Robust Bayesian analysis of heavy-tailed stochastic volatility models using scale mixtures of normal distributions

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Batch, sequential and hybrid approaches to spacecraft sensor alignment estimation

Two Kalman-filter formulations are presented for the estimation of spacecraft sensor misalignments from inflight data. In the first the sensor misalignments are part of the filter state variable; in the second, which we call HYLIGN, the state vector contains only dynamical variables, but the sensitivities of the filter innovations to the misalignments are calculated within the Kalman filter. This procedure permits the misalignments to be estimated in batch mode as well as a much smaller dimension for the Kalman filter state vector. This results not only in a significantly smaller computational burden but also in a smaller sensitivity of the misalignment estimates to outliers in the data. Numerical simulations of the filter performance are presented.

Bayesian outlier analysis in binary regression

We propose alternative approaches to analyze residuals in binary regression models based on random effect components. Our preferred model does not depend upon any tuning parameter, being completely automatic. Although the focus is mainly on accommodation of outliers, the proposed methodology is also able to detect them. Our approach consists of evaluating the posterior distribution of random effects included in the linear predictor. The evaluation of the posterior distributions of interest involves cumbersome integration, which is easily dealt with through stochastic simulation methods. We also discuss different specifications of prior distributions for the random effects. The potential of these strategies is compared in a real data set. The main finding is that the inclusion of extra variability accommodates the outliers, improving the adjustment of the model substantially, besides correctly indicating the possible outliers.

Consideracoes sobre a aplicacao da geoestatistica a dados geoquimicos.

Deals with some common problems in structural analysis when calculating the experimental semi-variogram and fitting a semi-variogram model. Geochemical data were used and the following cases were studied: regular versus irregular sampling grade, presence of 'outliers' values, skew distributions due to a high variability of the data and estimation using a kriging procedure. -from English summary

Batch and filter approaches to spacecraft sensor alignment estimation

Two Kalman-filter formulations are presented for the estimation of spacecraft sensor misalignments from inflight data. In the first the sensor misalignments are part of the filter state variable; in the second the state vector contains only dynamical variables, but the sensitivities of the filter innovations to the misalignments are calculated within the Kalman filter. This procedure permits the misalignments to be estimated in batch mode as well as a much smaller dimension for the Kalman filter state vector. This results not only in a significantly smaller computational burden but also in a smaller sensitivity of the misalignment estimates to outliers in the data. Numerical simulations of the filter performance are presented.

Robust linear mixed models with normal/independent distributions and Bayesian MCMC implementation

Linear mixed effects models have been widely used in analysis of data where responses are clustered around some random effects, so it is not reasonable to assume independence between observations in the same cluster. In most biological applications, it is assumed that the distributions of the random effects and of the residuals are Gaussian. This makes inferences vulnerable to the presence of outliers. Here, linear mixed effects models with normal/independent residual distributions for robust inferences are described. Specific distributions examined include univariate and multivariate versions of the Student-t, the slash and the contaminated normal. A Bayesian framework is adopted and Markov chain Monte Carlo is used to carry out the posterior analysis. The procedures are illustrated using birth weight data on rats in a texicological experiment. Results from the Gaussian and robust models are contrasted, and it is shown how the implementation can be used for outlier detection. The thick-tailed distributions provide an appealing robust alternative to the Gaussian process in linear mixed models, and they are easily implemented using data augmentation and MCMC techniques.

Uso de indicadores hidrológicos para classificação de trechos de estradas florestais quanto ao escoamento superficial

Forest roads are frequently pointed as source of environmental problems related to erosion and they also influence harvest cost due to maintenance operations. Roads not well designed are sources of hydrological problems on catchments and the current attention to sustainability of forest exploration projects point out to the need of diagnostics tools for guiding the redesign of the road system. At this study, runoff hydrological indicators for forest road segments were assessed in order to identify critical points of erosion and water concentration on soils. A road network of a forest production area was divided into 252 road segments that were used as observations of four variables: mean terrain slope, main segment slope, LS factor and topographic index. The data analysis was based on descriptive statistics for outliers' identification, principal component analysis and for variability study between variables and between observations, and cluster analysis for similar segments groups' identification. The results allowed classifying roads segments into five mains road types: road on the ridge, on the valley, on the slopes, on the slopes but in a contour line and on the steepest slope. The indicators were able to highlight the most critical segments that differ of others and are potential sources of erosion and water accumulation problems on forest roads. The principal component analysis showed two main variability sources related to terrain topographic characteristics and also road design, showing that indicators represent well those elements. The methodology seems to be appropriated for identification of critical road segments that need to be redesigned and also for road network planning at new forest exploration projects.

Improving the accuracy of the optimum-path forest supervised classifier for large datasets

In this work, a new approach for supervised pattern recognition is presented which improves the learning algorithm of the Optimum-Path Forest classifier (OPF), centered on detection and elimination of outliers in the training set. Identification of outliers is based on a penalty computed for each sample in the training set from the corresponding number of imputable false positive and false negative classification of samples. This approach enhances the accuracy of OPF while still gaining in classification time, at the expense of a slight increase in training time. © 2010 Springer-Verlag.

Globalizing talent and human capital: implications for developing countries

Includes bibliography

Fuzzy community structure detection by particle competition and cooperation

Identification and classification of overlapping nodes in networks are important topics in data mining. In this paper, a network-based (graph-based) semi-supervised learning method is proposed. It is based on competition and cooperation among walking particles in a network to uncover overlapping nodes by generating continuous-valued outputs (soft labels), corresponding to the levels of membership from the nodes to each of the communities. Moreover, the proposed method can be applied to detect overlapping data items in a data set of general form, such as a vector-based data set, once it is transformed to a network. Usually, label propagation involves risks of error amplification. In order to avoid this problem, the proposed method offers a mechanism to identify outliers among the labeled data items, and consequently prevents error propagation from such outliers. Computer simulations carried out for synthetic and real-world data sets provide a numeric quantification of the performance of the method. © 2012 Springer-Verlag.

A meta-analytical study about the relation of blood plasma addition in diets for piglets in the post-weaning and productive performance variables

The meta-analysis was used to evaluate the performance of piglets in post-weaning period, without imposition of sanitary challenge and fed diets containing blood plasma, obtained by spray-dried process (SDBP). Piglets are faced with normal challenges in post-weaning period such as environmental stress and the substitution of the liquid diet to a solid one. References regarding sanitary challenges were disregarded in this study. Only data regarding normal and expected challenges were considered. Data were obtained from indexed journals with information extracted from the material, methods and results sections of pre-selected scientific articles. First, the database was analyzed graphically to observe the distribution of data and presence of outliers. Afterwards correlation analysis and variance-covariance analyses were carried out. The database contained a total of 23 articles. The average initial weight of the piglets was 8.02. kg (4.00-9.28. kg) and the average initial age was 27 days (14-32 days). The average duration of feeding diets containing spray-dried blood plasma (SDBP) was 9 days (6-28 days). SDBP increased the feed conversion by 20.2% (P<0.05) during the initial period. Feed conversion during the total period was 10.2% higher (P<0.05) for animals fed with SDBP. Average daily weight gain and daily feed intake were not affected (P>0.05) during the entire period, but average daily gain was higher (P<0.05) for animals fed with SDBP during the initial period. The initial age of supplementation influenced the average daily weight gain and average daily feed intake of animals fed with SDBP. Better results were obtained than those obtained for animals up to 35 days of age fed diets without added SDBP supplementation. In early post-weaning period for piglets weaned up to 35 days of age, the SDBP supplementation positively influenced the average daily weight gain and feed conversion. © 2013 Elsevier B.V.

Quality of performance of the operation of sugarcane mechanized planting in day and night shifts

The sugarcane mechanized planting is becoming increasingly widespread in Brazil due to a higher operability and better working conditions offered to workers compared to other types of planting. Studies related to this topic are insufficient or scarce in Brazil. In this context, the aim of this study was to evaluate the operation quality of sugarcane mechanized planting in two operation shifts, by means of statistical process control. The mechanized planting was held on March 2012 and statistical design was completely randomized with two treatments, totaling 40 replications for the day shift and 40 replications for the night shift. The variables evaluated were: speed, engine rotation, engine oil pressure, water temperature of the engine, effective field capacity and the time consumption hourly and effective fuel. The use of statistical control charts showed that random intrinsic do not cause this process. The tractor alignment error showed outliers in the day and night shifts operations, indicating a possible delay in receiving the signal. The water temperature of the engine and the effective fuel consumption showed lower variability in nighttime operation with average values of 81°C and 22.66 L ha-1, respectively. The hourly fuel consumption had greater variability and consequently lower quality during the night of the operation, with an average consumption of 25.46 L h-1 while the day shift showed 26.86 L h-1.

Método dos mínimos quadrados com penalidades: aplicação no posicionamento relativo GPS

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Carbono orgânico no solo e sua relação com os compartimentos morfológicos representativos do estado de São Paulo

Pós-graduação em Geociências e Meio Ambiente - IGCE

Caminhamento fotogramétrico utilizando o fluxo óptico filtrado

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)