Rafael Freitas Souza

Prof. Dr. Rafael Freitas Souza

University of São Paulo, São Paulo, Brazil
orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
13 May 2021 in Mathematics
Verified
Journal Article
Open access
PDF file
LFLuiz Paulo Fávero
Luiz Paulo Fávero
JHJoseph F. Hair
Joseph F. Hair
Rafael Freitas SouzaRafael Freitas Souza
Rafael Freitas Souza
MAMatheus Albergaria
Matheus Albergaria
Talles BrugniTalles Brugni
Talles Brugni
Our article explores an underused mathematical analytical methodology in the social sciences. In addition to describing the method and its advantages, we extend a previously reported application of mixed models in a well-known database about corruption in 149 countries. The dataset in the mentioned study included a reasonable amount of zeros (13.19%) in the outcome variable, which is typical of this type of research, as well as quite a bit of social sciences research. In our paper, present detailed guidelines regarding the estimation of models where the data for the outcome variable includes an excess number of zeros, and the dataset has a natural nested structure. We believe our research is not likely to reject the hypothesis favoring the adoption of mixed modeling and the inflation of zeros over the original simpler framework. Instead, our results demonstrate the importance of considering random effects at country levels and the zero-inflated nature of the outcome variable.

14 June 2020 in Statistics, Optimization & Information Computing
Verified
Journal Article
Open access
PDF file
LFLuiz Paulo Lopes Fávero
Luiz Paulo Lopes Fávero
PBPatrícia Belfiore
Patrícia Belfiore
MSMarco Aurélio dos Santos
Marco Aurélio dos Santos
Rafael Freitas SouzaRafael Freitas Souza
Rafael Freitas Souza
Stata has several procedures that can be used in analyzing count-data regression models and, more specifically, in studying the behavior of the dependent variable, conditional on explanatory variables. Identifying overdispersion in countdata models is one of the most important procedures that allow researchers to correctly choose estimations such as Poisson or negative binomial, given the distribution of the dependent variable. The main purpose of this paper is to present a new command for the identification of overdispersion in the data as an alternative to the procedure presented by Cameron and Trivedi [5], since it directly identifies overdispersion in the data, without the need to previously estimate a specific type of count-data model. When estimating Poisson or negative binomial regression models in which the dependent variable is quantitative, with discrete and non-negative values, the new Stata package overdisp helps researchers to directly propose more consistent and adequate models. As a second contribution, we also present a simulation to show the consistency of the overdispersion test using the overdisp command. Findings show that, if the test indicates equidispersion in the data, there are consistent evidence that the distribution of the dependent variable is, in fact, Poisson. If, on the other hand, the test indicates overdispersion in the data, researchers should investigate more deeply whether the dependent variable actually exhibits better adherence to the Poisson-Gamma distribution or not.

12 January 2024 in Axioms
Verified
Journal Article
Open access
PDF file
Rafael Freitas SouzaRafael Freitas Souza
Rafael Freitas Souza
FLFabiano Lima
Fabiano Lima
HCHamilton Luiz Corrêa
Hamilton Luiz Corrêa
This tutorial delves into the application of proportional odds-type ordinal logistic regression to assess the impact of incorporating both fixed and random effects when predicting the rankings of Brazilian universities in a well-established international academic assessment utilizing authentic data. In addition to offering valuable insights into the estimation of ordinal logistic models, this study underscores the significance of integrating random effects into the analysis and addresses the potential pitfalls associated with the inappropriate treatment of phenomena exhibiting categorical ordinal characteristics. Furthermore, we have made the R language code and dataset available as supplementary resources for the replication.

26 July 2024 in ReMark - Revista Brasileira de Marketing
Verified
Journal Article
Open access
PDF file
LALuiz Guilherme Rodrigues Antunes
Luiz Guilherme Rodrigues Antunes
Rafael Freitas SouzaRafael Freitas Souza
Rafael Freitas Souza
AFAna Cristina Ferreira
Ana Cristina Ferreira
FZFernanda de Aguiar Zanola
Fernanda de Aguiar Zanola
LBLuiz Henrique de Barros Vilas Boas
Luiz Henrique de Barros Vilas Boas
Objective: This essay aims to discuss the rigor of the projective technique with a qualitative focus. Results: The main criticisms of projective techniques are not appropriate for qualitative research. As an alternative, the criteria proposed by Lincoln and Guba (1985) have been established. They are credibility, transferability, dependability and confirmability. Theoretical/Methodological Contributions: The essay demonstrates the methodological contribution. It also illustrates how the projective technique can be applied to build your rigor through a qualitative lens.

8 April 2023 in Paranoá: cadernos de arquitetura e urbanismo
Verified
Journal Article
Open access
PDF file
VSVinícius De Azevedo Silva
Vinícius De Azevedo Silva
Rafael Freitas SouzaRafael Freitas Souza
Rafael Freitas Souza
MOMateus Peixoto Oliveira
Mateus Peixoto Oliveira
FSFrancisco Lledo dos Santos
Francisco Lledo dos Santos
O desenvolvimento econômico associado a aspectos como a desigualdade social são processos que provocam a deterioração de recursos ambientais. São emergenciais o aperfeiçoamento das tecnologias para combater os efeitos dos desastres naturais, como a melhoria dos processos de transformação de chuva em vazão e da modelagem dos fenômenos hidrológicos em bacias hidrográficas. O objetivo desta comunicação científica foi obter, com o auxílio de técnicas de machine learning, previsões do comportamento hidrológico na Bacia do Rio Bananal. Essas informações reunidas foram submetidas aos seguintes modelos: redes neurais artificiais de aprendizado profundo (Deep Learning - InceptionTime, Resnet, FCN e ResCNN) e de aprendizado de máquina (Machine Learning - regressão linear, árvore de decisão e support-vector machine), e gradient boosting para levantar séries históricas consistentes e comparar os padrões de precipitação e da vazão (modelo chuva-vazão) do curso hídrico. Foram utilizadas as séries temporais médias diárias de 2002 a 2014 para treinamento a fim de estabelecer um comportamento otimizado para 2015. Foi possível concluir que o coeficiente R² com a melhor performance foi da arquitetura InceptionTime, com RMSE de 4.62, MAE de 2.36. O resultado com amior desempenho foi a árvore de decisão com R2 de 0.73.

20 September 2021 in International Journal of Globalisation and Small Business
Verified
Journal Article
Closed access
MSMarco Aurélio Dos Santos
Marco Aurélio Dos Santos
LFLuiz Paulo Fávero
Luiz Paulo Fávero
NFNuno Manoel Martins Dias Fouto
Nuno Manoel Martins Dias Fouto
PBPatrícia Belfiore
Patrícia Belfiore
Rafael Freitas SouzaRafael Freitas Souza
Rafael Freitas Souza
Credit access has an important role for small and medium enterprises (SMEs) to finance their activities. The purpose of this paper is to investigate the importance of firm, sector and country characteristics in credit access of SMEs in emerging economies. Through data collected from the World Bank enterprise surveys, we study 107,652 observations from 139 countries over the period 2006-2018 and estimate a multilevel logit model, what allows the comparison, in terms of quality of the prediction, with a traditional credit logit model. The results show that country characteristics related to banking sector development and informational credit system are statistically significant. Additionally, informational characteristics of firms play an important role in the probability of having credit access by SMEs. This paper also fills an important methodological gap, since logit models that take into account a multilevel perspective are rarely explored in studies involving credit access of SMEs in emerging economies.