Potencial da espectroscopia no infravermelho próximo para distinção de carvão de madeira de Eucalyptus e nativa

The objective of this study was to evaluate the potential of near infrared spectroscopy (NIRS) associated with multivariate statistics to distinguish coal produced from wood of planted and native forests. Timber forest species from the C errado (Cedrela sp., Aspidosperma sp., Jacaranda sp. and unknown species) and Eucalyptus clones from forestry companies (Vallourec and Cenibra) were carbonized in the final temperatures of 300, 500 and 700°C. In each heat treatment were carbonized 15 specimens of each vegetal material totaling 270 samples (3 treatments x 15 reps x 6 materials) produced in 18 carbonization (3 treatments x 6 materials). The acquisition of the spectra of coals in the near infrared using a spectrometer was performed. Principal Component Analysis (PCA) and Partial Least Squares Regression (PLS-R) were carried out in the spectra. NIR Spectroscopy associated with PCA was not able to differentiate charcoals produced from native and planted woods when utilizing all carbonized samples at different temperatures in the same analysis; The PCA of all charcoals was able to distinguish the samples depending on temperature in which they were carbonized. However, the separation of native and planted charcoal was possible when the samples were analyzed separately by final temperature. The prediction of native or planted classes by PLS-R presented better performance for samples carbonized at 300°C followed by those at 500°C, 700°C and for all together.

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.

Desenvolvimento de barra alimentícia adicionada de café: estudo de marketing

The consumption of snack bars is based especially on the demand for practical and nutritious food. Coffee is highlighted for being appreciated and consumed worldwide, presenting elevated antioxidant activity, in addition to peculiar sensorial attributes. Therefore, it has great potential for use in many formulations. However, the success in the acceptance of a new product also derives from adequate marketing strategies. In this context, the present study aimed at evaluating the feasibility of introducing to the market a snack bar added with coffee, by means of sensorial acceptance and purchase intent of the consumers, in addition to identifying the best concept and the possible market segments. This work was a qualitative, by means of a focus group (content analysis), and quantitative research, by means of sensorial analysis and structures questionnaires (descriptive – frequency distribution, arithmetic mean, crosstabs and t test – and multivariate – cluster and discriminate analysis - statistical techniques). With the results, we showed that the main aspects considered by the consumers regarding the snack bar added with coffee. According to the qualitative evaluation, the consumer prefers packaging with matte colors ranging in the tones related to the coffee grain. The analysis of the quantitative data allows us to infer that the evaluations of the product regarding overall impression, purchase intent, preference and expectation before and after consuming the product are better for packaging containing the information “special coffee flavor – 100% arabic”. Regarding market segment, it was possible to conclude that, of the three extracted groups, the group of “healthy and conscious consumers” was the segment with higher potential for exploitation regarding purchase and consumption of the snack bar added with coffee.

Propriedades e aspectos geométricos de estimadores tipo James-Stein e do estimador de Hartigan

The James-Stein estimator is a biased shrinkage estimator with uniformly smaller risk than the risk of the sample mean estimator for the mean of multivariate normal distribution, except in the one-dimensional or two-dimensional cases. In this work we have used more heuristic arguments and intensified the geometric treatment of the theory of James-Stein estimator. New type James-Stein shrinking estimators are proposed and the Mahalanobis metric used to address the James-Stein estimator. . To evaluate the performance of the estimator proposed, in relation to the sample mean estimator, we used the computer simulation by the Monte Carlo method by calculating the mean square error. The result indicates that the new estimator has better performance relative to the sample mean estimator.