|
Dissertations |
|
1
|
-
TAMARA TAVARES DE MELO
-
Gradings on the Grassmann algebra by the infinite cyclic group: polynomial identities and PI-equivalence.
-
Advisor : ALAN DE ARAUJO GUIMARAES
-
COMMITTEE MEMBERS :
-
ALAN DE ARAUJO GUIMARAES
-
ALEXEY KUZMIN
-
DAVID LEVI DA SILVA MACÊDO
-
DIOGO DINIZ PEREIRA DA SILVA E SILVA
-
Data: Feb 24, 2023
-
-
Show Abstract
-
Let E be the infinite dimensional Grassmann algebra over a field F of characteristic zero and Z be the infinite cyclic group. In the development of Kemer’s Theory, the algebra E plays a crucial role. In recent years, the abelian gradings on E and the respective graded identities have been addressed in several articles, and it is still a very fertile topic at the research level. Therefore, the focus of our dissertation is to study recent results regarding gradings on E by the group Z. We will study results on the construction of gradings on E and, using methods from elementary number theory, we will describe the Z-graded polynomial identities for the so-called 2-induced Z-gradings on E of full support. As a consequence of this fact, we will show some examples of Z-gradings in E, which are PI-equivalent, but not Z-isomorphic. This is the first example of graded algebras with infinite support that are PI-equivalent but not isomorphic as graded algebras. Furthermore, we will introduce the notion of central Z-gradings on E and show that their Z-graded polynomial identities are related to the Z2-graded polynomial identities of E.
|
|
2
|
-
FRANKLIN DIEGO DE LIMA RODRIGUES
-
Sequence segmentation in Markov Chain using penalized maximum likelihood
-
Advisor : FRANCISCO MOISES CANDIDO DE MEDEIROS
-
COMMITTEE MEMBERS :
-
FRANCISCO MOISES CANDIDO DE MEDEIROS
-
BRUNO MONTE DE CASTRO
-
ELIARDO GUIMARAES DA COSTA
-
ANDRESSA CERQUEIRA
-
Data: Mar 27, 2023
-
-
Show Abstract
-
The sequence segmentation problem has the objective of partitioning a sequence or a set
or a set of them into a finite number of distinct segments as homogeneous as possible. as
possible. In this paper, we consider the problem of segmenting a set of random sequences,
with values in a finite alphabet E, into a finite number of independent blocks. independent
blocks. Under the assumption that the data follows a Markov chain, the problem consists
in estimating the number and position of independence (or change) points. To this end,
we propose to use the penalized maximum likelihood criterion with the objective to
simultaneously infer the number and position of change points. The main result of our
work is the demonstration of the theorem that guarantees the strong consistency of the
consistency of the set of cut-off point estimators for a sufficiently large number of samples
sufficiently large.
|
|
3
|
-
JEFFERSON HENRIQUE DA SILVA
-
A new topological approach to interval metric
-
Advisor : FAGNER LEMOS DE SANTANA
-
COMMITTEE MEMBERS :
-
ANNAXSUEL ARAUJO DE LIMA
-
BENJAMIN RENE CALLEJAS BEDREGAL
-
FAGNER LEMOS DE SANTANA
-
REGIVAN HUGO NUNES SANTIAGO
-
SIDARTA ARAUJO DE LIMA
-
Data: Mar 28, 2023
-
-
Show Abstract
-
In this work we make a topological approach to the interval metric different from the
one based on the i-metric, which does not make use of the addition operation of Moore
arithmetic. Here we will use an admissible order that refines the KM order to modify the
triangular inequality and make it more like the case of usual metrics.
|
|
4
|
-
BARBARA KALINE DE SOUSA
-
Diagnostic Analysis in Bell Regression Models
-
Advisor : ARTUR JOSE LEMONTE
-
COMMITTEE MEMBERS :
-
ARTUR JOSE LEMONTE
-
ELIARDO GUIMARAES DA COSTA
-
JUVÊNCIO SANTOS NOBRE
-
Data: Mar 31, 2023
-
-
Show Abstract
-
The class of Bell regression models is an interesting alternative to the usual class of Poisson regression models for response variables in count form, mainly in the presence of overdispersion. In this work, diagnostic techniques such as global influence and local influence will be developed for the Bell regression model. In particular, analytical expressions for the normal curvature to study local influence will be derived under different perturbation schemes. Finally, the diagnostic techniques developed will be applied to real data sets.
|
|
5
|
-
EDWIN CASTRO FERNANDES DOS SANTOS
-
Performance Evaluation and Application of EWMA Control Chart for the stochastic process POMINAR(1)
-
Advisor : ANDRE LUIS SANTOS DE PINHO
-
COMMITTEE MEMBERS :
-
ANDRE LUIS SANTOS DE PINHO
-
LUZ MILENA ZEA FERNANDEZ
-
FRANCISCO FELIPE DE QUEIROZ
-
Data: Mar 31, 2023
-
-
Show Abstract
-
In this work we propose to evaluate the performance of the EWMA control chart, adapting it to the first-order mixed autoregressive model with Poisson innovations, called POMINAR(1), which is composed of two operators known as thinning binomial and thinning Poisson. The objective is to compare the results obtained with those of the Shewhart control chart, and to show that the EWMA control chart is more efficient to detect deviations in the process mean below 1.5 standard deviation. For this, the EWMA control chart and its expectation are defined. Two theorems and two corollaries are proposed in order to define the variance according to the size of the rational subgroup. Moreover, the EWMA upper and lower control limits will be set, to analyze its performance. After that, an analysis will be made comparing the results obtained from a simulation using the EWMA control chart with the results obtained using the Shewhart control chart. Finally, two applications with real data using the EWMA control chart are presented. The first situation relates to the Criminal Data Section on the Forecasting Principles website. The chosen variable represents the number of monthly robberies reported in political district nº 12, in Pittsburgh (USA), from Jan/1990 to Dec/2001, with a total of 144 observations. The second situation is the count of different IP addresses recorded in a period of two minutes in duration on the server of the Department of Statistics of the University of Wüsrzburg, on November 29, 2005, between 10 a.m. and 6 p.m. with 241 observations.
|
|
6
|
-
ISRAEL COSTA SMITH DE MEDEIROS
-
Residuals in Bell-Touchard regression models
-
Advisor : ARTUR JOSE LEMONTE
-
COMMITTEE MEMBERS :
-
ALDO WILLIAM MEDINA GARAY
-
ARTUR JOSE LEMONTE
-
FIDEL ERNESTO CASTRO MORALES
-
Data: Apr 20, 2023
-
-
Show Abstract
-
The Bell-Touchard distribution and its regression model, are a promising alternative to the statistical models that are already established in the count data modelling, as Poisson and Negative Binomial models. Count data are observations such that the variable assumes non-negative integer values and are useful, for example, to modelling the number of claims that happened in a given period of time, which are of interest to insurance companies, for example. The Poisson model, for this purpose, is not a model that does work well with the overdispersion problem, a situation in which the variance is greater than the expectation. Alternatives to deal with this kind of problem emerged, being proposed the zero-inflated models and the Negative Binomial model. The Bell-Touchard model, that is a generalization of Bell model, is a recent alternative that tries to solve this kind of problem. In this master’s dissertation, a deeper research is made about residuals in the Bell-Touchard regression model and the main goal is to improve the academic literature about count data.
|
|
7
|
-
CARLA DE MORAES APOLINARIO
-
A guide to design of experiments in education
-
Advisor : CARLA ALMEIDA VIVACQUA
-
COMMITTEE MEMBERS :
-
CARLA ALMEIDA VIVACQUA
-
ANDRE LUIS SANTOS DE PINHO
-
JANAINA WEISSHEIMER
-
ANDRE LUIS CALADO ARAUJO
-
Data: Jun 27, 2023
Ata de defesa assinada:
-
-
Show Abstract
-
Education in Brazil has presented and continues to present challenges of various kinds. During the 20th century the main educational challenge was access to schools and combating the high rate of illiteracy. The construction of public schools as a way of facilitating access to basic education led to other challenges that persist to the present day, such as the low quality of the education offered, a constant and relevant theme throughout the world, since the quality of education is a critical issue for the development of a country. Several studies have been carried out with the aim of identifying ways to improve teaching and learning and one way to identify best practices is to conduct a statistical experiment as a way to establish a causal relationship between different factors and students' academic performance. Furthermore, these studies make it possible to evaluate the impact of public policies and government programs aimed at improving education, helping to direct resources more efficiently and effectively. As important as performing these interventions is conducting them properly so that it is possible to obtain reliable data. With the wide variety of existing statistical techniques, it is common for researchers from other areas to innapropriately use of experimental statistics when conducting an intervention. In this work, a literature review is carried out as a way of mapping studies that use experimental statistics in the educational context, in order to identify the difficulties found by researchers, as well as good practices carried out, in addition to carrying a case study to identify possible practice difficulties that were not noted in the review. This work aims to disseminate the correct use of experimental statistics techniques in a clear, objective and understandable way for researchers from other areas who are not familiar with that subject. To achieve this goal, an accessible and simplified language is adopted when explaining complex concepts, using concrete examples and graphics that help to visualize the statistical concepts. Moreover, the importance of using controlled experiments and randomization are emphasized, which allow inferences followed up on the basis of quantitative evidence. Additionally, as part of the proposed work, a guide will be developed that will present the steps and important points to plan an experiment properly, guaranteeing the validity and reliability of the results obtained. This guide will include guidance on designing the experiment, choosing sample size, selecting experimental and control groups, randomization, selecting appropriate statistical tests, and other aspects crucial to successful experimental research. It is hoped that this guide will provide a useful reference for researchers from other fields who wish to use experimental statistics correctly and effectively in their research.
|
|
8
|
-
ANA BEATRIZ GOMES DA SILVA
-
Z2-gradings of the Grassmann algebra: construction, PI-equivalence, isomorphisms
-
Advisor : ALAN DE ARAUJO GUIMARAES
-
COMMITTEE MEMBERS :
-
ALAN DE ARAUJO GUIMARAES
-
CLAUDEMIR FIDELES BEZERRA JUNIOR
-
ELAINE GOUVEA PIMENTEL
-
LUCIO CENTRONE
-
Data: Aug 30, 2023
-
-
Show Abstract
-
The focus of our dissertation is to develope a study on the Z2-gradings of the infinite- dimensional Grassmann algebra E. The homogeneous Z2-gradings and their Z2-grade identities
are already well known in the literature, see (VINCENZO; SILVA, 2009), (CENTRONE, 2011) and (GONÇALVES, 2018). Nevertheless, the construction of non-homogeneous Z2-gradings demands the use of the duality between these structures and automorphisms of order ≤ 2 acting on E. Through this, we will study the non-homogeneous Z2-gradings, producing results
on their construction. In a second moment, we will investigate under what conditions a non- homogeneous Z2-grading is isomorphic to the canonical Z2-grading of E. Finally, we will
provide a Z2-grading on E in which there is no non-zero element of the space L homogeneous, refuting the conjecture presented in (GUIMARÃES; KOSHLUKOV, 2023).
|
|
9
|
-
MATHEUS WINGLES ALVES RIBEIRO
-
Space-temporal Analysis of the Homicides Frequency in the Natal-RN districts from 2011 to 2021
-
Advisor : FIDEL ERNESTO CASTRO MORALES
-
COMMITTEE MEMBERS :
-
ELIARDO GUIMARAES DA COSTA
-
FIDEL ERNESTO CASTRO MORALES
-
FRANCISCO ALIXANDRE ÁVILA RODRIGUES
-
Data: Nov 22, 2023
-
-
Show Abstract
-
Areal Units comprises information, quantities, or indicators that represent contiguous areas of a specific region, such as countries, cities, among others. They are subjects of study in various fields such as Geopolitics and Cartography, Urban Planning, Environment, Public Administration, and Health. Several software programs have been developed to assist in processing these types of data, such as CARBayesST, developed for the R language. It utilizes space-time structured Conditional Autoregressive Priors (CAR) within a Bayesian Hierarchical framework and employs Monte Carlo simulations via Markov Chains. The phenomenon of violence has existed since the dawn of civilizations. It is the result of the complex interaction of various elements, exacerbated by segregation and exclusion stemming from the urbanization process. The term "crime" is used to describe the violation of the laws that govern a society, which are regulated by a justice system backed by the State. The city of Natal, the capital of Rio Grande do Norte, transitioned from being the least violent city in the country in 2003 to the most violent in 2017, with a rate of 102.56 homicides per 100,000 inhabitants. In light of this, an analysis was conducted to assess the impacts on the number of occurrences of Intentional Lethal Violent Crimes (CVLIs), which encompass deliberate homicides, bodily injury followed by death, fatal robberies, feminicides, and other offenses leading to loss of life (excluding deaths resulting from state security actions) in the neighborhoods of Natal from 2011 to 2021, utilizing the CARBayesST package. The assessment of the best fit and convergence was conducted based on the criteria proposed by Geweke et al. (1991), Spiegelhalter et al. (2002), Watanabe and Opper (2010), and Congdon (2005). As covariates, information regarding public lighting expenditure in megawatt-hours (Mwh), the number of public facilities such as parks, police stations, and schools, the average nominal income in terms of minimum wages, the illiteracy rate, the number of enterprises, and the percentage of urban pavement were selected. This information was extracted from the Municipal Secretariat of Environment and Urbanism and the 2010 Census. Additionally, population estimates and population density were obtained from the Worldpop Project (2013), which utilizes census and geospatial data, along with satellite imagery, statistically modeling them to produce population distribution estimates in various global areas. Since the study period encompasses the COVID-19 pandemic, based on Freitas (2021), the addition of a dummy covariate for the pandemic years was considered necessary.
|
|