We are interested in variable sélection in linear régression models. This research is motivated by recent development in microarrays, proteomics, brain images, among others. We study this problem in both frequentist and bayesian viewpoints.In a frequentist framework, we propose methods to deal with the problem of variable sélection, when the number of variables is much larger than the sample size with a possibly présence of additional structure in the predictor variables, such as high corrélations or order between successive variables. The performance of the proposed methods is theoretically investigated ; we prove that, under regularity conditions, the proposed estimators possess statistical good properties, such as Sparsity Oracle Inequalities, variable sélection consistency and asymptotic normality.In a Bayesian Framework, we propose a global noninformative approach for Bayesian variable sélection. In this thesis, we pay spécial attention to two calibration-free hierarchical Zellner's g-priors. The first one is the Jeffreys prior which is not location invariant. A second one avoids this problem by only considering models with at least one variable in the model. The practical performance of the proposed methods is illustrated through numerical experiments on simulated and real world datasets, with a comparison betwenn Bayesian and frequentist approaches under a low informative constraint when the number of variables is almost equal to the number of observations.

Research on Machine learning (ML) explainability has received a lot of focus in recent times. The interest, however, mostly focused on supervised models, while other ML fields have not had the same level of attention. Despite its usefulness in a variety of different fields, unsupervised learning explainability is still an open issue. In this paper, we present a Visual Analytics framework based on eXplainable AI (XAI) methods to support the interpretation of Dimensionality reduction methods. The framework provides the user with an interactive and iterative process to investigate and explain user-perceived patterns for a variety of DR methods by using XAI methods to explain a supervised method trained on the selected data. To evaluate the effectiveness of the proposed solution, we focus on two main aspects: the quality of the visualization and the quality of the explanation. This challenge is tackled using both quantitative and qualitative methods, and due to the lack of pre-existing test data, a new benchmark has been created. The quality of the visualization is established using a well-known survey-based methodology, while the quality of the explanation is evaluated using both case studies and a controlled experiment, where the generated explanation accuracy is evaluated on the proposed benchmark. The results show a strong capacity of our framework to generate accurate explanations, with an accuracy of 89% over the controlled experiment. The explanation generated for the two case studies yielded very similar results when compared with pre-existing, well-known literature on ground truths. Finally, the user experiment generated high quality overall scores for all assessed aspects of the visualization.

The concept of Goal Orientations (GOs), which was initially developed in the area of educational psychology, is becoming more and more popular in organisational psychology. Although research on GOs has come a long way since the 1970s there are still a number of conceptual and operational issues which have yet to be addressed. These include issues with the definition, dimensionality, stability and specificity of GOs. It is considered essential to address these concerns because they greatly influence the reliability, validity and accuracy of GO research. Consequently, one aim of this study was to examine the dimensionality, stability and specificity of GOs. It is believed that once enough evidence regarding these issues is gathered this could be used to develop a comprehensive definition of GOs. This study aims to contribute towards gathering such evidence. GOs have been examined both in terms of profiles as well as in terms of individual GO scales (non-profile perspective) in the past. This study uses both perspectives in order to attempt to provide as much information as possible regarding the issues being investigated. Another aim of this study was to investigate the relationships between GOs and performance, mental effort and self-efficacy. Further knowledge of these relationships is considered to be of benefit to organisations. So as to achieve these aims a longitudinal study, consisting of a survey and an experimental study, was carried out. The survey sample consisted of 641 participants whilst the experimental sample was made up of 73 participants. The participants were mainly Loughborough University students. However, there were also a number of employed and retired individuals participating in the study. Quantitative analysis was deemed to be the most appropriate method of analysis to achieve the aims of this study. Data analyses were carried out using SPSS and Latent Gold software packages. The results point towards GOs not being as general and stable as initially assumed. There is a strong possibility of GOs being domain-specific. Consistent with a number of past studies, the approach GOs were found to be more strongly related to self-efficacy, mental effort and performance on tasks than the avoidance GOs. Moreover, the relationships between GOs and these variables seem to be moderated by task characteristics. The profile analyses results revealed that a number of GO profiles obtained in this study were very similar to those obtained in other studies. A closer look at these common GO profiles indicated that some profiles were consistently more strongly related to self-efficacy, mental effort and performance than others. This study provides a foundation for future research studies to build on in order to better understand the nature of GOs and their relationships with self-efficacy, mental effort and performance.

<p>This thesis is based upon synthesis and structure determination of new transition metal oxo-halide compounds, which includes p-element cations that have a stereochemically active lone pair. A synthesis concept has been developed, which uses several different structural features to increase the possibility to yield a low-dimensional arrangement of transition metal cations. A total of 17 new compounds has been synthesised and their structures have been determined <i>via</i> single-crystal X-ray diffraction. The halides and the stereochemically active lone-pairs will typically act as terminating species segregating into regions of non-bonding volumes, which may take the form of 2D layers, 1D channels or Euclidean spheres. The transition metals that have been used for this work are copper, cobalt and iron. The Hard-Soft-Acid-Base principle has been utilized to match strong Lewis acids to strong Lewis bases and weak acids to weak bases. All compounds show tendencies towards low-dimensionality; they all have sheets of transition metal cations arranged into layers, where the layers most often are connected via weak dispersion forces.</p>

This PhD work constitutes a series of inter-disciplinary studies that use biologically plausible computational techniques and experiments with human subjects in analyzing facial expressions. The performance of the computational models and human subjects in terms of accuracy and response time are analyzed. The computational models process images in three stages. This includes: Preprocessing, dimensionality reduction and Classification. The pre-processing of face expression images includes feature extraction and dimensionality reduction. Gabor filters are used for feature extraction as they are closest biologically plausible computational method. Various dimensionality reduction methods: Principal Component Analysis (PCA), Curvilinear Component Analysis (CCA) and Fisher Linear Discriminant (FLD) are used followed by the classification by Support Vector Machines (SVM) and Linear Discriminant Analysis (LDA). Six basic prototypical facial expressions that are universally accepted are used for the analysis. They are: angry, happy, fear, sad, surprise and disgust. The performance of the computational models in classifying each expression category is compared with that of the human subjects. The Effect size and Encoding face enable the discrimination of the areas of the face specific for a particular expression. The Effect size in particular emphasizes the areas of the face that are involved during the production of an expression. This concept of using Effect size on faces has not been reported previously in the literature and has shown very interesting results. The detailed PCA analysis showed the significant PCA components specific for each of the six basic prototypical expressions. An important observation from this analysis was that with Gabor filtering followed by non linear CCA for dimensionality reduction, the dataset vector size may be reduced to a very small number, in most cases it was just 5 components. The hypothesis that the average response time (RT) for the human subjects in classifying the different expressions is analogous to the distance measure of the data points from the classification hyper-plane was verified. This means the harder a facial expression is to classify by human subjects, the closer to the classifying hyper-plane of the classifier it is. A bi-variate correlation analysis of the distance measure and the average RT suggested a significant anti-correlation. The signal detection theory (SDT) or the d-prime determined how well the model or the human subjects were in making the classification of an expressive face from a neutral one. On comparison, human subjects are better in classifying surprise, disgust, fear, and sad expressions. The RAW computational model is better able to distinguish angry and happy expressions. To summarize, there seems to some similarities between the computational models and human subjects in the classification process.

Abstract Methylammonium lead (II) iodide has recently attracted considerable interest which may lead to substantial developments of efficient and inexpensive industrial photovoltaics. The application of this material as a light-absorbing layer in solid-state solar cells leads to impressive efficiency of over 22% in laboratory devices. However, for industrial applications, fundamental issues regarding their thermal and moisture stability need to be addressed. MAPbI3 belongs to the perovskite family of materials with the general formula ABX3 ,where is the organic cation (methylammonium) which is reported to be a major source of instability. In this work, a variety of alkyammonium lead (II) iodide materials have been synthesized by changing the organic cation, to study the relationship between the structural and physical properties of these materials. [(A)PbI3] and (A)PbI4 series were studied. Three dimensional (3D) networks (MAPbI3,MAPbBr3), two dimensional (2D) layered systems (BdAPbI4, HdAPbI4, OdAPbI4), and one dimensional (1D) columns (EAPbI3, PAPbI3, EAPb2I6) were found for the materials. [PbI6] octahedral structural units were repeated through the material network depending on the dimensionality and connectivity of the materials. Where a bulkier cation was introduced, the crystallographic unit cell increased in size which resulted in lower symmetry crystals. The connectivity of the unit cells along the material networks was found to be based on corner-sharing and face-sharing. Lower dimensionality resulted in larger bandgaps and lower photoconductivity, and hence a lower light conversion efficiency for the related solar cells. The thermal and moisture stability was greater in the 1D and 2D materials with bulkier organic cations than with methylammonium. In total, an overview is provided of the relationship between the chemical dimensionality and physical properties of the organic-inorganic lead halide materials with focus on the solar cell application. / Svenska sammandrag: Metylammoniumbly(II)jodid har under de senaste åren genererat ett stort intresse som ett möjligt material for utveckling av effektiva och på industriell skala billiga solceller. Detta material har använts som ljusabsorberande skikt i fasta solceller med imponerande omvandlingseffektiviteter på över 22% för solceller i laboratorieskala. För att denna nya typ av solceller ska bli intressanta för produktion på industriell skala, så behöver grundläggande frågeställningar kring materialens stabilitet avseende högre temperaturer och fukt klargöras. MAPbI3 har formellt perovskitstruktur med den allmänna formel ABX3, där A utgörs av den organiska katjonen (metyammoniumjonen) och som kan kopplas till materialets instabilitet. I denna avhandling har olika alkylammoniumbly(II)jodidmaterial syntetiserats där den organiska katjonen modifierats med syftet att studera växelverkan mellan struktur och fysikaliska egenskaper hos de resulterande materialen. Material av olika dimensionalitet erhölls; tredimensionella (3D) nätverk (MAPbI3, MAPbBr3), tvådimensionella (2D) skiktade strukturer (BdAPbI4, HdAPbI4, OdAPbI4), och endimensionella (1D) kedjestrukturer (EAPbI3, PAPbI3, EAPb2I6). Flera nya lågdimensionella material (2D och 1D) tillverkats och karaktäriserats för första gången. Enkristalldiffraktometri har använts för att erhålla materialens atomära struktur. Strukturen hos material tillverkade i större mängder konfirmerades genom jämförelse mellan resultat från pulverdiffraktion och enkristalldiffraktion. Den oktaedriska strukturenheten [PbI6] utgör ett återkommande tema i materialen sammankopplade till olika dimensioner. Då större organiska katjoner används karaktäriseras i regel strukturerna av större enhetsceller och lägre symmetri. De lågdimensionella materialen ger typiskt störe elektroniskt bandgap, lägre fotoinducerad ledningsförmåga och därför sämre omvandlingseffektiviteter då de används i solceller. De lågdimensionella materialen (1D och 2D) som baseras på de större organiska katjonerna uppvisar bättre stabilitet med avseende på högre tempereratur och fukt. De tvådimensionella materialens elektroniska struktur har karaktäriserats med hjälp av röntegenfotoelektronspektroskopi, liksom röntgenabsorptions- och emissionsspektroskopi. Resultat från teoretiska beräkningar stämmer väl överens med de experimentella resultaten, och de visar att materialens valensband huvudsakligen består av bidrag från atomorbitaler hos jod, medan atomorbitaler från bly främst bidrar till edningsbandet. Sammantaget erbjuder avhandlingen en översikt av sambandet mellan kemisk dimensionalitet och fysikaliska egenskaper hos ett antal organiska/oorganiska blyhalogenidmaterial med fokus på tillämpning i solceller. / <p>QC 20170123</p>

This thesis centers around dimensionality reduction and its usage on landmark-type data which are often used in anthropology and morphometrics. In particular we focus on non-linear dimensionality reduction methods - locally linear embedding and multidimensional scaling. We introduce a new approach to dimensionality reduction called multipass dimensionality reduction and show that improves the quality of classification as well as requiring less dimensions for successful classification than the traditional singlepass methods.

Random projection method is one of the important tools for the dimensionality reduction of data which can be made efficient with strong error guarantees. In this thesis, we focus on linear transforms of high dimensional data to the low dimensional space satisfying the Johnson-Lindenstrauss lemma. In addition, we also prove some theoretical results relating to the projections that are of interest when applying them in practical applications. We show how the technique can be applied to synthetic data with probabilistic guarantee on the pairwise distance. The connection between dimensionality reduction and compressed sensing is also discussed.

This thesis was constructed on the foundation of two broad theoretical criticisms levelled against Bandura’s (1986) social cognitive theory. The first was the lack of clarity about what constituted the building blocks of the theory and the second was the lack of clarity about how these constituent components interacted in consistent and predictable ways as an integrated model of human behaviour. These ‘theory-level’ criticisms, which detracted from the empirical testability of social cognitive theory, seemed to have filtered down to the level of its individual building blocks. Therefore, moral disengagement, which constituted the focal variable of interest in this investigation, was not unaffected by them. Bandura’s (1986) theoretical presentation of moral disengagement as either an eight or four-dimensional construct and the empirical treatments of moral disengagement by Bandura and his colleagues as a uni-dimensional (Bandura, Barbaranelli, Caprara & Pastorelli, 1996a; Bandura, Caprara, Barbaranelli, Pastorelli & Regalia, 2001b) and a four-dimensional variable (McAlister, Bandura & Owen, 2006), raised questions about its dimensionality. The first objective of this study was to examine moral disengagement’s dimensionality and the stability of its internal factor structure (i.e. longitudinal measurement invariance) over time. The general lack of clarity about how the constituent components of social cognitive theory were expected to cohere as an integrated framework of human behaviour had specific implications for the moral disengagement construct and its temporal position relative to other social cognitive variables. The second objective of this study was to examine moral disengagement’s temporal sequences relative to select social cognitive constructs (viz. proficiency-based self-efficacy, intention, and past and future behaviour) in order to comment on the likely temporal positions of these constructs relative to each other in the context of a model for predicting antisocial behaviour. Due to the exclusive activation of moral disengagement in antisocial contexts, the examination of its dimensionality and temporal sequences was contingent on an antisocial context. Software piracy, as a specific instance of antisocial behaviour, served as the context in which moral disengagement was researched in this study. A pilot investigation was conducted to test the psychometric properties of the scales that were developed to measure moral disengagement, proficiency-based self-efficacy, intention and behaviour in this study. Once their psychometric robustness was established, these scales were used in the context of a main longitudinal investigation separated by a three to four month time-lag in order to achieve the two main research objectives. Using the structural equation modelling family of data analysis techniques (specifically, confirmatory factor analysis and path analysis), the results of the main longitudinal study revealed that moral disengagement emerged as most meaningful as a uni-dimensional construct which consisted of four aggregated sets of items which represented the clusters of moral disengagement mechanisms that were likely to be activated at the four points in the self-regulation process envisaged by Bandura (1986). The findings suggested that this factor structure was longitudinally invariant when moral disengagement was measured across two assessment waves. Moral disengagement appeared to temporally precede intention and future behaviour and to temporally follow past behaviour. Self-efficacy, however, seemed to temporally precede future behaviour and to temporally follow past behaviour but unlike moral disengagement, self-efficacy appeared to temporally follow intention. Therefore, intention appeared to completely mediate the interaction between moral disengagement and proficiency-based self-efficacy in this study. The theoretical and practical implications of these findings were examined and directions for future research were proposed.

Cette thèse aborde deux problèmes ayant trait à la physique des gaz quantiques de basse dimensionnalité. Le premier système étudié est un mélange unidimensionnel de bosons et de fermions sans spin soumis à un potentiel aléatoire. Nous commençons par écrire un Hamiltonien de basse énergie et abordons la question de la localisation du point de vue de l'accrochage des ondes de densité par un désordre faible. En utilisant le Groupe de Renormalisation et une méthode variationnelle dans l'espace des répliques, le diagramme de phase peut être tracé en fonctions de deux paramètres : la force des interactions Bose-Bose et Bose-Fermi. La position et les propriétés des phases dépendent d'un paramètre additionnel, le rapport des vitesses du son de chaque composante du gaz. Quelque soit la valeur de ce rapport nous trouvons trois phases, (i) une phase totalement délocalisée, le liquide de Luttinger à deux composantes, (ii) une phase totalement localisée où les deux composantes sont accrochées par le désordre et (iii) une phase intermédiaire où seuls les fermions sont localisés. Le deuxième système est un gaz de bosons de cœur dur sur un réseau en échelle. Trois paramètres en contrôlent la physique : les amplitudes de saut transverse et longitudinale, et le remplissage. En utilisant plusieurs méthodes analytiques (théorie des perturbations, bosonisation et RG) nous proposons une interprétation de résultats numériques nouveaux obtenus par nos collaborateurs, notamment sur le paramètre de Luttinger du mode symétrique. Nous en déduisons un diagramme de phase en présence de désordre faible. / In this thesis we study two distinct problems related to the physics of quantum gases in one dimension. After writing a low-energy Hamiltonian, we address the question of localization by considering the pinning of density waves by weak disorder. Using the Renormalization Group and a variationnal method in replica space, we find that the phase diagram is adequately plotted as a function of two parameters: the strength of Bose-Bose and Bose-Fermi interactions. The position and properties of the various phases depend on an additional third parameter, the ratio of the phonon velocities of each component of the gas. Whatever the value of this ratio, we identify -- using the Renormalization Group and a variational calculation -- three types of phases, (i) a fully delocalized phase, that is a two-component Luttinger, (ii) a fully localized phase where both components are pinned by disorder and (iii) an intermediate phase where fermions are localized and bosons are superfluid. The second system is a two-leg ladder lattice of hardcore bosons. Three parameters control the physics: transverse and longitudinal tunneling and the filling. Using several analytical methods (perturbation theory, bosonization, RG) we give an interpretation of new numerical results obtained by our collaborators, namely on the Luttinger parameter of the symmetric mode. We deduce a phase diagram for weak disorder.