No description available.

No description available.

No description available.

No description available.

La question du développement inclusif dans les pays en développement est au cœur de cette thèse. Cette dernière s'articule autour de quatre chapitres sur les questions de politique fiscale et les questions liées à la croissance inclusive. Le chapitre 1 explore comment la politique fiscale de l’Etat affecte l'inclusivité de la croissance dans les pays en développement. Nous observons que la politique fiscale affecte la croissance inclusive de manière significative si et seulement si les pays ont de fortes qualités institutionnelles. En outre, notre résultat montre qu'il existe un seuil optimal au-delà duquel toute augmentation du taux d'imposition négativement la croissance inclusive. Le chapitre 2 examine les effets des composantes des dépenses publiques sur l'équité et la croissance dans les pays d’Afrique subsaharienne, notamment s'il est possible de concevoir des dépenses publiques en vue de promouvoir une société plus équitable sans sacrifier la croissance économique. Notre étude a permis de montrer que l’investissement en infrastructure a contribué à une croissance plus inclusive en Afrique subsaharienne que d'autres dépenses publiques. Ces résultats suggèrent que des programmes temporaires et bien ciblés devraient être mis en place pour aider ceux qui sont laissés pour compte par le processus de croissance. Le chapitre 3 cherche à savoir si les problèmes d’inégalités de revenus se sont posés ou non dans les périodes d'ajustement budgétaire en Côte d'Ivoire au cours de la période 1980-2014. Nos résultats montrent une amélioration de la performance de croissance après les épisodes de consolidation budgétaire, mais aussi des diminutions de l'écart de revenu dans les périodes suivantes les années d’ajustements budgétaires. Enfin, le chapitre 4 évalue la crédibilité des prévisions budgétaires et leurs effets sur le bien-être social dans les pays de la CEMAC et de l'UEMOA. Nous sommes aboutis aux résultats que l'inefficacité des prévisions budgétaires se produit dans la plupart des cas parce que les erreurs de prévisions sont proportionnelles à la prévision elle-même, mais aussi parce que les erreurs passées sont répétées dans le temps. En outre, une partie des erreurs de prévision des recettes peut s'expliquer par des chocs aléatoires survenus dans l'économie. Par conséquent, ces erreurs dans les prévisions de revenus considérées comme des chocs de politique budgétaire ont un effet négatif sur la croissance inclusive. / The issue of inclusive development in developing countries is at the heart of this thesis. The latter revolves around four chapters on fiscal policy issues and inclusive growth-related matters. Chapter 1 explores how government tax policy affects the inclusiveness of growth in developing countries. Evidence is shown that tax policy affects significantly inclusive growth if and only if the countries have a strong institution quality like low corruption and a good bureaucratic policy. In addition, our result shows that there is an optimal tax beyond which, any increase in the personal income tax rate should have negative impact on inclusive growth. The Chapter 2 examines the effects of government expenditure components on both equity and growth in sub-Saharan countries, especially whether it is possible to design public spending to promote a more equitable society without sacrificing economic growth. We find that investment in infrastructure contributed to more inclusive growth in Sub-sub Saharan African economies than others government spending. These results suggest that temporary and well-targeted programs should be implemented to help those being left out by the growth process. The Chapter 3 investigates whether income inequality matters in the periods of fiscal adjustments in Côte d’Ivoire over the period 1980-2014. The results show an improvement in growth performance after fiscal consolidations episodes, but also income gap decreases in the periods ahead fiscal adjustments. Lastly, Chapter 4 assesses the credibility of fiscal forecasts and their social effects in CEMAC and WAEMU countries. We obtain evidence that the inefficiency of fiscal forecast occurs in most time because the forecast deviation is proportional to the forecast itself, but also because the past errors are repeated in the present. Furthermore, a part of revenue forecast errors can be explained by random shocks to the economy. Therefore, these errors in revenue forecast considered as fiscal policy shocks has a detrimental effect on inclusive growth.

A hanseníase, doença crônica estigmatizante com potencial de causar danos neurológicos, resulta da infecção pelo Mycobacterium leprae. Análises epidemiológicas atuais têm utilizado ferramentas clínicas e de análise espacial para o mapeamento dos principais focos de ocorrência de doenças e de áreas de alto risco. Analisar os municípios maranhenses quanto à distribuição dos casos de hanseníase torna-se uma ferramenta a mais na prevenção e controle da Hanseníase no estado por inúmeros fatores: comporta-se como área hiperendêmica de hanseníase; apresenta fluxo migratório intenso com outras cidades de forma interestadual; e tem grandes contrastes sociais marcados por pouca, ou nenhuma, infraestrutura básica em algumas áreas dos vários municípios deste. Objetivos: Analisar a distribuição espaço-temporal da hanseníase para o estado do Maranhão, no período de 2001 a 2013. Identificar a ocorrência de agrupamentos espaços-temporais de provável alta transmissão (risco) e verificar se há associação dessa distribuição de taxas de detecção de risco relativo (RR) da doença com as variáveis do contexto geográfico como socioeconômicas e ambientais. Metodologia: A fonte de coleta dos dados clínicos e epidemiológicos foi o Sistema de Informação Nacional de Agravos Notificáveis do Ministério da Saúde e dos dados demográficos, ambientais e bases cartográficas digitais do Instituto Brasileiro de Geografia e Estatística. Foi adotada uma abordagem ecológica sobre tendências dos padrões espaçostemporais de transmissibilidade, com utilização dos métodos: varredura espacial (scan), para a identificação dos agregados (clusters) de risco, considerando o modelo de distribuição de probabilidade Discreto de Poisson; Estimador Bayesiano Empírico para a suavização local de taxas, a partir de informações de municípios vizinhos tendo como estratégia de construção o critério da contiguidade; regressão múltipla espacial considerando uma modelagem com distribuição de Poisson no contexto Bayesiano, levando em conta a dependência espacial, com o propósito de avaliar a relação entre a ocorrência da variável dependente com as variáveis demográficas, socioeconômicas e ambientais. Resultados: A taxa média de detecção foi de 6,73 casos por 10.000 hab., com 53.826 casos notificados no período. O estudo revelou que a distribuição dos casos de sexo masculino (57,75%) apresentou maior proporção em relação ao feminino (42,25%), havendo predominância da doença na faixa etária >15 anos (89,87%). A alta ocorrência na classificação operacional multibacilar (60,10%) é um forte indicativo decorrente do longo período de incubação da doença somado ao não diagnóstico precoce. A análise da distribuição dos agregados espaciais identificou 14 (7 de risco alto e 7 de risco baixo) e 6 (3 de risco alto e 3 de risco baixo) agrupamentos espaciais, considerando-se 10% e 50% da população em risco, respectivamente, em áreas com taxas de detecção alta e que possuem baixa qualidade de vida. O estimador Bayesiano empírico local possibilitou gerar índices corrigidos e com menores instabilidades. A análise de regressão múltipla espacial mostrou que as variáveis índice Gini, bioma predominante cerrado/caatinga e percentual de população urbana tiveram associação positiva e significativa para explicar o risco relativo (RR) no estado do Maranhão. Conclusões: O estudo mostrou que existem aglomerados com elevado risco para transmissão da hanseníase no estado do Maranhão. A associação entre o risco relativo da hanseníase e o percentual de população urbana indica que a hipótese que associa o M. leprae e a população que vive em condições de acentuada desigualdade socioeconômica ainda é forte. Essa hiperendemicidade pode demonstrar que o crescimento da população urbana é um preditor de incidência da hanseníase, face à urbanização descontrolada e ao fluxo de migrantes advindos de diferentes espaços rurais. Foi possível identificar áreas prioritárias para implementação de programas eficazes de controle de hanseníase no estado do Maranhão. / Leprosy, a chronic stigmatizing disease with the potential to cause neurological damage resulting from infection by Mycobacterium leprae. Current epidemiological studies have used clinical and spatial analysis for mapping of the main occurrence of disease outbreaks and high-risk areas. Analyze the municipalities of Maranhão state regarding the distribution of leprosy cases becomes another tool in the prevention and control of leprosy in the state by numerous factors like behaves as hyper-endemic area of leprosy; It presents intense migration to other interstate cities; and has great social contrasts marked by little or no basic infrastructure in some areas of several municipalities.. Objectives: To analyze the spatiotemporal distribution of leprosy in the Maranhão state, from 2001 to 2013. To identify the spatiotemporal clusters occurrence of probable high transmission (risk) and check for association of this distribution of relative risk (RR) detection rates of the disease with the variables of geographic context as socioeconomic and environmental. Methodology: Clinical and epidemiological data was obtained from the Ministry of Healths Disease Reporting System and demographic data, environmental and digital cartographic bases were obtained from the Brazilian Geography and Statistics Institute. An ecological approach to trends transmissibility of spatiotemporal patterns, using the methods: spatial scan to identification the clusters of risk, considering the Discrete Poisson probability distribution model; empirical Bayesian method was applied for local rate flattening, using data from municipalities having as building strategy the criterion of contiguity; ecological regression modeling with considering a Poisson distribution in the Bayesian context, taking into account the spatial dependence, in order to evaluate the relationship between the occurrence of the dependent variable with demographic, socioeconomic and environmental variables. Results: The mean detection rate was 6.73 cases per 10,000 inhabitants, with 53,826 reported cases. The study revealed that the distribution of male cases (57.75%) showed a predominance over female (42.25%), with predominance of the disease in the age group upper than 15 years (89.87%). The high occurrence in operational classification multibacillary (60.10%) is a strong indication due to the long incubation period of the disease added to no early diagnosis. The analysis of the distribution of spatial clusters identified 14 (7 high risk and 7 low risk) and 6 (3 high risk and 3 low risk) spatial clusters, considering 10% and 50% of the population at risk in areas with high detection rates and which have low quality of life. Local empirical Bayes estimator allowed to generate fixed and minor instabilities indexes. The best results of modeling to spatial multiple regression analysis for the relative risk (RR) presented for the variables Gini index, cerrado/caatinga biome and percentage of urban population. Conclusions: The study showed that there are clusters at high risk for transmission of leprosy in the Maranhao state. The association between the relative risk of leprosy and the percentage of urban population indicates that the hypothesis that associates M. leprae and the population living in severe socioeconomic inequality is still strong. This hyperendemicity can demonstrate that the growth of the urban population is a predictor incidence of leprosy due to uncontrolled urbanization and the influx of migrants coming from different rural areas.It was possible to identify priority areas for implementation of effective leprosy control programs in the Maranhão state.

Les modèles de Rejets Urbains par Temps de Pluie (MRUTP) de Matières en Suspension (MES) dans les systèmes d’assainissement urbains sont essentiels pour des raisons scientifiques, environnementales, opérationnelles et réglementaires. Néanmoins, les MRUTP ont été largement mis en question, surtout pour reproduire des données mesurées en continu à l’exutoire des grands bassins versants. Dans cette thèse, trois limitations potentielles des MRUTP traditionnels ont été étudiées dans un bassin versant de 185 ha (Chassieu, France), avec des mesures en ligne de 365 événements pluvieux : a) incertitudes des données dû aux conditions sur le terrain, b) incertitudes dans les modèles hydrologiques et mesures de pluie et c) incertitudes dans les structures traditionnelles des MRUTP. Ces aspects sont approfondis dans six apports séparés, dont leurs résultats principaux peuvent être synthétisés comme suites : a) Acquisition et validation des données : (i) quatre stratégies d’échantillonnage pendant des événements pluvieux sont simulées et évaluées à partir de mesures en ligne de MES et débit. Les intervalles d’échantillonnage recommandés sont de 5 min, avec des erreurs moyennes entre 7 % et 20 % et des incertitudes sur ces erreurs d’environ 5 %, selon l’intervalle d’échantillonnage; (ii) la probabilité de sous-estimation de la concentration moyenne dans la section transversale du réseau est estimée à partir de deux méthodologies. Une méthodologie montre des sous-estimations de MES plus réelles (vers 39 %) par apport à l'autre (vers 269 %). b) Modèles hydrologiques et mesures de pluie : (iii) une stratégie d’estimation de paramètres d’un modèle conceptuel pluie-débit est proposée, en analysant la variabilité des paramètres optimaux obtenus à partir d’un calage Bayésien évènement-par-évènement; (iv) une méthode pour calculer les précipitations moyennes sur un bassin versant est proposée, sur la base du même modèle hydrologique et les données de débit. c) MRUTP (pollutographes) : (v) la performance de modélisation à partir du modèle traditionnel courbe d’étalonnage (RC) a été supérieur aux différents modèles linéaires de fonctions de transfert (TF), surtout en termes de parcimonie et précision des simulations. Aucune relation entre les potentielles erreurs de mesure de la pluie et les conditions hydrologiques définies en (iii) et (iv) avec les performances de RC et TFs n’a pu être établie. Des tests statistiques renforcent que l’occurrence des évènements non-représentables par RC ou TF au cours de temps suit une distribution aléatoire (indépendante de la période sèche précédente); (vi) une méthode de reconstruction Bayésienne de variables d’état virtuelles indique que des processus potentiellement manquants dans une description RC sont ininterprétables en termes d’un unique état virtuel de masse disponible dans le bassin versant qui diminue avec le temps, comme nombre de modèles traditionnels l’ont supposé. / Total Suspended Solids (TSS) stormwater models in urban drainage systems are often required for scientific, legal, environmental and operational reasons. However, these TSS stormwater traditional model structures have been widely questioned, especially when reproducing data from online measurements at the outlet of large urban catchments. In this thesis, three potential limitations of traditional TSS stormwater models are analyzed in a 185 ha urban catchment (Chassieu, Lyon, France), by means 365 rainfall events monitored online: a) uncertainties in TSS data due to field conditions; b) uncertainties in hydrological models and rainfall measurements and c) uncertainties in the stormwater quality model structures. These aspects are investigated in six separate contributions, whose principal results can be summarized as follows: a) TSS data acquisition and validation: (i) four sampling strategies during rainfall events are simulated and evaluated by online TSS and flow rate measurements. Recommended sampling time intervals are of 5 min, with average sampling errors between 7 % and 20 % and uncertainties in sampling errors of about 5 %, depending on the sampling interval; (ii) the probability of underestimating the cross section mean TSS concentration is estimated by two methodologies. One method shows more realistic TSS underestimations (about 39 %) than the other (about 269 %). b) Hydrological models and rainfall measurements: (iii) a parameter estimation strategy is proposed for conceptual rainfall-runoff model by analyzing the variability of the optimal parameters obtained by single-event Bayesian calibrations, based on clusters and graphs representations. The new strategy shows more performant results in terms of accuracy and precision in validation; (iv) a methodology aimed to calculate “mean” areal rainfall estimation is proposed, based on the same hydrological model and flow rate data. Rainfall estimations by multiplying factors over constant-length time window and rainfall zero records filled with a reverse model show the most satisfactory results compared to further rainfall estimation models. c) Stormwater TSS pollutograph modelling: (v) the modelling performance of the traditional Rating Curve (RC) model is superior to different linear Transfer Function models (TFs), especially in terms of parsimony and precision of the simulations. No relation between the rainfall corrections or hydrological conditions defined in (iii) and (iv) with performances of RC and TFs could be established. Statistical tests strengthen that the occurrence of events not representable by the RC model in time is independent of antecedent dry weather conditions; (vi) a Bayesian reconstruction method of virtual state variables indicate that potential missing processes in the RC description are hardly interpretable as a unique state of virtual available mass over the catchment decreasing over time, as assumed by a great number of traditional models.

A hanseníase, doença crônica estigmatizante com potencial de causar danos neurológicos, resulta da infecção pelo Mycobacterium leprae. Análises epidemiológicas atuais têm utilizado ferramentas clínicas e de análise espacial para o mapeamento dos principais focos de ocorrência de doenças e de áreas de alto risco. Analisar os municípios maranhenses quanto à distribuição dos casos de hanseníase torna-se uma ferramenta a mais na prevenção e controle da Hanseníase no estado por inúmeros fatores: comporta-se como área hiperendêmica de hanseníase; apresenta fluxo migratório intenso com outras cidades de forma interestadual; e tem grandes contrastes sociais marcados por pouca, ou nenhuma, infraestrutura básica em algumas áreas dos vários municípios deste. Objetivos: Analisar a distribuição espaço-temporal da hanseníase para o estado do Maranhão, no período de 2001 a 2013. Identificar a ocorrência de agrupamentos espaços-temporais de provável alta transmissão (risco) e verificar se há associação dessa distribuição de taxas de detecção de risco relativo (RR) da doença com as variáveis do contexto geográfico como socioeconômicas e ambientais. Metodologia: A fonte de coleta dos dados clínicos e epidemiológicos foi o Sistema de Informação Nacional de Agravos Notificáveis do Ministério da Saúde e dos dados demográficos, ambientais e bases cartográficas digitais do Instituto Brasileiro de Geografia e Estatística. Foi adotada uma abordagem ecológica sobre tendências dos padrões espaçostemporais de transmissibilidade, com utilização dos métodos: varredura espacial (scan), para a identificação dos agregados (clusters) de risco, considerando o modelo de distribuição de probabilidade Discreto de Poisson; Estimador Bayesiano Empírico para a suavização local de taxas, a partir de informações de municípios vizinhos tendo como estratégia de construção o critério da contiguidade; regressão múltipla espacial considerando uma modelagem com distribuição de Poisson no contexto Bayesiano, levando em conta a dependência espacial, com o propósito de avaliar a relação entre a ocorrência da variável dependente com as variáveis demográficas, socioeconômicas e ambientais. Resultados: A taxa média de detecção foi de 6,73 casos por 10.000 hab., com 53.826 casos notificados no período. O estudo revelou que a distribuição dos casos de sexo masculino (57,75%) apresentou maior proporção em relação ao feminino (42,25%), havendo predominância da doença na faixa etária >15 anos (89,87%). A alta ocorrência na classificação operacional multibacilar (60,10%) é um forte indicativo decorrente do longo período de incubação da doença somado ao não diagnóstico precoce. A análise da distribuição dos agregados espaciais identificou 14 (7 de risco alto e 7 de risco baixo) e 6 (3 de risco alto e 3 de risco baixo) agrupamentos espaciais, considerando-se 10% e 50% da população em risco, respectivamente, em áreas com taxas de detecção alta e que possuem baixa qualidade de vida. O estimador Bayesiano empírico local possibilitou gerar índices corrigidos e com menores instabilidades. A análise de regressão múltipla espacial mostrou que as variáveis índice Gini, bioma predominante cerrado/caatinga e percentual de população urbana tiveram associação positiva e significativa para explicar o risco relativo (RR) no estado do Maranhão. Conclusões: O estudo mostrou que existem aglomerados com elevado risco para transmissão da hanseníase no estado do Maranhão. A associação entre o risco relativo da hanseníase e o percentual de população urbana indica que a hipótese que associa o M. leprae e a população que vive em condições de acentuada desigualdade socioeconômica ainda é forte. Essa hiperendemicidade pode demonstrar que o crescimento da população urbana é um preditor de incidência da hanseníase, face à urbanização descontrolada e ao fluxo de migrantes advindos de diferentes espaços rurais. Foi possível identificar áreas prioritárias para implementação de programas eficazes de controle de hanseníase no estado do Maranhão. / Leprosy, a chronic stigmatizing disease with the potential to cause neurological damage resulting from infection by Mycobacterium leprae. Current epidemiological studies have used clinical and spatial analysis for mapping of the main occurrence of disease outbreaks and high-risk areas. Analyze the municipalities of Maranhão state regarding the distribution of leprosy cases becomes another tool in the prevention and control of leprosy in the state by numerous factors like behaves as hyper-endemic area of leprosy; It presents intense migration to other interstate cities; and has great social contrasts marked by little or no basic infrastructure in some areas of several municipalities.. Objectives: To analyze the spatiotemporal distribution of leprosy in the Maranhão state, from 2001 to 2013. To identify the spatiotemporal clusters occurrence of probable high transmission (risk) and check for association of this distribution of relative risk (RR) detection rates of the disease with the variables of geographic context as socioeconomic and environmental. Methodology: Clinical and epidemiological data was obtained from the Ministry of Healths Disease Reporting System and demographic data, environmental and digital cartographic bases were obtained from the Brazilian Geography and Statistics Institute. An ecological approach to trends transmissibility of spatiotemporal patterns, using the methods: spatial scan to identification the clusters of risk, considering the Discrete Poisson probability distribution model; empirical Bayesian method was applied for local rate flattening, using data from municipalities having as building strategy the criterion of contiguity; ecological regression modeling with considering a Poisson distribution in the Bayesian context, taking into account the spatial dependence, in order to evaluate the relationship between the occurrence of the dependent variable with demographic, socioeconomic and environmental variables. Results: The mean detection rate was 6.73 cases per 10,000 inhabitants, with 53,826 reported cases. The study revealed that the distribution of male cases (57.75%) showed a predominance over female (42.25%), with predominance of the disease in the age group upper than 15 years (89.87%). The high occurrence in operational classification multibacillary (60.10%) is a strong indication due to the long incubation period of the disease added to no early diagnosis. The analysis of the distribution of spatial clusters identified 14 (7 high risk and 7 low risk) and 6 (3 high risk and 3 low risk) spatial clusters, considering 10% and 50% of the population at risk in areas with high detection rates and which have low quality of life. Local empirical Bayes estimator allowed to generate fixed and minor instabilities indexes. The best results of modeling to spatial multiple regression analysis for the relative risk (RR) presented for the variables Gini index, cerrado/caatinga biome and percentage of urban population. Conclusions: The study showed that there are clusters at high risk for transmission of leprosy in the Maranhao state. The association between the relative risk of leprosy and the percentage of urban population indicates that the hypothesis that associates M. leprae and the population living in severe socioeconomic inequality is still strong. This hyperendemicity can demonstrate that the growth of the urban population is a predictor incidence of leprosy due to uncontrolled urbanization and the influx of migrants coming from different rural areas.It was possible to identify priority areas for implementation of effective leprosy control programs in the Maranhão state.

Dans cette thèse nous avons traité le problème de l'estimation non paramétrique des lois de probabilités. Dans un premier temps, nous avons supposé que la densité inconnue f a été approchée par un mélange de base B-spline quadratique. Puis, nous avons proposé un nouvel estimateur de la densité inconnue f basé sur les fonctions B-splines quadratiques, avec deux méthodes d'estimation. La première est base sur la méthode du maximum de vraisemblance et la deuxième est basée sur la méthode d'estimation Bayésienne MAP. Ensuite, nous avons généralisé notre étude d'estimation dans le cadre du mélange et nous avons proposé un nouvel estimateur du mélange de lois inconnues basé sur les deux méthodes d'estimation adaptées. Dans un deuxième temps, nous avons traité le problème de la segmentation statistique semi supervisée des images en se basant sur le modèle de Markov caché et les fonctions B-splines. Nous avons montré l'apport de l'hybridation du modèle de Markov caché et les fonctions B-splines en segmentation statistique bayésienne semi supervisée des images. Dans un troisième temps, nous avons présenté une approche de fusion basée sur la méthode de maximum de vraisemblance, à travers l'estimation non paramétrique des probabilités, pour chaque pixel de l'image. Nous avons ensuite appliqué cette approche sur des images multi-spectrales et multi-temporelles segmentées par notre algorithme non paramétrique et non supervisé. / In this thesis we are treated the problem of nonparametric estimation probability distributions. At first, we assumed that the unknown density f was approximated by a basic mixture quadratic B-spline. Then, we proposed a new estimate of the unknown density function f based on quadratic B-splines, with two methods estimation. The first is based on the maximum likelihood method and the second is based on the Bayesian MAP estimation method. Then we have generalized our estimation study as part of the mixture and we have proposed a new estimator mixture of unknown distributions based on the adapted estimation of two methods. In a second time, we treated the problem of semi supervised statistical segmentation of images based on the hidden Markov model and the B-sline functions. We have shown the contribution of hybridization of the hidden Markov model and B-spline functions in unsupervised Bayesian statistical image segmentation. Thirdly, we presented a fusion approach based on the maximum likelihood method, through the nonparametric estimation of probabilities, for each pixel of the image. We then applied this approach to multi-spectral and multi-temporal images segmented by our nonparametric and unsupervised algorithm.

自1997年以降，受到亞洲金融風暴的衝擊，亞洲各國匯率巨幅波動，於是如何增進匯率預測的準確度已成為重要的研究課題。而自1973年布列敦森林體制崩潰，各工業國家改採浮動匯率以來，匯率巨幅波動致使國際收支理論不再能解釋匯率如何決定，於是1970年代，學者們紛紛提出各種匯率決定理論，其中以貨幣學派模型與資產組合平衡模型最受到重視。然而，自1978年始，這些結構模型的解釋能力逐漸受到質疑，在1983年Meese and Rogoff甚至提出結構模型的樣本外預測能力不如隨機漫步模型的樣本外預測表現，引起學者們的討論到底何者的樣本外預測表現較佳。而隨著計量方法的演進實證研究已由恆定的計量方法演進至非恆定的計量方法，在非恆定的計量方法方面，MacDonald and Taylor(1993、1994)、吳宜璋(1996)等人的研究皆採誤差修正模型來做預測。 本研究亦採誤差修正模型來做預測，但對其他學者的研究稍作改良：1.加入結構變動虛擬變數2.以向量誤差修正模型而非一條誤差修正的式子來做預測，在此以整個體系的觀點來做預測3.以背氏方法加入相驗情報來改善預測。 結論為在金融風暴發生期間，匯率受非基本面因素影響較大時，貝氏向量自迴歸模型預測表現較佳。而在金融風暴發生之前，匯率受基本面影響較小時，以貝氏向量誤差修正模型為良好的預測模型。 / This study improves other scholars' empirical studies by testing structure changes and by using Vector Error Correction Model to forecast N.T. Dollars. Futhermore,use Bayesian Method to improve predition .The conclusion is Bayesian VAR Model perform better when forecasting period include Asian finanl crisis . And Bayesian VECM Model is better model when forecasting period don't include Asian financial crisis.And the out of sample prediction performance of structure model is better than Random Walk Model.