Previsão do índice bovespa por meio de redes neurais artificiais: uma análise comparada aos métodos tradicionais de séries de tempo

Forecast is the basis for making strategic, tactical and operational business decisions. In financial economics, several techniques have been used to predict the behavior of assets over the past decades.Thus, there are several methods to assist in the task of time series forecasting, however, conventional modeling techniques such as statistical models and those based on theoretical mathematical models have produced unsatisfactory predictions, increasing the number of studies in more advanced methods of prediction. Among these, the Artificial Neural Networks (ANN) are a relatively new and promising method for predicting business that shows a technique that has caused much interest in the financial environment and has been used successfully in a wide variety of financial modeling systems applications, in many cases proving its superiority over the statistical models ARIMA-GARCH. In this context, this study aimed to examine whether the ANNs are a more appropriate method for predicting the behavior of Indices in Capital Markets than the traditional methods of time series analysis. For this purpose we developed an quantitative study, from financial economic indices, and developed two models of RNA-type feedfoward supervised learning, whose structures consisted of 20 data in the input layer, 90 neurons in one hidden layer and one given as the output layer (Ibovespa). These models used backpropagation, an input activation function based on the tangent sigmoid and a linear output function. Since the aim of analyzing the adherence of the Method of Artificial Neural Networks to carry out predictions of the Ibovespa, we chose to perform this analysis by comparing results between this and Time Series Predictive Model GARCH, developing a GARCH model (1.1).Once applied both methods (ANN and GARCH) we conducted the results' analysis by comparing the results of the forecast with the historical data and by studying the forecast errors by the MSE, RMSE, MAE, Standard Deviation, the Theil's U and forecasting encompassing tests. It was found that the models developed by means of ANNs had lower MSE, RMSE and MAE than the GARCH (1,1) model and Theil U test indicated that the three models have smaller errors than those of a naïve forecast. Although the ANN based on returns have lower precision indicator values than those of ANN based on prices, the forecast encompassing test rejected the hypothesis that this model is better than that, indicating that the ANN models have a similar level of accuracy . It was concluded that for the data series studied the ANN models show a more appropriate Ibovespa forecasting than the traditional models of time series, represented by the GARCH model

Empirical validation of CAPM

This paper pretends to show empirical evidence of the CAPM model of Sharpe-Lintner (1964) for Colombia from 2003 to 2010, whose validation is carried out using the method of Black, Jensen and Scholes (1972) but introducing certain methodological econometric type changes associated to the requirements imposed by the used sample -- Specifically, we found no empirical evidence to reject the CAPM for the Colombian economyin the period under analysis

Long-term relationship between energy consumption and GDP in Latin America: an empirical assessment using panel data

The main objetive of this research is to evaluate the long term relationship between energy consumption and GDP for some Latin American countries in the period 1980-2009 -- The estimation has been done through the non-stationary panel approach, using the production function in order to control other sources of GDP variation, such as capital and labor -- In addition to this, a panel unit root tests are used in order to identify the non-stationarity of these variables, followed by the application of panel cointegration test proposed by Pedroni (2004) to avoid a spurious regression (Entorf, 1997; Kao, 1999)

Is the meander growth in the Brazil Current system off Southeast Brazil due to baroclinic instability?

Temporally-growing frontal meandering and occasional eddy-shedding is observed in the Brazil Current (BC) as it flows adjacent to the Brazilian Coast. No study of the dynamics of this phenomenon has been conducted to date in the region between 22 degrees S and 25 degrees S. Within this latitude range, the flow over the intermediate continental slope is marked by a current inversion at a depth that is associated with the Intermediate Western Boundary Current (IWBC). A time series analysis of 10-current-meter mooring data was used to describe a mean vertical profile for the BC-IWBC jet and a typical meander vertical structure. The latter was obtained by an empirical orthogonal function (EOF) analysis that showed a single mode explaining 82% of the total variance. This mode structure decayed sharply with depth, revealing that the meandering is much more vigorous within the BC domain than it is in the IWBC region. As the spectral analysis of the mode amplitude time series revealed no significant periods, we searched for dominant wavelengths. This search was done via a spatial EOF analysis on 51 thermal front patterns derived from digitized AVHRR images. Four modes were statistically significant at the 95% confidence level. Modes 3 and 4, which together explained 18% of the total variance, are associated with 266 and 338-km vorticity waves, respectively. With this new information derived from the data, the [Johns, W.E., 1988. One-dimensional baroclinically unstable waves on the Gulf Stream potential vorticity gradient near Cape Hatteras. Dyn. Atmos. Oceans 11, 323-350] one-dimensional quasi-geostrophic model was applied to the interpolated mean BC-IWBC jet. The results indicated that the BC system is indeed baroclinically unstable and that the wavelengths depicted in the thermal front analysis are associated with the most unstable waves produced by the model. Growth rates were about 0.06 (0.05) days(-1) for the 266-km (338-km) wave. Moreover, phase speeds for these waves were low compared to the surface BC velocity and may account for remarks in the literature about growing standing or stationary meanders off southeast Brazil. The theoretical vertical structure modes associated with these waves resembled very closely to the one obtained for the current-meter mooring EOF analysis. We interpret this agreement as a confirmation that baroclinic instability is an important mechanism in meander growth in the BC system. (C) 2008 Elsevier B.V. All rights reserved.

Modelos autorregressivos com valores inteiros não negativos : aplicação em séries económicas de Cabo Verde

No estudo de séries temporais, os processos estocásticos usuais assumem que as distribuições marginais são contínuas e, em geral, não são adequados para modelar séries de contagem, pois as suas características não lineares colocam alguns problemas estatísticos, principalmente na estimação dos parâmetros. Assim, investigou-se metodologias apropriadas de análise e modelação de séries com distribuições marginais discretas. Neste contexto, Al-Osh and Alzaid (1987) e McKenzie (1988) introduziram na literatura a classe dos modelos autorregressivos com valores inteiros não negativos, os processos INAR. Estes modelos têm sido frequentemente tratados em artigos científicos ao longo das últimas décadas, pois a sua importância nas aplicações em diversas áreas do conhecimento tem despertado um grande interesse no seu estudo. Neste trabalho, após uma breve revisão sobre séries temporais e os métodos clássicos para a sua análise, apresentamos os modelos autorregressivos de valores inteiros não negativos de primeira ordem INAR (1) e a sua extensão para uma ordem p, as suas propriedades e alguns métodos de estimação dos parâmetros nomeadamente, o método de Yule-Walker, o método de Mínimos Quadrados Condicionais (MQC), o método de Máxima Verosimilhança Condicional (MVC) e o método de Quase Máxima Verosimilhança (QMV). Apresentamos também um critério automático de seleção de ordem para modelos INAR, baseado no Critério de Informação de Akaike Corrigido, AICC, um dos critérios usados para determinar a ordem em modelos autorregressivos, AR. Finalmente, apresenta-se uma aplicação da metodologia dos modelos INAR em dados reais de contagem relativos aos setores dos transportes marítimos e atividades de seguros de Cabo Verde.

Respiratory syncytial virus seasonality in Brazil: implications for the immunisation policy for at-risk populations

Respiratory syncytial virus (RSV) infection is the leading cause of hospitalisation for respiratory diseases among children under 5 years old. The aim of this study was to analyse RSV seasonality in the five distinct regions of Brazil using time series analysis (wavelet and Fourier series) of the following indicators: monthly positivity of the immunofluorescence reaction for RSV identified by virologic surveillance system, and rate of hospitalisations per bronchiolitis and pneumonia due to RSV in children under 5 years old (codes CID-10 J12.1, J20.5, J21.0 and J21.9). A total of 12,501 samples with 11.6% positivity for RSV (95% confidence interval 11 - 12.2), varying between 7.1 and 21.4% in the five Brazilian regions, was analysed. A strong trend for annual cycles with a stable stationary pattern in the five regions was identified through wavelet analysis of the indicators. The timing of RSV activity by Fourier analysis was similar between the two indicators analysed and showed regional differences. This study reinforces the importance of adjusting the immunisation period for high risk population with the monoclonal antibody palivizumab taking into account regional differences in seasonality of RSV.

DEVELOPMENT OF AN OFF-LINE RAINFLOW COUNTING ALGORITHM WITH TEMPORAL PARAMETERS AND DATA REDUCTION

Rainflow counting methods convert a complex load time history into a set of load reversals for use in fatigue damage modeling. Rainflow counting methods were originally developed to assess fatigue damage associated with mechanical cycling where creep of the material under load was not considered to be a significant contributor to failure. However, creep is a significant factor in some cyclic loading cases such as solder interconnects under temperature cycling. In this case, fatigue life models require the dwell time to account for stress relaxation and creep. This study develops a new version of the multi-parameter rainflow counting algorithm that provides a range-based dwell time estimation for use with time-dependent fatigue damage models. To show the applicability, the method is used to calculate the life of solder joints under a complex thermal cycling regime and is verified by experimental testing. An additional algorithm is developed in this study to provide data reduction in the results of the rainflow counting. This algorithm uses a damage model and a statistical test to determine which of the resultant cycles are statistically insignificant to a given confidence level. This makes the resulting data file to be smaller, and for a simplified load history to be reconstructed.

The meaning of implied volatility in pricing stock options traded in options markets

Ph.D. in the Faculty of Business Administration

Dinâmica das pescas e gestão participativa do polvo vulgar (Octopus vulgaris) capturado pela frota de covos e alcatruzes no sul de Portugal

Tese de Doutoramento, Ciências do Mar, da Terra e do Ambiente, Faculdade de Ciências e Tecnologia, Universidade do Algarve, 2015

The determinants of VAT revenues in Portugal

Mestrado em Finanças

Análise de agrupamentos dos dados de DFA oriundos de perfis elétricos de indução de poços de petróleo

The main objective of this study is to apply recently developed methods of physical-statistic to time series analysis, particularly in electrical induction s profiles of oil wells data, to study the petrophysical similarity of those wells in a spatial distribution. For this, we used the DFA method in order to know if we can or not use this technique to characterize spatially the fields. After obtain the DFA values for all wells, we applied clustering analysis. To do these tests we used the non-hierarchical method called K-means. Usually based on the Euclidean distance, the K-means consists in dividing the elements of a data matrix N in k groups, so that the similarities among elements belonging to different groups are the smallest possible. In order to test if a dataset generated by the K-means method or randomly generated datasets form spatial patterns, we created the parameter Ω (index of neighborhood). High values of Ω reveals more aggregated data and low values of Ω show scattered data or data without spatial correlation. Thus we concluded that data from the DFA of 54 wells are grouped and can be used to characterize spatial fields. Applying contour level technique we confirm the results obtained by the K-means, confirming that DFA is effective to perform spatial analysis

Análise de homogeneidade de temperatura mínima mensal para o Estado de São Paulo.

Neste trabalho, o pacote Climatol-R foi aplicado a 122 séries mensais de temperatura mínima, cobrindo o interior do estado de São Paulo para os anos 1940 até 2012.

Riesgo sistémico, concentración y tamaño: Caso del sistema bancario colombiano

El presente documento tiene como propósito establecer en qué medida la concentración y el tamaño de la banca comercial puede afectar, si es que se da, la exposición de riesgo en el sistema bancario colombiano en el periodo de 1995 – 2014 -- Para tal fin, se siguió la metodología de Chumacero y Langon (2001) y Barro (2011), la cual realiza un modelo de serie de tiempo, tomando la razón entre cartera total y cartera vencida del total de los bancos, como variable proxy que mide el riesgo; así mismo, el indicador Herfindahl - Hirschman que determina el nivel de concentración, finalmente, con la razón entre activos de la banca como porcentaje del PIB -- El resultado obtenido describe que para el caso de la concentración, muestra un coeficiente menor a cero, que soportaría la idea de que la competencia se daría en riesgo ofertado en el mercado bancario colombiano; el tamaño por su parte, su coeficiente registra ser mayor que cero, soportando la existencia de bancos demasiado grandes para quebrar

The Nature of Microvariability in Blazar 0716+714

We organized an international campaign to observe the blazar 0716+714 in the optical band. The observations took place from February 24, 2009 to February 26, 2009. The global campaign was carried out by observers from more that sixteen countries and resulted in an extended light curve nearly seventy-eight hours long. The analysis and the modeling of this light curve form the main work of this dissertation project. In the first part of this work, we present the time series and noise analyses of the data. The time series analysis utilizes discrete Fourier transform and wavelet analysis routines to search for periods in the light curve. We then present results of the noise analysis which is based on the idea that each microvariability curve is the realization of the same underlying stochastic noise processes in the blazar jet. Neither reoccuring periods nor random noise can successfully explain the observed optical fluctuations. Hence in the second part, we propose and develop a new model to account for the microvariability we see in blazar 0716+714. We propose that the microvariability is due to the emission from turbulent regions in the jet that are energized by the passage of relativistic shocks. Emission from each turbulent cell forms a pulse of emission, and when convolved with other pulses, yields the observed light curve. We use the model to obtain estimates of the physical parameters of the emission regions in the jet.