Estimation of State Space Models and Stochastic Volatility

Ma thèse est composée de trois chapitres reliés à l'estimation des modèles espace-état et volatilité stochastique. Dans le première article, nous développons une procédure de lissage de l'état, avec efficacité computationnelle, dans un modèle espace-état linéaire et gaussien. Nous montrons comment exploiter la structure particulière des modèles espace-état pour tirer les états latents efficacement. Nous analysons l'efficacité computationnelle des méthodes basées sur le filtre de Kalman, l'algorithme facteur de Cholesky et notre nouvelle méthode utilisant le compte d'opérations et d'expériences de calcul. Nous montrons que pour de nombreux cas importants, notre méthode est plus efficace. Les gains sont particulièrement grands pour les cas où la dimension des variables observées est grande ou dans les cas où il faut faire des tirages répétés des états pour les mêmes valeurs de paramètres. Comme application, on considère un modèle multivarié de Poisson avec le temps des intensités variables, lequel est utilisé pour analyser le compte de données des transactions sur les marchés financières. Dans le deuxième chapitre, nous proposons une nouvelle technique pour analyser des modèles multivariés à volatilité stochastique. La méthode proposée est basée sur le tirage efficace de la volatilité de son densité conditionnelle sachant les paramètres et les données. Notre méthodologie s'applique aux modèles avec plusieurs types de dépendance dans la coupe transversale. Nous pouvons modeler des matrices de corrélation conditionnelles variant dans le temps en incorporant des facteurs dans l'équation de rendements, où les facteurs sont des processus de volatilité stochastique indépendants. Nous pouvons incorporer des copules pour permettre la dépendance conditionnelle des rendements sachant la volatilité, permettant avoir différent lois marginaux de Student avec des degrés de liberté spécifiques pour capturer l'hétérogénéité des rendements. On tire la volatilité comme un bloc dans la dimension du temps et un à la fois dans la dimension de la coupe transversale. Nous appliquons la méthode introduite par McCausland (2012) pour obtenir une bonne approximation de la distribution conditionnelle à posteriori de la volatilité d'un rendement sachant les volatilités d'autres rendements, les paramètres et les corrélations dynamiques. Le modèle est évalué en utilisant des données réelles pour dix taux de change. Nous rapportons des résultats pour des modèles univariés de volatilité stochastique et deux modèles multivariés. Dans le troisième chapitre, nous évaluons l'information contribuée par des variations de volatilite réalisée à l'évaluation et prévision de la volatilité quand des prix sont mesurés avec et sans erreur. Nous utilisons de modèles de volatilité stochastique. Nous considérons le point de vue d'un investisseur pour qui la volatilité est une variable latent inconnu et la volatilité réalisée est une quantité d'échantillon qui contient des informations sur lui. Nous employons des méthodes bayésiennes de Monte Carlo par chaîne de Markov pour estimer les modèles, qui permettent la formulation, non seulement des densités a posteriori de la volatilité, mais aussi les densités prédictives de la volatilité future. Nous comparons les prévisions de volatilité et les taux de succès des prévisions qui emploient et n'emploient pas l'information contenue dans la volatilité réalisée. Cette approche se distingue de celles existantes dans la littérature empirique en ce sens que ces dernières se limitent le plus souvent à documenter la capacité de la volatilité réalisée à se prévoir à elle-même. Nous présentons des applications empiriques en utilisant les rendements journaliers des indices et de taux de change. Les différents modèles concurrents sont appliqués à la seconde moitié de 2008, une période marquante dans la récente crise financière.

Doppler vortography : detection and quantification of the vortices in the left ventricle

Nous proposons une nouvelle méthode pour quantifier la vorticité intracardiaque (vortographie Doppler), basée sur l’imagerie Doppler conventionnelle. Afin de caractériser les vortex, nous utilisons un indice dénommé « Blood Vortex Signature (BVS) » (Signature Tourbillonnaire Sanguine) obtenu par l’application d’un filtre par noyau basé sur la covariance. La validation de l’indice BVS mesuré par vortographie Doppler a été réalisée à partir de champs Doppler issus de simulations et d’expériences in vitro. Des résultats préliminaires obtenus chez des sujets sains et des patients atteints de complications cardiaques sont également présentés dans ce mémoire. Des corrélations significatives ont été observées entre la vorticité estimée par vortographie Doppler et la méthode de référence (in silico: r2 = 0.98, in vitro: r2 = 0.86). Nos résultats suggèrent que la vortographie Doppler est une technique d’échographie cardiaque prometteuse pour quantifier les vortex intracardiaques. Cet outil d’évaluation pourrait être aisément appliqué en routine clinique pour détecter la présence d’une insuffisance ventriculaire et évaluer la fonction diastolique par échocardiographie Doppler.

Mixed layer characteristics and hydrography off the west and east coasts of India

In this thesis, a detailed attempt has been made to understand the general hydrography of the upper 300m of the water column, in the eastern Arabian Sea and the western Bay of Bengal, the two contrasting basins in the northern Indian Ocean, using recently collected data sets of Marine Research-Living Resources (MR-LR) assessment programme, funded by Department of Ocean Development, from various cruises, pertaining to different seasons. Initially it discuss the general hydrography of the west and east coasts of India are covered, in the context of mixed layer processes. The study describes the materials and methods . To compare the hydrography of the AS and BOB, a unique MLD(Mixed Layer Depth) definition for AS and BOB is essential, for which the 275 CTD profiles were used. A comparison has been made among the various MLD criteria with the actual MLD. The monthly evolution of MLD, barrier layer thickness and the role of atmospheric forcing on the dynamics of the mixed layer in the AS and BOB were studied. The general hydrography along the west coast of India is described. The upwelling/downwelling, winter cooling processes, in the context of chemical and biological parameters, are also addressed. Finally the general hydrography of the Bay of Bengal is covered. The most striking feature in the hydrography are the signature of an anticyclonic subtropical gyre during spring intermonsoon and a cold core eddy during winter monsoon. The TTS(Typical Tropical Structure) of the euphotic layer was also investigated.

Studies on the Effect of High Energy Ball Milling On the Structural, Electrical and Magnetic Properties of Some Normal Spinets in the Ultrafine Regime

The present work is an attempt to understand the characteristics of high energy ball milling on the structural, electrical and magnetic properties of some normal spinets in the ultra fine regime, Magnetism and magnetic materials have been a fascinating subject for the mankind ever since the discovery of lodestone. Since then, man has been applying this principle of magnetism to build devices for various applications. Magnetism can be classified broadly into five categories. They are diamagnetic, paramagnetic, ferromagnetic antiferromagnetic and ferrimagnetic. Of these, ferro and ferri magnetic materials assume great commercial importance due to their unique properties like appropriate magnetic characteristics, high resistivity and low eddy current losses. The emergence of nanoscience and nanotechnology during the last decade had its impact in the field of magnetism and magnetic materials too. Now, it is common knowledge that materials synthesized in the nanoregime exhibit novel and superlative properties with respect to their coarser sized counterparts in the micron regime. These studies reveal that dielectric properties can be varied appreciably by high-energy ball milling in nanosized zinc ferrites produced by coprecipitation method. A semi conducting behaviour was observed in these materials with the Oxygen vacancies acting as the main charge carrier for conduction, which was produced at the time of coprecipitation and milling. Thus through this study, it was possible to successfully investigate the finite size effects on the structural, electrical and magnetic properties of normal spinels in the ultra fine regime

Fabrication and characterisation of polymer optical fibers for smart sensing and optical amplification

The thesis presented the fabrication and characterisation of polymer optical fibers in their applications as optical amplifier and smart sensors.Optical polymers such as PMMA are found to be a very good host material due to their ability to incorporate very high concentration of optical gain media like fluorescent dyes and rare earth compounds. High power and high gain optical amplification in organic dye-doped polymer optical fibers is possible due to extremely large emission cross sections of oyes. Dye doped (Rhodamine 6G) optical fibers were fabricated by using indigenously developed polymer optical fiber drawing tower. Loss characterization of drawn dye doped fibers was carried out using side illumination technique. The advantage of the above technique is that it is a nondestructive method and can also be used for studying the uniformity in fiber diameter and doping. Sensitivity of the undoped polymer fibers to temperature and microbending were also studied in its application in smart sensors.Optical amplification studies using the dye doped polymer optical fibers were carried out and found that an amplification of l8dB could be achieved using a very short fiber of length lOcm. Studies were carried out in fibers with different dye concentrations and diameter and it was observed that gain stability was achieved at relatively high dye concentrations irrespective of the fiber diameter.Due to their large diameter, large numerical aperture, flexibility and geometrical versatility of polymer optical fibers it has a wide range of applications in the field of optical sensing. Just as in the case of conventional silica based fiber optic sensors, sensing techniques like evanescent wave, grating and other intensity modulation schemes can also be efficiently utilized in the case of POF based sensors. Since polymer optical fibers have very low Young's modulus when compared to glass fibers, it can be utilized for sensing mechanical stress and strain efficiently in comparison with its counterpart. Fiber optic sensors have proved themselves as efficient and reliable devices to sense various parameters like aging, crack formation, weathering in civil structures. A similar type of study was carried out to find the setting characteristics of cement paste used for constructing civil structures. It was found that the measurements made by using fiber optic sensors are far more superior than that carried out by conventional methods. More over,POF based sensors were found to have more sensitivity as well.

Modeling and Analysis of Some Heavy Tailed Time Series

The thesis has covered various aspects of modeling and analysis of finite mean time series with symmetric stable distributed innovations. Time series analysis based on Box and Jenkins methods are the most popular approaches where the models are linear and errors are Gaussian. We highlighted the limitations of classical time series analysis tools and explored some generalized tools and organized the approach parallel to the classical set up. In the present thesis we mainly studied the estimation and prediction of signal plus noise model. Here we assumed the signal and noise follow some models with symmetric stable innovations.We start the thesis with some motivating examples and application areas of alpha stable time series models. Classical time series analysis and corresponding theories based on finite variance models are extensively discussed in second chapter. We also surveyed the existing theories and methods correspond to infinite variance models in the same chapter. We present a linear filtering method for computing the filter weights assigned to the observation for estimating unobserved signal under general noisy environment in third chapter. Here we consider both the signal and the noise as stationary processes with infinite variance innovations. We derived semi infinite, double infinite and asymmetric signal extraction filters based on minimum dispersion criteria. Finite length filters based on Kalman-Levy filters are developed and identified the pattern of the filter weights. Simulation studies show that the proposed methods are competent enough in signal extraction for processes with infinite variance.Parameter estimation of autoregressive signals observed in a symmetric stable noise environment is discussed in fourth chapter. Here we used higher order Yule-Walker type estimation using auto-covariation function and exemplify the methods by simulation and application to Sea surface temperature data. We increased the number of Yule-Walker equations and proposed a ordinary least square estimate to the autoregressive parameters. Singularity problem of the auto-covariation matrix is addressed and derived a modified version of the Generalized Yule-Walker method using singular value decomposition.In fifth chapter of the thesis we introduced partial covariation function as a tool for stable time series analysis where covariance or partial covariance is ill defined. Asymptotic results of the partial auto-covariation is studied and its application in model identification of stable auto-regressive models are discussed. We generalize the Durbin-Levinson algorithm to include infinite variance models in terms of partial auto-covariation function and introduce a new information criteria for consistent order estimation of stable autoregressive model.In chapter six we explore the application of the techniques discussed in the previous chapter in signal processing. Frequency estimation of sinusoidal signal observed in symmetric stable noisy environment is discussed in this context. Here we introduced a parametric spectrum analysis and frequency estimate using power transfer function. Estimate of the power transfer function is obtained using the modified generalized Yule-Walker approach. Another important problem in statistical signal processing is to identify the number of sinusoidal components in an observed signal. We used a modified version of the proposed information criteria for this purpose.

Dynamics and Thermodynamics of the Arabian Sea Warm Pool

The present study examines the importance of low saline waters and resulting barrier layer in the dynamics of the ASWP using observational data.The oceanic general circulation models (OGCM) are very useful for exploring the processes responsible for the ASWP and their variability. The circulation and thermohaline structure stimulated by an OGCM changes a lot when the resolution is increased from mesoscale to macro scale. For a reasonable simulation of the ASWP, we must include the mesoscale turbulence in numerical models. Especially the SEAS is an eddy prominent region with a horizontal dimension of 100 to 500 km and vertical extent of hundred meters. These eddies may have an important role on the evolution of ASWP, which has not been explored so far.Most of the earlier studies in the SEAS showed that the heat buildup in the mixed layer during the pre-monsoon (March-May) is primarily driven by the surface heat flux through the ocean-atmosphere interface, while the 3-dimensional heat budget of the ML physical processes that are responsible for the formation of the ASWP are unknown. With this background the present thesis also examines the relative importance of mixed layer processes that lead to the formation of warm pool in the SEAS.

Bayes quadratic unbiased estimator of spatial covariance parameters

This work presents Bayes invariant quadratic unbiased estimator, for short BAIQUE. Bayesian approach is used here to estimate the covariance functions of the regionalized variables which appear in the spatial covariance structure in mixed linear model. Firstly a brief review of spatial process, variance covariance components structure and Bayesian inference is given, since this project deals with these concepts. Then the linear equations model corresponding to BAIQUE in the general case is formulated. That Bayes estimator of variance components with too many unknown parameters is complicated to be solved analytically. Hence, in order to facilitate the handling with this system, BAIQUE of spatial covariance model with two parameters is considered. Bayesian estimation arises as a solution of a linear equations system which requires the linearity of the covariance functions in the parameters. Here the availability of prior information on the parameters is assumed. This information includes apriori distribution functions which enable to find the first and the second moments matrix. The Bayesian estimation suggested here depends only on the second moment of the prior distribution. The estimation appears as a quadratic form y'Ay , where y is the vector of filtered data observations. This quadratic estimator is used to estimate the linear function of unknown variance components. The matrix A of BAIQUE plays an important role. If such a symmetrical matrix exists, then Bayes risk becomes minimal and the unbiasedness conditions are fulfilled. Therefore, the symmetry of this matrix is elaborated in this work. Through dealing with the infinite series of matrices, a representation of the matrix A is obtained which shows the symmetry of A. In this context, the largest singular value of the decomposed matrix of the infinite series is considered to deal with the convergence condition and also it is connected with Gerschgorin Discs and Poincare theorem. Then the BAIQUE model for some experimental designs is computed and compared. The comparison deals with different aspects, such as the influence of the position of the design points in a fixed interval. The designs that are considered are those with their points distributed in the interval [0, 1]. These experimental structures are compared with respect to the Bayes risk and norms of the matrices corresponding to distances, covariance structures and matrices which have to satisfy the convergence condition. Also different types of the regression functions and distance measurements are handled. The influence of scaling on the design points is studied, moreover, the influence of the covariance structure on the best design is investigated and different covariance structures are considered. Finally, BAIQUE is applied for real data. The corresponding outcomes are compared with the results of other methods for the same data. Thereby, the special BAIQUE, which estimates the general variance of the data, achieves a very close result to the classical empirical variance.

Agricultural, architectural and archaeological evidence for the role and ecological adaptation of a scattered mountain oasis in Oman

The recent discovery of the monumental 5000 years old tower tombs on top of the up to 1850 m high Shir plateau has raised numerous questions about the economic and infrastructural basis of the agro-pastoral-piscicultural society which likely has constructed them. The scattered oasis settlement of Maqta, situated just below the towers in a rugged desert environment has therefore been studied from 2001 to 2003 to understand its prehistoric and present role along the ancient trade route which connected the inner-Omani Sharqiya across the southern Hajar mountains with the ocean port of Tiwi. Maqta consists of a central area with 59 buildings and 12 scattered temporary settlements comprising a total of about 200 semi-nomadic inhabitants and next to 900 sheep and goats. The 22 small springs with a flow rate between 5 and 1212-l h^-1 are watering 16 terrace systems totaling 4.5 ha of which 2.9 ha are planted to date palms (Phoenix dactylifera L.), 0.4 ha to wheat landraces (Triticum durum and Triticum aestivum) during the cooler winter months, 0.4 are left fallow and 0.8 h are abandoned. During a pronounced drought period from 2001 to 2003, the springs’ flow rate declined between 38% and 72%. Most of the recent buildings of the central housing area were found empty or used as temporary stores by the agro-pastoral population watching their flocks on the surrounding dry mountains. There is no indication that there ever was a settlement older than the present one. A number of Hafit (3100–2700 BC) and Umm an-Nar (2700–2000 BC) tombs just above the central housing area and further along one of the trade routes to the coast are the only indication of an old pastoral landuse in Maqta territory where oasis agriculture may have entered only well after 1000 AD. With this little evidence of existence during the 3rd millennium BC, Maqta is unlikely to have played any major role favouring the construction of the nearby monumental Shir tower tombs other than providing water for herders and their flocks, early migrant traders or tower tomb constructors.

Natural resource windfalls and efficiency of local government expenditures: evidence from Peru

We study the role of natural resource windfalls in explaining the efficiency of public expenditures. Using a rich dataset of expenditures and public good provision for 1,836 municipalities in Peru for period 2001-2010, we estimate a non-monotonic relationship between the efficiency of public good provision and the level of natural resource transfers. Local governments that were extremely favored by the boom of mineral prices were more efficient in using fiscal windfalls whereas those benefited with modest transfers were more inefficient. These results can be explained by the increase in political competition associated with the boom. However, the fact that increases in efficiency were related to reductions in public good provision casts doubts about the beneficial effects of political competition in promoting efficiency.

Filter for Car Tracking Based on Acceleration and Steering Angle

The motion of a car is described using a stochastic model in which the driving processes are the steering angle and the tangential acceleration. The model incorporates exactly the kinematic constraint that the wheels do not slip sideways. Two filters based on this model have been implemented, namely the standard EKF, and a new filter (the CUF) in which the expectation and the covariance of the system state are propagated accurately. Experiments show that i) the CUF is better than the EKF at predicting future positions of the car; and ii) the filter outputs can be used to control the measurement process, leading to improved ability to recover from errors in predictive tracking.

Solar influences on dynamical coupling between the stratosphere and troposphere

We use a simplified atmospheric general circulation model (AGCM) to investigate the response of the lower atmosphere to thermal perturbations in the lower stratosphere. The results show that generic heating of the lower stratosphere tends to weaken the sub-tropical jets and the tropospheric mean meridional circulations. The positions of the jets, and the extent of the Hadley cells, respond to the distribution of the stratospheric heating, with low latitude heating displacing them poleward, and uniform heating displacing them equatorward. The patterns of response to the low latitude heating are similar to those found to be associated with solar variability in previous observational data analysis, and to the effects of varying solar UV radiation in sophisticated AGCMs. In order to investigate the chain of causality involved in converting the stratospheric thermal forcing to a tropospheric climate signal we conduct an experiment which uses an ensemble of model spin-ups to analyse the time development of the response to an applied stratospheric perturbation. We find that the initial effect of the change in static stability at the tropopause is to reduce the eddy momentum flux convergence in this region. This is followed by a vertical transfer of the momentum forcing anomaly by an anomalous mean circulation to the surface, where it is partly balanced by surface stress anomalies. The unbalanced part drives the evolution of the vertically integrated zonal flow. We conclude that solar heating of the stratosphere may produce changes in the circulation of the troposphere even without any direct forcing below the tropopause. We suggest that the impact of the stratospheric changes on wave propagation is key to the mechanisms involved.

Langmuir turbulence and deeply penetrating jets in an unstratified mixed layer

The influence of surface waves and an applied wind stress is studied in an ensemble of large eddy simulations to investigate the nature of deeply penetrating jets into an unstratified mixed layer. The influence of a steady monochromatic surface wave propagating parallel to the wind direction is parameterized using the wave-filtered Craik-Leibovich equations. Tracer trajectories and instantaneous downwelling velocities reveal classic counterrotating Langmuir rolls. The associated downwelling jets penetrate to depths in excess of the wave's Stokes depth scale, δs. Qualitative evidence suggests the depth of the jets is controlled by the Ekman depth scale. Analysis of turbulent kinetic energy (tke) budgets reveals a dynamical distinction between Langmuir turbulence and shear-driven turbulence. In the former, tke production is dominated by Stokes shear and a vertical flux term transports tke to a depth where it is dissipated. In the latter, tke production is from the mean shear and is locally balanced by dissipation. We define the turbulent Langmuir number Lat = (v*/Us)0.5 (v* is the ocean's friction velocity and Us is the surface Stokes drift velocity) and a turbulent anisotropy coefficient Rt = /( + ). The transition between shear-driven and Langmuir turbulence is investigated by varying external wave parameters δs and Lat and by diagnosing Rt and the Eulerian mean and Stokes shears. When either Lat or δs are sufficiently small the Stokes shear dominates the mean shear and the flow is preconditioned to Langmuir turbulence and the associated deeply penetrating jets.