variance). The autoregressive conditional heteroscedastic (ARCH) model and its variants have been used to estimate a time dependent variance for many financial time series. However, such models are essentially linear in form and we can ask whether a non-linear model for variance can improve results just as non-linear models (such as neural networks) for the mean have done. In this paper we consider two neural network models for variance estimation. Mixture Density Networks (Bishop 1994, Nix and Weigend 1994) combine a Multi-Layer Perceptron (MLP) and a mixture model to estimate the conditional data density. They are trained using a maximum likelihood approach. However, it is known that maximum likelihood estimates are biased and lead to a systematic under-estimate of variance. More recently, a Bayesian approach to parameter estimation has been developed (Bishop and Qazaz 1996) that shows promise in removing the maximum likelihood bias. However, up to now, this model has not been used for time series prediction. Here we compare these algorithms with two other models to provide benchmark results: a linear model (from the ARIMA family), and a conventional neural network trained with a sum-of-squares error function (which estimates the conditional mean of the time series with a constant variance noise model). This comparison is carried out on daily exchange rate data for five currencies.

Robust control of nonlinear stochastic systems by modelling conditional distributions of control signals

We introduce a novel inversion-based neuro-controller for solving control problems involving uncertain nonlinear systems that could also compensate for multi-valued systems. The approach uses recent developments in neural networks, especially in the context of modelling statistical distributions, which are applied to forward and inverse plant models. Provided that certain conditions are met, an estimate of the intrinsic uncertainty for the outputs of neural networks can be obtained using the statistical properties of networks. More generally, multicomponent distributions can be modelled by the mixture density network. In this work a novel robust inverse control approach is obtained based on importance sampling from these distributions. This importance sampling provides a structured and principled approach to constrain the complexity of the search space for the ideal control law. The performance of the new algorithm is illustrated through simulations with example systems.

Conditional distribution modeling for estimating and exploiting uncertainty in control systems

This paper presents a general methodology for estimating and incorporating uncertainty in the controller and forward models for noisy nonlinear control problems. Conditional distribution modeling in a neural network context is used to estimate uncertainty around the prediction of neural network outputs. The developed methodology circumvents the dynamic programming problem by using the predicted neural network uncertainty to localize the possible control solutions to consider. A nonlinear multivariable system with different delays between the input-output pairs is used to demonstrate the successful application of the developed control algorithm. The proposed method is suitable for redundant control systems and allows us to model strongly non Gaussian distributions of control signal as well as processes with hysteresis.

Spatial correlations between the vacuolation, prion protein (PrPsc) deposits and the cerebral blood vessels in sporadic Creutzfeldt-Jakob disease

In the variant form of Creutzfeldt-Jakob disease (vCJD), 'florid' deposits of the protease resistant form of prion protein (PrP(sc)) were aggregated around the cerebral blood vessels suggesting the possibility that prions may spread into the brain via the cerebral microcirculation. The objective of the present study was to determine whether the pathology was spatially related to blood vessels in cases of sporadic CJD (sCJD), a disease without an iatrogenic etiology, and therefore, less likely to be caused by hematogenous spread. Hence, the spatial correlations between the vacuolation ('spongiform change'), PrP(sc) deposits, and the blood vessels were studied in immunolabelled sections of the cerebral cortex and cerebellum in eleven cases of the common M/M1 subtype of sCJD. Both the vacuolation and the PrP(sc) deposits were spatially correlated with the blood vessels; the PrP(sc) deposits being more focally distributed around the vessels than the vacuoles. The frequency of positive spatial correlations was similar in the different gyri of the cerebral cortex, in the upper and lower cortical laminae, and in the molecular layer of the cerebellum. It is hypothesized that the spatial correlation is attributable to factors associated with the blood vessels which promote the aggregation of PrP(sc) to form deposits rather than representing the hematogenous spread of the disease. The aggregated form of PrP(sc) then enhances cell death and may encourages the development of vacuolation in the vicinity of the blood vessels.

Spatial correlations between the vacuolation, prion protein deposits, and surviving neurons in the cerebral cortex in sporadic Creutzfeldt-Jakob disease

In the cerebral cortex of cases of sporadic Creutzfeldt-Jakob disease (sCJD), the vacuolation (spongiform change) and PrP deposits are aggregated into clusters which are regularly distributed parallel to the pia mater. The objective of the present study was to determine the spatial relationships between the clusters of the vacuoles and PrP deposits and between the pathological changes and variations in the density of surviving neurons. In areas with low densities of pathological change, clusters of vacuoles were spatially correlated with the surviving neurons and not with the PrP deposits. By contrast, in more significantly affected areas, clusters of vacuoles were spatially correlated with those of the PrP deposits and not with the surviving neurons. In addition, areas with a high density of vacuoles and a low density of PrP deposits exhibited no spatial correlations between the variables. These data suggest that the spatial relationships between the vacuolation, PrP deposits and surviving neurons in sCJD depend on the density of lesions present. Differences in the pattern of correlation may reflect the developmental stage of the pathology in particular cortical areas.

Using monthly returns to model conditional heteroscedasticity

This empirical study examines the extent of non-linearity in a multivariate model of monthly financial series. To capture the conditional heteroscedasticity in the series, both the GARCH(1,1) and GARCH(1,1)-in-mean models are employed. The conditional errors are assumed to follow the normal and Student-t distributions. The non-linearity in the residuals of a standard OLS regression are also assessed. It is found that the OLS residuals as well as conditional errors of the GARCH models exhibit strong non-linearity. Under the Student density, the extent of non-linearity in the GARCH conditional errors was generally similar to those of the standard OLS. The GARCH-in-mean regression generated the worse out-of-sample forecasts.

Clustering and spatial correlations of the neuronal cytoplasmic inclusions, astrocytic plaques and ballooned neurons in corticobasal degeneration

This study tested three hypotheses: (1) that there is clustering of the neuronal cytoplasmic inclusions (NCI), astrocytic plaques (AP) and ballooned neurons (BN) in corticobasal degeneration (CBD), (2) that the clusters of NCI and BN are not spatially correlated, and (3) that the lesions are correlated with disease ‘stage’. In 50% of the regions, clusters of lesions were 400–800 µm in diameter and regularly distributed parallel to the tissue boundary. Clusters of NCI and BN were larger in laminae II/III and V/VI, respectively. In a third of regions, the clusters of BN and NCI were negatively spatially correlated. Cluster size of the BN in the parahippocampal gyrus (PHG) was positively correlated with disease ‘stage’. The data suggest the following: (1) degeneration of the cortico-cortical pathways in CBD, (2) clusters of NCI and BN may affect different anatomical pathways and (3) BN may develop after the NCI in the PHG.

Spatial correlations between beta-amyloid (A beta) deposits and blood vessels in familial Alzheimer's disease

In sporadic Alzheimer’s disease (SAD), the classic (‘dense-cored’) ß-amyloid (Aß) deposits are aggregated around the larger blood vessels in the upper laminae of the cerebral cortex. To determine whether a similar relationship exists in familial AD (FAD), the spatial correlations between the diffuse, primitive, and classic ß-amyloid (Aß deposits and blood vessels were studied in ten FAD cases including cases linked to amyloid precursor protein (APP) and presenilin (PSEN) gene mutations and expressing apolipoprotein E (apo E) allele E4. Sections of frontal cortex were immunolabelled with antibodies against Aß and with collagen IV to reveal the Aß deposits and blood vessel profiles. In the FAD cases as a whole, Aßdeposits were distributed in clusters. There was a positive spatial correlation between the clusters of the diffuse Aßdeposits and the larger (>10 µm) and smaller diameter (<10 µm) blood vessels in one and three cases respectively. The primitive Aß deposits were spatially correlated with larger and smaller blood vessels each in four cases and the classic deposits in three and four cases respectively. Apo E genotype of the patient did not influence spatial correlation with blood vessels. Hence, spatial correlations between the classic deposits and larger diameter blood vessels were significantly less frequent in FAD compared with SAD. It was concluded that both Aß deposit morphology and AD subtype determine spatial correlations with blood vessels in AD.

Spatial correlations between the vacuolation, prion protein deposition and surviving neurons in variant Creutzfeldt-Jakob Disease (vCJD)

The histological features of cases of variant Creutzfeldt-Jakob disease (vCJD) are often distributed in the brain in clusters. This study investigated the spatial associations between the clusters of the vacuoles, surviving neurons, and prion protein (PrP) deposits in various brain areas in 11 cases of vCJD. Clusters of vacuoles and surviving neurons were positively correlated in the cerebral cortex but negatively correlated in the dentate gyrus. Clusters of the florid and diffuse type of PrP deposit were not positively correlated with those of either the vacuoles or the surviving neurons although a negative correlation was observed between the florid plaques and surviving neurons in some cortical areas. Clusters of the florid and diffuse deposits were either negatively correlated or uncorrelated. These data suggest: 1) that clusters of vacuoles in the cerebral cortex are associated with the presence of surviving neuronal cell bodies, 2) that the clusters of vacuoles are not spatially related to those of the PrP deposits, and 3) different factors are involved in the pathogenesis of the florid and diffuse PrP deposits.