Sigmae

Letter from the Organizers

2023-03-06T23:59:18+00:00

Letter from the Organizers.

Comparative study of Minas Gerais GINI index between the years 1990 to 2010 through Ordinary Kriging and Split Kriging

2023-03-06T23:59:18+00:00

The GINI index is a measure of inequality widely used to verify the income distribution of a region, it indicates the difference in income from the poorest to the richest, and varies numerically between values from 0 to 1, where the highest value indicates large concentration of income. Performing the analysis of this index in the State of Minas Gerais, using data from Atlas IBGE from 1991 to 2010, it was possible to build maps of Ordinary Kriging and Split Kriging using the Spatial Product Partition Model (SPPM). With the Split Kriging, a division in the sampling grid of the state was obtained, which showed the separation of the central region, the most economically developed in the state, in the 3 analysed periods, and the fluctuation of the GINI indices over the periods in the other regions. We conclude that there was a gradual increase in the GINI index in practically most of the mesoregions of the North of Minas, and the West of Minas remained with the lowest index during all periods compared to the other regions.

Modeling and forecasting of time series models of electricity consumption in the Northeast Region of Brazil

2023-03-06T23:59:20+00:00

Electric energy is one of the most used forms of energy, which is important for world economic growth. In this context, we analyzed the time series of electricity consumption in the Brazilian Northeast from January 1997 to May 2021. The forecast for the year 2021 was estimated based on methodologies used in the time series. The methods applied for these predictions were the Holt-Winters algorithms in the additive and multiplicative forms and the Box-Jenkins modeling methodology (we used the SARIMA and SARIMAX models). For the case of the SARIMAX model, a dummy variable was applied, with values of 1 for the months from June 2001 onwards, using the energy rationing of the Fernando Henrique Cardoso government as a reference and 0 for the previous months. The choice of model for time series adjustment was based on the criteria AIC (Akaike Information Criterion), BIC (Bayesian Information Criterion), and MSPE (Mean Prediction Forecast Error). The calculations were performed using the R statistical software. Finally, the model SARIMA (4,1,1)(2,0,0)₁₂ provided the best forecast for electricity consumption in the Brazilian Northeast.

Correlation and path analysis between teosinte characters

2023-03-06T23:59:21+00:00

The objective of this work was to verify if there are linear relationships between morphological and productive traits of teosinte plants (Zea mays ssp. mexicana). The experiment was conducted in a completely randomized design with nine sowing dates. On each date, teosinte was sown in plots of a 5 m long row, spaced 0.80 m between rows and 0.20 m between plants. In each row, five plants were marked to evaluate the morphological and productive traits. Analysis of variance and F test at 5% significance level were performed. Sowing date averages were compared using the Scott-Knott test. Pearson's matrix of linear correlation coefficients between the 16 traits based on the 45 plants was estimated. The diagnosis of multicollinearity was carried out in the correlation matrix of morphological traits and 12 path analyzes of productive traits were carried out as a function of morphological ones. Plants with more leaves have higher amounts of fresh and dry mass of leaves. Plants with more tillers have higher amounts of fresh and dry mass of tillers and shoots. The fact that there is no need to destroy the plants to count the numbers of leaves and tillers makes it possible to select plants aiming at increasing fresh and dry mass, keeping them in the field.

Bibliometric research on the use of analysis of variance in seed germination studies

2023-03-06T23:59:22+00:00

Estudos em fitotecnia com enfoque na investigação da germinação de sementes são desenvolvidos frente uma ampla gama de finalidades, sendo a análise estatística dos dados um componente imprescindível para confiabilidade e comprovação experimental. Entre os métodos estatísticos adotados, a análise de variância (ANOVA) seguida da aplicação de testes de médias caracteriza-se como a principal ferramenta utilizada na análise dos dados obtidos. Dentro deste contexto, o presente estudo foi realizado com o objetivo de avaliar quantitativamente o uso da ANOVA na produção científica envolvendo estudos com germinação de sementes, utilizando para isso uma análise bibliométrica para o período de 2000 a 2020, considerando a base de dados Web of Science. A estratégia de pesquisa consistiu na indexação de termos de busca para a ANOVA por operadores booleanos e de truncagem, restringindo a busca à artigos originais. Avaliou-se as relações das publicações entre áreas de conhecimento, evolução anual da produção científica, países e revistas nas quais os artigos foram publicados e instituições de pesquisa responsáveis pela realização dos estudos, observando predomínio de publicações desenvolvidas sob o eixo de agricultura (52,5%), crescimento da produção científica utilizando-se da ANOVA nas últimas duas décadas, e notório destaque da produção científica atribuída ao Brasil e revistas brasileiras, responsáveis por 46,7 e 44% das publicações do período, respectivamente.

Hunger and prices in Brazil: a spatial analysis of the increase in the price of the basic food basket during the covid-19 pandemic

2023-03-06T23:59:22+00:00

The advent of the Covid-19 pandemic worsened trade relations in Brazil and in the world, causing enormous social, economic and health instabilities. As a country of continental dimensions, the five macro-regions of the country are unique, some more industrialized and others not so much. And through the Global and Local Moran Index, it was possible to map and identify clusters of high and low prices of the basic food basket in the Southeast and Northeast regions, respectively. Using the SAR and CAR models, it was estimated that, with the increase of one thousand of the employed population, there was an increase in the prices of the basic food basket by R$ 0.10. The Covid-19 Pandemic triggered an increase in the prices of the basic food basket in a spatial way, as for every 1000 infected with the SarsCov2 virus in a given state, it was estimated that there was an increase in prices by R$ 1.31 (SAR) and R$ 1.21 ( CAR) in its neighbours, increasing the disheartened population in the country.

A study on the acceptance of the use of the R language in Mathematics and Statistics disciplines

2023-03-06T23:59:23+00:00

R language is an open-source programming that allows, in addition to statistical procedures, simple mathematical operations, manipulation of vectors and matrices, among other procedures. Due to these characteristics, R has been used as support to disciplines of Mathematics and Statistics from Centro de Ciências Agrárias of Universidade Federal de São Carlos, such in “Computer Basics and Coding”, “Mathematical Topics II” and “Probability and Statistical Notions”, offered for the courses of Biotechnology and Agronomic Engineering in Center. The intention of using R is that students understand better the subjects taught in classes. In this way, the aim of this work was to evaluate the acceptance of the students of the mentioned disciplines about the use of R programming language during the classes. The research utilized exploratory descriptive methods with the help of R to analyze acceptance of the students about the use of this language, by analyzing the answers of a satisfaction questionnaire that the students answered after the conclusion of each discipline. The approval rates of R usage among classes were 100% in Computer Basics and Coding; 78% in Mathematical Topics II, and 95% in Probability and Statistical Notions, which shows that R utilization, for these disciplines, makes a reliable and promising resource to help the learning and teaching process.

A comparison of multiple imputation methods for the analysis of survival data with outcome related missing covariate values

2023-03-06T23:59:23+00:00

The Cox proportional hazards model is commonly used in medical research for investigating the association between the survival time and covariates. However, it is quite common for the analysis to involve missing covariate values. A reasonable assumption is that data are censoring-ignorable MAR in the sense that missingness does not depend on censoring time but may depend on failure time. In this case, a complete cases analysis produce biased regression coefficient estimates. Through a simulation study, we compare three multiple imputation approaches for a missing covariate when missingness is survival time-dependent: (i) the method proposed by White & Royston (2009) that uses the cumulative hazard in an approximation to the imputation model, (ii) the method described by Bartlett et al. (2015) that incorporates the Cox model in the imputation process, and (iii) the CART approach, a method known to deal with skewed distributions, interaction and nonlinear relations. Simulation results show that the method of White & Royston (2009) may produce very biased estimates while the CART approach underestimates the imputation uncertainty resulting in low coverage rates. The method of Bartlett et al. (2015) had the best performance overall, with small finite sample bias and coverage rates close to nominal values. We apply the imputation approaches to a Chagas disease dataset.

Comparison of nitrogen loss in fertilizers applied to coffee plants using Gompertz model estimates

2023-03-06T23:59:24+00:00

The increase in coffee productivity is related to many factors, mainly the management of soil fertility. Nitrogen (N) is among the nutrients most demanded by the coffee and the conventional nitrogen fertilizer most used to suppress this demand is urea. However, urea has a large loss of N, mainly due to ammonia volatilization. With the aim of reducing the losses of conventional fertilizers and improving their use, researchers have developed innovations such as stabilized nitrogen fertilizers, resulting in the need to compare N losses in each one of them. The nonlinear Gompertz model is commonly used to describe the sigmoidal pattern, characteristic of the accumulated loss of N by ammonia volatilization. Thus, the objective of this study is to compare the accumulated loss of N from the nitrogen fertilizers urea, urea + NBPT and Ammonium Nitrate applied to coffee plants based on the parameters of the nonlinear Gompertz model. Comparison between treatments was performed using the method proposed by Carvalho et al. (2010), the Gompertz model was adjusted to each of the repetitions of the experiment, the analysis of variance was performed for each of the parameters, the F test was significant in all cases, so the Tukey test was applied. The analyzes were carried out in the R software at the 1% probability level. The conventional nitrogen fertilizer urea showed the highest accumulated loss of N in the coffee tree, whereas the stabilized nitrogen fertilizers urea + NBPT and ammonium nitrate did not show significant differences between them.

Application of linear regression analysis in school performance of public high schools in Brazil

2023-03-06T23:59:24+00:00

From 2010 to 2019, according to data released by INEP, there was a reduction in the number of students that make up public High School classes in Brazil and, at the same time, there was a slight increase in the number of daily classes studied. It can also be noted that the pass rate, in the same period, went from 76% to 85%. Given this information, the following questions arise: Does the number of students in the classroom inﬂuence learning? Or, will increasing classroom hours result in better learning? Or, even more emphatic, will reducing the number of students in the classroom and increasing the study hours will the result be satisfactory to the point of raising the pass rate? Such questions were analyzed and answered through regression analysis models using the statistical R software. The results obtained by such models state that reducing the number of students in the classroom and/or increasing the study hours will have as an answer an increase in the pass rate, showing that the variables related to the initial questions inﬂuence the learning of public High School students in Brazil.

Keywords: Educational Indicators; Regression Analysis; R Software.

Battle of cheeses

2023-10-21T00:12:30+00:00

Dairy consumption in Brazil is determined by family income, consumer profile and their eating and consumption habits, as well as their origins, beliefs, culture and ideologies. In 2018, the IBGE revealed that Muçareala is the most consumed cheese in Brazil ($.809kg/person/year$), followed by Minas cheese ($.565kg/person/year$), Requeijão ($.285kg/person/year$) , Prato ($.267kg/person/year$) and Parmesão ($.074kg/person/year$). On the other hand, works scraping on Twitter revealed that the most commented cheeses on this social network are, in that order, Coalho cheese, Requeijão, Cheddar, Prato, Parmesão, Muçarela, Swiss and Gorgonzola. However, the citing frequency does not necessarily reflects preference. Not even the consumption faithfully reflects the preference, after all, one consumes the cheese that fits in the family budget. To estimate the preference among the eight most popular cheeses in Brazil, this work carried out a $2^k$ bracket experiment, with $k=3$ phases (quarter-finals, semi-finals and finals). The experiment was conducted in the \emph{stories} of Instagram, using the \emph{poll} feature, and promoted entirely random matches. The result differed from the literature for consumption and citation on Twitter. The resulting grouping was: in first place Parmesão (55.9\%); second, Muçarela (47.1\%); third, Prato (43.6\%) and Coalho (34.2\%); fourth, Swiss (45.5\%), Cheddar (41.3\%), Requeijão (32.3\%) and Gorgonzola (29.4\%). Future work should develop the inferential statistics for tournament bracket experiments.

Genetic divergence between single maize hybrids in relation to ear traits

2023-03-06T23:59:25+00:00

The objective of this work was to verify if there is genetic diversity between corn single hybrids for ear characters. An experiment was carried out in the agricultural year 2021/2022, in Santa Maria, State of Rio Grande do Sul, with ten single corn hybrids being evaluated (AG8780, B2620, BM3066, DKB255, K3100, LG36680, MAXIMUS, NK467, NS75 e NS80). Ten ears per hybrid were randomly collected to evaluate the weight, in grams, of the ear, the grains in the lower, middle and upper thirds of the ear, the grains on the ear and the cob. In order to understand the expression trends of the characters and highlight those that most contribute to the total variability, principal component analysis was used. Subsequently, the dissimilarity matrix between the hybrids was determined using the Euclidean distance and the clustering was performed using the UPGMA algorithm. The dendrogram was cut using as a criterion the large level change in the clustering distance, being observed in 53,65% of dissimilarity. There is genetic divergence between single maize hybrids for ear traits with formation of two groups. The masses, of the ear and grains of the ear, present a greater contribution to the genetic diversity.

Factors associated with understanding nutritional labels reported by consumers in a city in the interior of São Paulo

2023-03-06T23:59:25+00:00

The nutritional labels help people to do choices about their products. This study evaluated the factors associated to the ease comprehension of nutritional labels related by consumers in a countryside city of São Paulo state, Brazil. A questionnaire was answered by 100 consumers of a supermarket chain, through which sociodemographic variables and information about labels were collected. For sample characterization, tables with percentage values were used; chi-square tests were performed to verify the association between the variables studied and the ease of understanding of the contents contained in the labels, and a logistic regression model was proposed. The factors that showed significant associations with the understanding of the contents on the labels were gender, age, education level and previous knowledge to their information (p<0.05). According to the logistic model, corrected by age, to assess the ease of understanding the labels, it was found that men were more likely to understand their contents than women (OR (CI 95%): 0.284 (0.092- 0.876)), as well as those people who already had some previous education on the subjects described in them (OR (CI 95%): 0.106(0.029-0.390)). People with more education reported having more problems to understand the information (OR (CI 95%): 3.572(1.257-10.152)). It was concluded that gender, age group, education level and to have accessing to prior information about labels affect the understanding of their contents; and detailed and more accessible label is desirable.

Florianópolis (SC) temperature analysis using a GAMLSS approach

2023-03-06T23:59:25+00:00

Understanding the variability of climate elements in the temperature is important for economic activities and people's daily lives. With this in mind, the main aim of this paper is to analyse the average temperature of Florianópolis, SC over a one-year period (1 July 2021 to 30 June 2022). The following explanatory variables were considered for this task: date (time), dew point temperature, total precipitation, atmospheric pressure,
humidity, and wind speed. The generalised additive models for location, scale and shape (GAMLSS) were used due to their flexibility to explain the behaviour of the response variable. The Box-Cox power exponential (BCPE) distribution was chosen to explain the response since it can deal with positive variables with varying degrees of kurtosis. A stepwise-based method was performed to select covariates in each of the distribution's parameters. The residuals obtained from the final model were found to be adequate for
explaining the data set.

Factors associated with the learning impairment perception' by students from Brazilian public universities during the Covid-19 pandemic

2023-03-06T23:59:26+00:00

The Covid-19 pandemic hit, in march 2020, the whole society, with restrictions on conviviality and the need for adaptations in all areas. Specifically in education, institutions temporarily interrupted their activities and got mobilized to continue their classes remotely, supported by technological ways that allow virtual meetings in real time. Given the uniqueness of the situation, not everyone in the academic area was prepared to replace face-to-face classrooms with virtual learning environments. In this context, this work sought to look into the impacts of remote teaching in the lives of students at brazilian public universities during the Covid-19 pandemic. A query was carried out with the students, through an electronic form, questioning, among other things, the feeling of loss in learning during the duration of remote teaching. The responses to this query composed a database analyzed using the statistical methodology of Binary Logistic Regression. Thus, this work aimed to adjust a statistical model to identify possible factors associated with the feeling of loss in the learning process, on the part of students from public universities, in relation to remote teaching. The results show that five covariables, selected through the stepwise process, had greater influence on the response variable. The highlighted covariables were: number of synchronous classes, student’s ability to concentrate, remote interaction with the teacher, remote assistance from the teacher and age group. This result reveals the role of the teacher in the learning process.

Data analysis in experiments involving potato processing: systematic mapping

2023-03-06T23:59:26+00:00

Potato processing is the subject of research in food technology, which is generally carried out through observation of experiments and statistical treatment of data. The objectives of this work were to analyze the potato processing technologies and the way in which the data treatment is being conducted. A systematic literature review was carried out in Aug/2022 considering the terms “potato not sweet” and “process”, limiting it to Brazilian articles published between 2017-2021 on “Food Science and Technology”. This search resulted in 43 articles and 17 were suitable. The grouping of works resulted in: physical damage (1 article), chemical treatment (1), infrared drying (1), frying with different types of oils (3), vacuum microwave potato chips (3), quantification (1), ozone modification (2), sonication (1), potato starch hydrogel (2) and potato starch film (2). 88.2% of the articles did not present experimental study planning in the methodology. 11.8% of the studies did not use statistical procedure and 5.9% used a simple average. ANOVA and Tukey's test were applied to 70.6% of the articles, 25.0% of which were complemented by Principal Component Analysis. ANOVA with Duncan and DCCR were used by 5.9% of the articles each. The verification of the assumptions for the application of the tests was not explained. It is possible to verify the diversity of themes studied among the technologies, but there is an indication that the experimental planning and analysis of the results demand more information in the methodology description and/or expansion of knowledge in the statistical tools.

Shrinkage effect in the Bayesian analysis of the GGE model using maximum entropy prior

2023-03-06T23:59:26+00:00

In this work, the maximum entropy principle was used to assign a priori information to the variance components of the singular values in the genotype main effects model plus genotype×environment interaction (GGE). The method was exemplified from simulated data. The results showed that the GGE model with maximum entropy priori (BGGEE) produces a shrinkage effect on the estimates of singular values, when compared with the frequentist GGE analysis or with the Bayesian GGE version that uses non-informative priors (referred to by BGGE). The BGGEE showed greater parsimony, estimating the singular values with greater contribution to the interaction effect and shrinking the estimates of singular values associated with larger dimensions to zero. Thus, BGGEE captured more pattern and discarded more noise than the typical Bayesian version. When using maximum entropy priori, it was found that the complete model and the one with only two bilinear terms are almost indistinguishable. This signals that model selection in the BGGEE fit would not be a necessary step. The method also avoids sampling problems observed when Jeffreys prior are used, resulting in proper and unimodal posterior marginal distributions.

Use of Poisson, Poisson-Gamma, Poisson-Inverse Gaussian, and Generalized Poisson-Lindley distributions for count data

2023-03-06T23:59:27+00:00

The usual analysis for discrete data is through a Poisson, Binomial or Negative Binomial distribution, via Generalized Linear Models (GLM). However, one of the precautions to be taken when analyzing discrete data is overdispersion. This term is used when the presence of variation in the data exceeds the nominal variance stipulated by the proposed model. Thus, the use of a model based on the Poisson distribution, which assumes equidispersion, would be unfounded in the presence of overdis persion. An alternative to this problem is to use mixed distributions, through models in two stages, or hierarchical, as a way to accommodate this overdispersion. The methodology of the two-stage models as sociates a distribution to the response conditioned to its average and, later, a distribution to the average parameter, so that, unconditionally, there is a compound distribution for the response variable. In this work, the classical Poisson distribution is used for counting data, and the Gama, Inverse Gaussian and Generalized Lindley distributions for the Poisson mean parameter, thus generating the Poisson-Gama,
35 Poisson-Inverse Gaussian and Generalized Poisson-Lindley. So, the main objective of this work is to present these hierarchical models, or models in two stages, that allow the modeling of count data with overdispersion. Futhermore, some types of residues of the structure of the MLGs were also approached, adapted for the composite distributions.