Análise bayesiana do modelo fatorial dinâmico para um vetor de séries temporais utilizando a distribuição t multivariada

The multivariate t models are symmetric and with heavier tail than the normal distribution, important feature in financial data. In this theses is presented the Bayesian estimation of a dynamic factor model, where the factors follow a multivariate autoregressive model, using multivariate t distribution. Since the multivariate t distribution is complex, it was represented in this work as a mix between a multivariate normal distribution and a square root of a chi-square distribution. This method allowed to define the posteriors. The inference on the parameters was made taking a sample of the posterior distribution, through the Gibbs Sampler. The convergence was verified through graphical analysis and the convergence tests Geweke (1992) and Raftery & Lewis (1992a). The method was applied in simulated data and in the indexes of the major stock exchanges in the world.

Rotulagem como mecanismo de compartilhamento de informações com agentes da cadeia produtiva do café

The Agroindustrial System coffee after decades of state regulation has become a decentralized economic activity. This situation compelled most of the actors in the production chain to resort to self r egulatory systems offered by certification agencies, which have specific criteria and procedures. However the diversity criteria of the agencies do not offer resources able to ensure efficient management of the governance structure. There is a need to reduce the asymmetry of information, which is possible through the sharing of data compatible with the production tracking feature. This work is supported in this contextualized problem, based on Transaction Cost Theory and the use of qualitative and quantitative research methodologies. The first part of the work seeks to know the procedures required by leading regulatory agencies in Brazil, with perspective to emphasize the similarities and compatibilities between them, which was reached after analysis of standards and comparison of similarities. Next is registered the operation and the coffee traceability of the structure, in order to identify, through observation, documental and bibliographical analysis, the systems in place and traceable information in line with the recommendations of the coffee certification. Finally, he sought to create a labeling model that allows to generate and share information about the product from the field to the sale for consumption. The information obtained in the previous steps were the basis for data collection with the production chain agents through a structured questionnaire administered to 618 agents of the production chain, whose answers were treated by multivariate methods of statistical analysis. The results showed that actors in the chain are in favor of inclusion and sharing information related to rural production and economic and environmental data. This knowledge enabled develop a labeling model where the information sharing agents is an efficient mechanism to mitigate the governance problems identified.