In this paper a partial least squares (PLS) approach to dynamic modelling with latent variables is proposed. Let Y be a matrix of manifest variables and H the matrix of the corresponding latent variables. And let H = BH+ε be a structural PLS model with a coefficient matrix B. Then this model can be made a dynamic one by substituting for B a matrix F = B + CL containing the lag operator L. Then the structural dynamic model H = FH+ε is formally estimated like an ordinary PLS model. In an exploratory way the model can be used for forecasting purposes. The procedure is being programmed in ISP.

No description available.

No description available.

Cette étude porte sur l‘identification de modèles dynamiques pour l‘évaluation des performances et le diagnostic énergétique de bâtiments existants. Le travail de thèse se place donc dans un contexte d‘économie d‘énergie et d‘efficacité énergétique accrue qui sont d‘intérêt primordial aujourd‘hui. Nous nous adressons à des bâtiments de bureaux occupés mais relativement bien instrumentés. Nous disposons des mesures horaires de température extérieure, de rayonnement solaire, de puissance de chauffage, de puissance électrique et de température de l‘air intérieur. L‘objectif étant de proposer une démarche méthodologique permettant de quantifier les performances énergétiques de l‘enveloppe du bâtiment à partir des données disponibles, d‘une part, et de préconiser des voies pour leur amélioration, d‘autre part. Les étapes majeurs de la démarche d‘évaluation/diagnostic proposée s‘ajuste pour l‘essentiel sur celles d‘une procédure classique d‘identification : a) analyse préliminaire des données disponible ; b) choix des structures mathématiques susceptibles de reproduire convenablement le comportement dynamique du bâtiment ; c) estimation du modèle et validation ; et exploitation du modèle pour des fins d‘évaluation et de diagnostic. Grâce aux résultats obtenus par une première approche « boîte noire » nous effectuons une tentative de diagnostic énergétique approfondi en s‘appuyant sur une modélisation physique du bâtiment (« boîte blanche »). / This study concerns the identification of dynamic models for performance evaluation and energy diagnosis of existing buildings. The work of this PhD takes place in a context of energy conservation and energy efficiency which are of essential interest today. We are dealing with occupied office buildings but relatively well instrumented. We have hourly measurements of outdoor temperature, solar radiation, heating power, electrical power and indoor air temperature. The aim is to propose a methodological approach to quantify the energy performance of building envelope from the available data, on the one hand, and to recommend ways to improve them, on the other. Major steps of the process evaluation / diagnosis given for the most fits with those of a standard procedure of identification: a) preliminary analysis of available data, b) choice of mathematical structures for well describing the building behavior c) model estimation and validation, and operation of the model for evaluation and diagnosis. With the results obtained by a first approach "black box" we make a tentative of detailed diagnosis based on physical building model ("white box").

The aim of this thesis is to explore methods to incorporate external effects on decision making of public health programmes in a UK setting, using smoking cessation as an example. The National Institute for Health and Clinical Excellence (NICE) methodological guidance for evaluating public health programmes is missing the incorporation of external effects. Therefore there is a need for considering their incorporation in such evaluations and to assess what are the appropiate methods to do so. Smoking cessation is an example where epidemiological evidence of external effects exists but has not generally been incorporated into economic evaluation. This thesis therefore focused in measuring the impact, in terms of costs and QALYs lost, of the incorporation of passive smoking, smoking during pregnancy and transmission of smoking behavior into economic evaluation of smoking cessation programmes previously developed to inform policy. A static Markov model is used to incorporate passive smoking and smoking during pregnancy, whereas transmisison of smoking behaviour is incorporated through a dynamic model. The findings show that some external effects can be incorporated without a system dynamic model, when this does occur, a static Markov model may be used to account for external effects in economic evaluation. Sometimes, to incorporate external effects, the model needs a change of population. Because smoking cessation interventions are generally highly cost-effective, the incorporation of external effects does not appear to change policy decisions, but there is a clear impact on the magnitude of the ICER. Passive smoking and smoking during pregnancy have higher impact in terms of costs and QALYs lost than transmission of smoking behaviour. Our discussion considers the validity of the methods used; how much the decision making process would be affected considering or not external effects on economic evaluation of smoking cessation interventions; and other valuation approaches for external effects, such as contingent valuation.

<p>In this dissertation I study the role of limited commitment in dynamic models. In the first part, I consider firms that face uncertainty shocks in a principal-agent setting but have only limited ability to commit to long-term contracts. Limited commitment firms expedite payments to their managers when uncertainty is high, a finding that helps to explain the puzzling large bonuses observed during the recent financial crisis. In the second part, I examine a dynamic investment model where firms invest in a risky asset but cannot hedge the risk of their investment because they lack the ability to commit to future repayments of debt. Once firms have access to exogenous supply of risk free assets they may, on the aggregate level, invest more in the risky asset because risk free technology allows them to grow richer in equilibrium. This result helps to explain the asset price booms in emerging countries when those countries experience substantial capital outflow.</p> / Dissertation

Doctor of Philosophy / Department of Statistics / Juan Du / It is common to assume the spatial or spatio-temporal data are realizations of underlying random elds or stochastic processes. E ective approaches to modelling of the underlying autocorrelation structure of the same random eld and the association among multiple processes are of great demand in many areas including atmospheric sciences, meteorology and agriculture. To this end, this dissertation studies methods and application of the spatial modeling of large-scale dependence structure and spatio-temporal regression modelling. First, variogram and variogram matrix functions play important roles in modeling dependence structure among processes at di erent locations in spatial statistics. With more and more data collected on a global scale in environmental science, geophysics, and related elds, we focus on the characterizations of the variogram models on spheres of all dimensions for both stationary and intrinsic stationary, univariate and multivariate random elds. Some e cient approaches are proposed to construct a variety of variograms including simple polynomial structures. In particular, the series representation and spherical behavior of intrinsic stationary random elds are explored in both theoretical and simulation study. The applications of the proposed model and related theoretical results are demonstrated using simulation and real data analysis. Second, knowledge of the influential factors on the number of days suitable for fieldwork (DSFW) has important implications on timing of agricultural eld operations, machinery decision, and risk management. To assess how some global climate phenomena such as El Nino Southern Oscillation (ENSO) a ects DSFW and capture their complex associations in space and time, we propose various spatio-temporal dynamic models under hierarchical Bayesian framework. The Integrated Nested Laplace Approximation (INLA) is used and adapted to reduce the computational burden experienced when a large number of geo-locations and time points is considered in the data set. A comparison study between dynamics models with INLA viewing spatial domain as discrete and continuous is conducted and their pros and cons are evaluated based on multiple criteria. Finally a model with time- varying coefficients is shown to reflect the dynamic nature of the impact and lagged effect of ENSO on DSFW in US with spatio-temporal correlations accounted.

Although research in leadership perception tends to show males have an advantage over females as a result of gender stereotypes, researchers have theorized recently some of this gender-related cognitive bias may be offset by perceiver affect (Medvedeff & Lord, 2007). In this experiment, a between-participants factorial design was used to examine the impact of gender stereotypes (male or female) and perceiver affect (positive or negative) on participants\' leader networks and dynamic perceptions of leadership. Participants were randomly assigned to a affect and leader gender condition with roughly 33 undergraduate students in each group. Leadership perceptions were assessed by examining connections between concepts in cognitive networks and repeated measurements of dynamic ratings. Data were analyzed using the Pathfinder and GEMCAT II (General Multivariate Methodology for Estimating Catastrophe Models) programs. Results suggested gender stereotypes and perceiver affect yield differential effects on leader networks. There was more stability in leader networks for a male leader than for a female, whereas there was more accuracy for perceivers in a neutral mood when compared to those in a negative mood condition. Furthermore, dynamic ratings showed the perceptual process in leadership emergence recognition was non-linear for both the male and female leader. Additionally, those in the negative mood condition were less resistant to changing their leadership perceptions when compared to those in the neutral mood condition. Potential interpretations for these findings are discussed and recommendations for future work in this area are provided. / Ph. D.

L'analyse du risque de survenue d'événements récurrents est une motivation majeure dans de nombreuses études de recherche clinique ou épidémiologique. En cancérologie, certaines stratégies thérapeutiques doivent être évaluées au cours d'essais randomisés où l'efficacité est mesurée à partir de la survenue d'événements successifs marquant la progression de la maladie. L'état de santé de patients infectés par le VIH évolue en plusieurs étapes qui ont pu être définies par la survenue d'événements cliniques successifs.Ce travail de thèse porte sur les modèles de régression du risque pour l'analyse de la survenue d'événements successifs. En pratique, la présence de corrélations entre les temps d'attente séparant les événements successifs est une hypothèse qui peut rarement être écartée d'emblée. L'objectif de la thèse porte sur le développement de modèles de régression permettant d'évaluer une telle corrélation. Dans ce cadre, la méthode le plus souvent utilisée suppose que la corrélation entre les délais successifs a pour origine une hétérogénéité aléatoire, non observée, entre sujets. Le modèle correspondant définit le risque instantané individuel en fonction d'un terme aléatoire, ou « fragilité », de distribution gamma et dont la variance quantifie l'hétérogénéité entre sujets et donc la corrélation entre délais d'un même sujet. Cependant, l'utilisation de ce modèle pour évaluer l'ampleur des corrélations présente l'inconvénient de conduire à une estimation biaisée de la variance de la fragilité.Une première approche a été définie pour deux événements successifs dans une échelle de temps « par intervalles », c'est-à-dire où le risque est exprimé en fonction du temps écoulé depuis l'événement précédent. L'approche mise au point a été obtenue à partir d'une approximation du risque de second événement conditionnellement au premier délai dans un modèle à fragilité pour plusieurs distributions de fragilité. Une seconde approche a été définie en échelle de temps « calendaire », où le risque est exprimé en fonction du temps écoulé depuis le début du suivi du sujet. L'approche retenue a été obtenue à partir d'une approximation de l'intensité conditionnelle au passé dans un modèle à fragilité. Dans les deux échelles de temps, l'approche mise au point consiste à introduire une covariable interne, calculée sur le passé du processus, qui correspond à la différence entre le nombre d'événements observés pour le sujet sur la période passée, et le nombre attendu d'événements pour ce sujet sur la même période compte tenu de ses covariables externes. Une revue de la littérature des études de simulations a montré que le cas d'une hétérogénéité dans la population face au risque d'événement était souvent envisagé par les auteurs. En revanche, dans beaucoup d'études de simulations, le cas d'un risque dépendant du temps, ou d'une dépendance entre événements, n'étaient pas considérés. Des études de simulations ont permis de montrer dans les deux échelles de temps considérées un gain de puissance du test mis au point par rapport au test d'homogénéité correspondant au modèle à fragilité gamma. Ce gain est plus marqué en échelle de temps par intervalles. Par ailleurs, dans cette échelle de temps, le modèle proposé permet une amélioration de l'estimation de la variance de la fragilité dans le cas d'une hétérogénéité faible ou modérée, plus particulièrement pour de petits échantillons.L'approche développée en échelle de temps par intervalles a été utilisée pour analyser les données d'une cohorte de patients infectés par le VIH, montrant une corrélation négative entre le délai entre infection et première manifestation mineure d'immunodéficience et le délai entre première manifestation mineure d'immunodéficience et stade SIDA déclaré. / The risk analysis for the occurrence of recurrent events is a major concern in many clinical research studies or epidemiological studies. In the field of oncology, therapeutic strategies are evaluated in randomised clinical trials in which efficacy is assessed through the occurrence of sequential events that define the progression of the disease. In HIV-infected patients, the infection evolves in several stages that have been defined by the occurrence of successive clinical events. The frame of this work is the regression models for the risk of multiple successive events. In practice, the hypothesis of existing correlations between the inter-event times cannot be a priori discarded. The aim of this work is to develop a regression model that would assess such correlations. In this setting, the most common method is to assume that correlations between inter-event times are induced by a random, unobserved heterogeneity across individuals. The corresponding model defines the individual hazard as a function of a random variable, or " frailty ", assumed to be gamma-distributed with a variance that quantifies the heterogeneity across individuals and incidentally the correlations between inter-event times. However, the use of this model when evaluating the correlations has the drawback that it tends to underestimate the variance of the frailty.A first approach was proposed for two sequential events in a "gap-timescale", in which the risk is defined as a function of the time elapsed since the previous event. The proposed method was derived from an approximation of the risk of second event given the first time-to-event in a frailty model for various frailty distributions. Another approach was defined in "calendar-time", in which the risk is expressed as a function of the time elapsed since the beginning of the subject's follow-up. The proposed method was derived from an approximation of the intensity conditional on the past in a frailty model. In both timescales, the method that was developed consists in including in the model an internal covariate, that is calculated on the history of the process, and that corresponds to the difference between the observed number of events and the expected number of events in the past period given the individual's other covariates.A review of the literature involving simulation studies showed that when defining the generation processes, most authors considered the case of heterogeneity in the population. However, in many simulation studies, only constant hazards are considered, and no event-dependence is introduced. Simulations studies showed that in both timescales, the test of the effect of the internal covariate in the proposed model proved more powerful that the usual test of homogeneity in the gamma frailty model. This gain of power is more noticeable in gap-time. Additionally, in this timescale, the proposed model provides a better estimation of the variance of the frailty when heterogeneity is low or moderate, more particularly in small samples.The method developed in gap-time was used to analyse data from a cohort of HIV-infected patients. It showed a negative correlation between the time from infection to first minor manifestation of immunodeficiency and the time from first minor manifestation of immunodeficiency to AIDS. The method developed in calendar-time was used to study the occurrence of repeated progressions and severe toxicities in a clinical trial for patients with advanced colorectal cancer. In this example, the method corroborated the results obtained with a gamma frailty model which showed a significant heterogeneity.

Introdução: A premissa do programa nacional de controle da leishmaniose visceral (LV) é que a doença humana esteja relacionada com a canina, sendo o controle do reservatório canino um dos focos do programa. Objetivos: Mensurar a taxa de incidência da LV em humanos, relacionando-a com as coberturas do controle químico e do reservatório canino. Relacionar a soroprevalência canina com características dos cães e de seus tutores. E avaliar a eficácia da eutanásia de cães soropositivos no controle da infecção canina. Métodos: Os casos humanos e os domicílios com cães soropositivos registrados no período de 2007 a 2015 no município de Araçatuba, estado de São Paulo, foram geocodificados e calculadas a soroprevalência canina, a taxa de incidência humana e as coberturas das atividades de inquérito sorológico, eutanásia e controle químico. A associação entre as variáveis foi avaliada por comparação de mapas, por regressão linear e pela função K de Ripley. Um estudo transversal foi conduzido entre 2015 e 2016, nos municípios de Araçatuba e Birigui, tendo como base uma amostra da população canina. A soroprevalência foi modelada por regressão logística em uma abordagem geoestatística usando a aproximação de Laplace integrada aninhada para inferência bayesiana. Dados secundários e dos inquéritos realizados foram utilizados para elaborar e calibrar modelos dinâmicos. Resultados: Observou-se no município de Araçatuba a diminuição da taxa de incidência LV e da soroprevalência canina, apesar das coberturas de controle terem sido baixas no mesmo período estudado. O inquérito sorológico revelou uma soroprevalência canina de 8% em Araçatuba e 4% em Birigui. Em Araçatuba a ocorrência de cães soropositivos foi associada à domicílios que tiveram mais de 10 cães ao longo do tempo, domicílios com histórico de cães com a infecção ou que morreram por outras causas não naturais, e à permanência dos cães no peridomicílio ao longo do dia. Foi observada dependência espacial (46 m) entre as observações. Considerando controle contínuo e um esforço das atividades de inquérito sorológico três vezes maior que a média do observado em Araçatuba e duas vezes maior em Birigui, as atividades relacionadas à eutanásia de cães com diagnóstico positivos possibilitariam, em teoria, o controle da infecção canina. Conclusões: A diminuição da LV ao longo do tempo está relacionada com as ações de controle, uma vez que pequenas alterações na dinâmica da infecção canina têm importância epidemiológica. O encontro de dependência espacial entre os domicílios com casos caninos em pequenas distâncias reforça a existência de um padrão local da transmissão da infecção entorno dos domicílios, relacionado com as características do vetor. A eutanásia de cães soropositivos, em teoria, é capaz de controlar a infecção canina, porém, este resultado desse ser entendido com cautela, dada a complexidade operacional desta medida e as questões éticas relacionadas. Novos estudos precisam ser desenvolvidos para uma melhor compreensão se fatores além das atividades de controle estariam envolvidos na diminuição da incidência da LV. Faz-se necessário planejamento a longo prazo das ações de controle e investimento em pesquisas sobre o custo-efetividade de outras medidas que auxiliem no controle da LV. / Background: The assumption of visceral leishmaniasis (VL) control program is that human disease (HVL) is related to canine infection (CanL), and that supports the culling of infected dogs. Objectives: Estimate the coverage of visceral leishmaniasis (VL) control measures and to relate them to the occurrence of HVL in an endemic urban area (Araçatuba, SP). Determine the CanL seroprevalence and to evaluate its relationship with the characteristics of dogs and their owners. Evaluated the culling dogs efficacy in controlling the canine infection. in the municipalities of Araçatuba and Birigui, state of São Paulo, Brazil. Methods: The cases of HVL and households with seropositive dogs registered in the period from 2007 to 2015 were geocoded the coverage of the serological inquiry, culling dogs and chemical spaying, canine seroprevalence and HVL incidence rates were calculated. The relationship between CanL, HVL and control measures was evaluated by map comparison, by linear regression and was also assessed using the Ripley K function. A cross-sectional study was conducted between 2015 and 2016, based on a sample of the canine population. Seroprevalence was modelled by logistic regression in a geostatistical approach using the integrated nested Laplace approximation for Bayesian inference. The spatial component was modelled by a Gaussian field, using a stochastic partial differential equation approach. Secondary data and the surveys were used to elaborate and calibrate dynamic models of canine disease transmission. Results: Verified the decrease of HVL and the CanL in Araçatuba over time, even in low coverage of control measures. The CanL seroprevalence was 8% in Araçatuba and 4% in Birigui. The occurrence of a seropositive dog in Araçatuba was associated with the presence of more than 10 dogs living in the same house, house with dogs that previously died of VL or died of other unnatural causes, and the place of dogs stayed during the day. Spatial dependence among observations occurred within about 46 m. Considering a continuous control and a serological survey effort three times higher than the average of the observed in Araçatuba and twice as high in Birigui, the activities related to culling dogs is effective in controlling canine infection. Conclusions: The observation of VL decrease over time may be related to control measures. The short-distance spatial dependence could be related to the vector characteristics, producing a local neighbourhood VL transmission pattern. The culling dogs were effective in controlling the disease in the dogs\' population. However, this result should be understood with caution given the operational complexity of this measure and related ethical issues. New studies need to be developed for a better understanding if factors other than control activities would be involved in reducing the incidence of VL. It is necessary in addition to long-term planning of the control actions carried out by the program, investment in researches that evaluate the cost-effectiveness of other measures that may help in the control of VL.