Revista Brasileira de Gestão De Negócios, Jun 30, 2008
Processo de Avaliação: Double Blind Review Trabalho apresentado em versão preliminar (working pap... more Processo de Avaliação: Double Blind Review Trabalho apresentado em versão preliminar (working paper) na Universidade do Porto Portugal. RESUMO O presente trabalho apresenta uma revisão da literatura sobre segmentação de mercado, através de uma discussão em torno das bases de segmentação e métodos de classificação. As bases de segmentação são organizadas em dois eixos observáveis/não observáveis e gerais/específicas do produto e avaliadas em função das propriedades desejáveis para uma segmentação efetiva: identificabilidade, substancialidade, acessibilidade, estabilidade, acionabilidade e grau de resposta. Os métodos de classificação são também organizados em três classes, em função do formato da matriz de partição que produzem, a referir: nãosobreposta, sobreposta ou difusa.
Este trabalho propõe-se apresentar uma revisão dos modelos mistura de regressão para variáveis no... more Este trabalho propõe-se apresentar uma revisão dos modelos mistura de regressão para variáveis normais, frequentes em estudos de pesquisa de mercados. De facto, exemplos de aplicação destes modelos continuam a acumular na literatura do marketing, dadas as suas vantagens relativas. Adicionalmente, estes modelos são facilmente implementados, devido à sua incorporação em vários programas comerciais de pesquisa de mercados. Pretende-se apresentar as raízes históricas que motivaram o desenvolvimento dos modelos mistura de regressão (regressions, clusterwise regression e modelos mistura finitos) e rever a formulação do modelo base, bem como as suas extensões principais aos cenários de dados em painel e estudos de análise conjunta. Palavras-chave: segmentação de mercado, modelos mistura de regressão, dados normais.
The purpose of this work is to determine how well, criteria designed to help the selection of the... more The purpose of this work is to determine how well, criteria designed to help the selection of the adequate number of market segments, perform in recovering small niche segments, in mixture regressions of normal data, with experimental data. The simulation experiment compares several segment retention criteria, including information criteria and classificationbased criteria. We also address the impact of distributional misspecification on segment retention criteria success rates. This study shows that Akaike's Information criterion with penalty factors of 3 and 4, rather than the traditional value of 2, are the best segment retention criteria to use in recovering small niche segments. Although these criteria were designed for the specific context of mixture models, they are rarely applied in the marketing literature.
The aim of this work is to determine how well criteria designed to help the selection of the adeq... more The aim of this work is to determine how well criteria designed to help the selection of the adequate number of mixture components perform in mixture regressions of normal data. We address this research question based on results of an extensive experimental design. The simulation experiment compares several criteria (26), including information criteria and classification-based criteria. In this full factorial design we manipulate 9 factors and 22 levels, namely: true number of segments (2 or 3), mean separation between segments (low, medium or high), number of consumers (100 or 300), number of observations per consumer (5 or 10), number of predictors (2, 6 or 10), measurement level of predictors (binary, metric or mixed), error variance (20% or 60%), minimum segment size (5-10%, 10-20% or 20-30%) and error distribution (normal versus uniform). The performance of the segment retention criteria is evaluated by their success rates; we also investigate the influence of experimental factors and their levels on success rates. The best results were obtained for the criteria AIC 3 , AIC 4 , HQ, ICLBIC and ICOMPLBIC. BIC and CAIC also perform well with large samples and a large number of market segments.
Despite the widespread application of finite mixture models, the decision of how many classes are... more Despite the widespread application of finite mixture models, the decision of how many classes are required to adequately represent the data is, according to many authors, an important, but unsolved issue. This work aims to review, describe and organize the available approaches designed to help the selection of the adequate number of mixture components (including Monte Carlo test procedures, information criteria and classification-based criteria); we also provide some published simulation results about their relative performance, with the purpose of identifying the scenarios where each criterion is more effective (adequate).
The aim of this work is to (1) analyse whether countries differ on political indicators (democrac... more The aim of this work is to (1) analyse whether countries differ on political indicators (democracy, rule of law, government effectiveness and corruption) and (2) study whether countries with different political profiles are associated with different levels of economic, human development and gender-related development indicators. Using a fuzzy classification approach (fuzzy k-means algorithm), we propose a typology of 124 countries based on 10 political variables. Six segments are identified; these political groups implicate the access to different levels of economic and human development. In this study evidence of a positive but not perfect relationship between democracy and economic and human development is observed, thus presenting new insights for the understanding of the heterogeneity of behaviors relatively to political indicators.
Iberoamerican Journal of Strategic Management, Dec 1, 2015
Although internationalization efforts in higher education have become increasingly driven by econ... more Although internationalization efforts in higher education have become increasingly driven by economic considerations, this is not the case for all initiatives, particularly those at the level of curriculum, where academic, social/cultural, ethical, political, and even environmental rationales feature more strongly.
O presente artigo propoe-se rever a literatura em tomo da segmentacao de mercado, relevando o pap... more O presente artigo propoe-se rever a literatura em tomo da segmentacao de mercado, relevando o papel das bases de segmentacao. Com o proposito de orientar a tomada de decisao neste contexto, apresenta-se um sistema orientado para a classificacao e avaliacao das variaveis e caracteristicas mais frequentemente usadas na segmentacao do mercado consumidor
Revista Brasileira de Gestão e Desenvolvimento Regional, 2009
This study considers 11 variables of technological development and 10 variables of political char... more This study considers 11 variables of technological development and 10 variables of political character so as to classify 54 countries (those which had published information on the 21 variables) in two sets of groups. We used the fuzzy k-means method that admits the overlapping classification (a country may belong to more than one group). Three groups of countries were identified with base on technological development, and four groups with base on the respective political development. These groups can be hierarchized and are associated to different levels of GDP per capita and HDI-Human Development Index.
International Journal of Innovation and Learning, 2016
Authors commonly agree that the identity of a brand is internally connected with staff and extern... more Authors commonly agree that the identity of a brand is internally connected with staff and externally connected with the consumers and the rest of the stakeholders. Brand management studies are much focused on the external part, mainly on consumers. This research follows a different agenda exploring the brand identity dimensions by measuring the brand identity prism developed by Kapferer, both internally and externally. The measurement of brand identity is scarce in brand management literature. A reliable, valid and unique brand identity scale that empirically establishes the construct's dimensionality has yet to be developed in a highly consumer involvement context. This paper reports the findings of a research conducted at 235 engineering higher education students. Data were analysed using confirmatory factor analysis. Findings reveal that the brand identity prism is moderated by brand culture. This research also gave important insights regarding the theory proposed by Kapferer regarding the external brand identity.
In this paper we investigate the behaviour of credit default in start-up companies. Using a logit... more In this paper we investigate the behaviour of credit default in start-up companies. Using a logit regression technique on a panel data of 1430 start-ups and considering a tracking period of three years, we tested the impact on the probability of occurrence of the first credit event in financing agreements due to variables grouped into three categories: financial capital, human capital and industry dynamics. We concluded from a financial point of view, that the support provided by partners in the financing of the company’s activity, the intensity of use of assets under management and reduced debt pay-back periods, were decisive in mitigating risk of default. In addition we found that the occurrence of a credit event will only be as limited as higher the quality of human capital held by the promoter of the project in terms of educational background and management experience.
Revista Brasileira de Gestão De Negócios, Jun 30, 2008
Processo de Avaliação: Double Blind Review Trabalho apresentado em versão preliminar (working pap... more Processo de Avaliação: Double Blind Review Trabalho apresentado em versão preliminar (working paper) na Universidade do Porto Portugal. RESUMO O presente trabalho apresenta uma revisão da literatura sobre segmentação de mercado, através de uma discussão em torno das bases de segmentação e métodos de classificação. As bases de segmentação são organizadas em dois eixos observáveis/não observáveis e gerais/específicas do produto e avaliadas em função das propriedades desejáveis para uma segmentação efetiva: identificabilidade, substancialidade, acessibilidade, estabilidade, acionabilidade e grau de resposta. Os métodos de classificação são também organizados em três classes, em função do formato da matriz de partição que produzem, a referir: nãosobreposta, sobreposta ou difusa.
Este trabalho propõe-se apresentar uma revisão dos modelos mistura de regressão para variáveis no... more Este trabalho propõe-se apresentar uma revisão dos modelos mistura de regressão para variáveis normais, frequentes em estudos de pesquisa de mercados. De facto, exemplos de aplicação destes modelos continuam a acumular na literatura do marketing, dadas as suas vantagens relativas. Adicionalmente, estes modelos são facilmente implementados, devido à sua incorporação em vários programas comerciais de pesquisa de mercados. Pretende-se apresentar as raízes históricas que motivaram o desenvolvimento dos modelos mistura de regressão (regressions, clusterwise regression e modelos mistura finitos) e rever a formulação do modelo base, bem como as suas extensões principais aos cenários de dados em painel e estudos de análise conjunta. Palavras-chave: segmentação de mercado, modelos mistura de regressão, dados normais.
The purpose of this work is to determine how well, criteria designed to help the selection of the... more The purpose of this work is to determine how well, criteria designed to help the selection of the adequate number of market segments, perform in recovering small niche segments, in mixture regressions of normal data, with experimental data. The simulation experiment compares several segment retention criteria, including information criteria and classificationbased criteria. We also address the impact of distributional misspecification on segment retention criteria success rates. This study shows that Akaike's Information criterion with penalty factors of 3 and 4, rather than the traditional value of 2, are the best segment retention criteria to use in recovering small niche segments. Although these criteria were designed for the specific context of mixture models, they are rarely applied in the marketing literature.
The aim of this work is to determine how well criteria designed to help the selection of the adeq... more The aim of this work is to determine how well criteria designed to help the selection of the adequate number of mixture components perform in mixture regressions of normal data. We address this research question based on results of an extensive experimental design. The simulation experiment compares several criteria (26), including information criteria and classification-based criteria. In this full factorial design we manipulate 9 factors and 22 levels, namely: true number of segments (2 or 3), mean separation between segments (low, medium or high), number of consumers (100 or 300), number of observations per consumer (5 or 10), number of predictors (2, 6 or 10), measurement level of predictors (binary, metric or mixed), error variance (20% or 60%), minimum segment size (5-10%, 10-20% or 20-30%) and error distribution (normal versus uniform). The performance of the segment retention criteria is evaluated by their success rates; we also investigate the influence of experimental factors and their levels on success rates. The best results were obtained for the criteria AIC 3 , AIC 4 , HQ, ICLBIC and ICOMPLBIC. BIC and CAIC also perform well with large samples and a large number of market segments.
Despite the widespread application of finite mixture models, the decision of how many classes are... more Despite the widespread application of finite mixture models, the decision of how many classes are required to adequately represent the data is, according to many authors, an important, but unsolved issue. This work aims to review, describe and organize the available approaches designed to help the selection of the adequate number of mixture components (including Monte Carlo test procedures, information criteria and classification-based criteria); we also provide some published simulation results about their relative performance, with the purpose of identifying the scenarios where each criterion is more effective (adequate).
The aim of this work is to (1) analyse whether countries differ on political indicators (democrac... more The aim of this work is to (1) analyse whether countries differ on political indicators (democracy, rule of law, government effectiveness and corruption) and (2) study whether countries with different political profiles are associated with different levels of economic, human development and gender-related development indicators. Using a fuzzy classification approach (fuzzy k-means algorithm), we propose a typology of 124 countries based on 10 political variables. Six segments are identified; these political groups implicate the access to different levels of economic and human development. In this study evidence of a positive but not perfect relationship between democracy and economic and human development is observed, thus presenting new insights for the understanding of the heterogeneity of behaviors relatively to political indicators.
Iberoamerican Journal of Strategic Management, Dec 1, 2015
Although internationalization efforts in higher education have become increasingly driven by econ... more Although internationalization efforts in higher education have become increasingly driven by economic considerations, this is not the case for all initiatives, particularly those at the level of curriculum, where academic, social/cultural, ethical, political, and even environmental rationales feature more strongly.
O presente artigo propoe-se rever a literatura em tomo da segmentacao de mercado, relevando o pap... more O presente artigo propoe-se rever a literatura em tomo da segmentacao de mercado, relevando o papel das bases de segmentacao. Com o proposito de orientar a tomada de decisao neste contexto, apresenta-se um sistema orientado para a classificacao e avaliacao das variaveis e caracteristicas mais frequentemente usadas na segmentacao do mercado consumidor
Revista Brasileira de Gestão e Desenvolvimento Regional, 2009
This study considers 11 variables of technological development and 10 variables of political char... more This study considers 11 variables of technological development and 10 variables of political character so as to classify 54 countries (those which had published information on the 21 variables) in two sets of groups. We used the fuzzy k-means method that admits the overlapping classification (a country may belong to more than one group). Three groups of countries were identified with base on technological development, and four groups with base on the respective political development. These groups can be hierarchized and are associated to different levels of GDP per capita and HDI-Human Development Index.
International Journal of Innovation and Learning, 2016
Authors commonly agree that the identity of a brand is internally connected with staff and extern... more Authors commonly agree that the identity of a brand is internally connected with staff and externally connected with the consumers and the rest of the stakeholders. Brand management studies are much focused on the external part, mainly on consumers. This research follows a different agenda exploring the brand identity dimensions by measuring the brand identity prism developed by Kapferer, both internally and externally. The measurement of brand identity is scarce in brand management literature. A reliable, valid and unique brand identity scale that empirically establishes the construct's dimensionality has yet to be developed in a highly consumer involvement context. This paper reports the findings of a research conducted at 235 engineering higher education students. Data were analysed using confirmatory factor analysis. Findings reveal that the brand identity prism is moderated by brand culture. This research also gave important insights regarding the theory proposed by Kapferer regarding the external brand identity.
In this paper we investigate the behaviour of credit default in start-up companies. Using a logit... more In this paper we investigate the behaviour of credit default in start-up companies. Using a logit regression technique on a panel data of 1430 start-ups and considering a tracking period of three years, we tested the impact on the probability of occurrence of the first credit event in financing agreements due to variables grouped into three categories: financial capital, human capital and industry dynamics. We concluded from a financial point of view, that the support provided by partners in the financing of the company’s activity, the intensity of use of assets under management and reduced debt pay-back periods, were decisive in mitigating risk of default. In addition we found that the occurrence of a credit event will only be as limited as higher the quality of human capital held by the promoter of the project in terms of educational background and management experience.
Uploads
Papers by Vitorino Martins