Yes / This study estimates output market power in the Chinese banking industry using the multi-output Lerner index. We propose a minimum distance cost function approach, which allows us to determine not only the level of market power but also the non-profit maximizers and efficiency level of Chinese banks. Following the first-stage analysis, we employ the generalized method of moment system estimator to evaluate the impacts of bank innovation and trade openness on market power in a multi-output banking context. In particular, we innovatively propose a causal structure analysis based on Wang and Blei (2019) to validate and verify the robustness of our results. We also assess this relationship for different types of bank ownership in China. The findings suggest that Chinese banks exhibit high market power in loans. Furthermore, the results show that bank innovation and trade openness have a significant negative impact on market power in loans, but a significant positive impact on market power in securities. The results also indicate a significantly negative impact of trade openness on overall market power. We find that higher levels of innovation among state-owned and joint-stock commercial banks improve the overall level of market power. The results suggest that, for all bank ownership types, trade openness has a significant negative impact on market power in loans but a significant positive impact on market power in securities. The impact on the overall level of market power is consistently significant and negative. / The full-text of this article will be released for public view at the end of the publisher embargo on 11 Aug 2025.

Data Envelopment Analysis (Charnes et al, 1978) is a technique used to evaluate the relative efficiency of any process or an organization. The efficiency evaluation is relative, which means it is compared with other processes or organizations. In real life situations different processes or units seldom operate in similar environments. Within a relative efficiency context, if units operating in different environments are compared, the units that operate in less desirable environments are at a disadvantage. In order to ensure that the comparison is fair within the DEA framework, a two-stage framework is presented in this thesis. Fuzzy clustering is used in the first stage to suitably group the units with similar environments. In a subsequent stage, a relative efficiency analysis is performed on these groups. By approaching the problem in this manner the influence of environmental variables on the efficiency analysis is removed. The concept of environmental dependency index is introduced in this thesis. The EDI reflects the extent to which the efficiency behavior of units is due to their environment of operation. The EDI also assists the decision maker to choose appropriate peers to guide the changes that the inefficient units need to make. A more rigorous series of steps to obtain the clustering solution is also presented in a separate chapter (chapter 5). / Master of Science

Yes / Prediction of corporate failure is one of the major activities in auditing firms risks and uncertainties. The design of reliable models to predict bankruptcy is crucial for many decision making processes. Although a large number of models have been designed to predict bankruptcy, the relative performance evaluation of competing prediction models remains an exercise that is unidimensional in nature, which often leads to reporting conflicting results. In this research, we overcome this methodological issue by proposing an orientation-free super-efficiency data envelopment analysis model as a multi-criteria assessment framework. Furthermore, we perform an exhaustive comparative analysis of the most popular bankruptcy modeling frameworks for UK data including our own models. In addition, we address two important research questions; namely, do some modeling frameworks perform better than others by design? and to what extent the choice and/or the design of explanatory variables and their nature affect the performance of modeling frameworks?, and report on our findings.

Yes / Although many modelling and prediction frameworks for corporate bankruptcy and distress have been proposed, the relative performance evaluation of prediction models is criticised due to the assessment exercise using a single measure of one criterion at a time, which leads to reporting conflicting results. Mousavi et al. (Int Rev Financ Anal 42:64–75, 2015) proposed an orientation-free super-efficiency DEA-based framework to overcome this methodological issue. However, within a super-efficiency DEA framework, the reference benchmark changes from one prediction model evaluation to another, which in some contexts might be viewed as “unfair” benchmarking. In this paper, we overcome this issue by proposing a slacks-based context-dependent DEA (SBM-CDEA) framework to evaluate competing distress prediction models. In addition, we propose a hybrid crossbenchmarking- cross-efficiency framework as an alternative methodology for ranking DMUs that are heterogeneous. Furthermore, using data on UK firms listed on London Stock Exchange, we perform a comprehensive comparative analysis of the most popular corporate distress prediction models; namely, statistical models, under both mono criterion and multiple criteria frameworks considering several performance measures. Also, we propose new statistical models using macroeconomic indicators as drivers of distress.

Yes / On feature selection, as one of the critical steps to develop a distress prediction model (DPM), a variety of expert systems and machine learning approaches have analytically supported developers. Data envel- opment analysis (DEA) has provided this support by estimating the novel feature of managerial efficiency, which has frequently been used in recent two-stage DPMs. As key contributions, this study extends the application of expert system in credit scoring and distress prediction through applying diverse DEA mod- els to compute corporate market efficiency in addition to the prevailing managerial efficiency, and to estimate the decomposed measure of mix efficiency and investigate its contribution compared to Pure Technical Efficiency and Scale Efficiency in the performance of DPMs. Further, this paper provides a com- prehensive comparison between two-stage DPMs through estimating a variety of DEA efficiency measures in the first stage and employing static and dynamic classifiers in the second stage. Based on experimen- tal results, guidelines are provided to help practitioners develop two-stage DPMs; to be more specific, guidelines are provided to assist with the choice of the proper DEA models to use in the first stage, and the choice of the best corporate efficiency measures and classifiers to use in the second stage.

Data science and evaluation are two disciplines that could benefit enormously from successful integration. While data science can provide useful information in terms of statistics for any evaluation process, it as a subject can benefit from incorporating elements that investigate the value addition aspects addressed by evaluation and evaluative thinking. Evaluative thinking when incorporated with the analysis of big data sources can become a powerful tool in our hands that could be used in various sectors, for various purposes, to build equity and justice in society and make us better prepared to deal with exigencies. The new advancements in data science tools and approaches have attracted researchers from various disciplines, including evaluators. However social scientists and evaluators have been slow adopters of data science technologies compared to other fields. If evaluation practitioners and scholars do not pay attention, then the other fields will race ahead with different methods, models, tools, and approaches (Bamberger, Raftree, and Olazabal, 2016). The new and emerging data sources and analytical approaches can not only help the evaluation practitioners to solve problems of various dimensions, but also the integration of disciplines like data science with evaluation has the potential to benefit each other and as well as for the promotion of social good. Data Envelopment Analysis (DEA) is a nonparametric linear programming approach to measure the efficiency and productivity of decision-making units (DMUs), which can be used in both public and private sectors. This approach can enhance the decision-making process by utilizing new emerging data sources. DEA, after being introduced in the late 1970s, has been widely used in the management sector, and over the last few decades, it has gained popularity in various additional fields due to being a data-driven approach. As far back as 1986, DEA was the subject of an entire textit{New Directions for Evaluation} volume, but it has rarely been explored again in the field of evaluation since then. Especially given the increased availability and use of big data in evaluation, there is a need to revisit DEA and explore its potential applications and implications for evaluation. This study is threefold, where it first explores what the published literature reveals about the nature of DEA and its relationship to the core evaluation concepts of evaluative thinking, reasoning, and ethics, using a scoping review. Secondly, it demonstrates a proof of concept of how DEA could be applied and the implications for evaluative thinking and reasoning using big data. Lastly, this study seeks the perspectives of thought leaders on the application of data science technologies and DEA in evaluation. / Doctor of Philosophy / Big data is an important trend worldwide, and most of the innovations and discussions going on around big data are all happening outside evaluation, and this poses a double-sided risk. On one hand, if other fields like data science, management, banking, agriculture, chemistry, healthcare, etc. continue to innovate around big data without the understanding of evaluative thinking, reasoning, and ethics, then the applied inquiry that the researchers have developed and reflected upon within evaluation for decades, will be at risk due to an overly technical approach to data. On the other hand, the field of evaluation faces the problem of being left behind. For evaluation to remain relevant as a field, it must stay up to date with developments in adjacent disciplines. In other words, if evaluation practitioners and scholars do not pay attention, then the other fields will race ahead with different methods, models, tools, and approaches (Bamberger et al., 2016). It is a problem on two levels. One of the biggest challenges with big data is that they lack quality. It thus becomes imperative to make the best use of the data and to convey valid and compelling stories with these data, we must continue to explore different approaches to working with it. This paper explores an approach, Data Envelopment Analysis (DEA), to make sense of the data with potential contribution to decision-making. DEA is a nonparametric linear programming method for measuring the efficiency and productivity of decision-making units (DMUs) in both the public and private sectors. It has maintained popularity in various subject areas that use big data, like operations research, mathematics, environmental science, engineering, material science, etc. After being introduced in the late 1970s, it has been widely used in the management sector, and over the last few decades, has gained popularity in various additional fields due to being a data-driven approach. As far back as 1986, linear optimization, in particular DEA, was the subject of an entire textit{New Directions for Evaluation} volume, but it has rarely been explored again in the field of evaluation since then. Especially given the increased availability and use of big data in evaluation, there is a need to revisit DEA and explore its potential applications and implications for evaluation. As such, this study is divided into three parts, where the first part is a scoping review that explores what the published literature reveals about the nature of DEA and its relationship to the core evaluation concepts of evaluative thinking, reasoning, and ethics. Secondly, this study provides a demonstration of the application of DEA using big data in evaluation. And lastly, this study seeks the perspectives of thought leaders on the application of data science technologies and DEA in evaluation.

Submitted by SBI Biblioteca Digital (sbi.bibliotecadigital@puc-campinas.edu.br) on 2018-08-09T11:58:01Z No. of bitstreams: 1 MARIA PAULA MINORIN BABONI.pdf: 3935036 bytes, checksum: 6b16b5f82fcb82f4f4e69e7cfd8367d7 (MD5) / Made available in DSpace on 2018-08-09T11:58:02Z (GMT). No. of bitstreams: 1 MARIA PAULA MINORIN BABONI.pdf: 3935036 bytes, checksum: 6b16b5f82fcb82f4f4e69e7cfd8367d7 (MD5) Previous issue date: 2018-07-28 / To maximize basic sanitation benefits, it?s necessary to solve the challenge of conflicting objectives. As the performance depends on the value of the one who evaluates, this research proposes to evaluate the sanitation from the perspective of different stakeholders that have conflicting objectives: the User Population - PU and the Service Provider - PS. In order to verify how the municipalities placed themselves in each perspective and in the joint vision, this research proposed to classify the Services of Water Supply and Sanitary Sewage of the municipalities of the Metropolitan Region of Campinas, from the vision of the PU and the PS, during the years of 2014 and 2015, according to the relations of efficiencies. Data Envelopment Analysis was used to evaluate the efficiencies of the municipalities in the two views, considering the CCR model oriented to Output and the data provided by the SNIS and IMP, and the Malmquist Index in order to evaluate the movement of the municipalities. It was verified that the majority of the municipal policies favored the PS in detriment of better services for the PU. The municipalities that reached the Great Balance were Engenheiro Coelho and Americana in 2014 and 2015 and Cosm?polis in 2015. In addition, the dominant force of advancement towards the PS occurred due to Technological Progress rather than to the improvement of municipal relative efficiency in the period, while the forces advancing towards the PU were results of the progress of the Frontier and relative municipal efficiency. As regards the characterization of the service providers, it was concluded that the Scope is decisive in the view of the stakeholder when compared to the Legal Nature and the Property, since the municipalities operated by the Regional provider were considered efficient in the view of the PS but inefficient in the vision of the PU, obtaining the last positions in the Ranking of the User Population. / A quest?o dos objetivos conflitantes deve ser resolvida para universalizar os servi?os do saneamento, foco estrat?gico do setor. Para tanto, prop?e-se avaliar o desempenho dos sistemas de abastecimento de ?gua e esgotamento sanit?rio da Regi?o Metropolitana de Campinas ? RMC sob a ?tica de stakeholders que t?m objetivos conflitantes: a Popula??o Usu?ria ? PU e o Prestador de Servi?os ? PS. Os servi?os de ?gua e esgoto foram classificados a partir da vis?o da PU e do PS durante os anos de 2014 e 2015, segundo suas rela??es de efici?ncia, para verificar como os munic?pios colocavam-se em cada perspectiva e na vis?o conjunta. Utilizaram-se a An?lise Envolt?ria de Dados ? DEA para avaliar a efici?ncia municipal, considerando o modelo CCR orientado para Sa?da e os dados p?blicos disponibilizados pelo Sistema Nacional de Informa??es sobre Saneamento ? SNIS e pelo produto Informa??es dos Munic?pios Paulistas ? IMP da Funda??o Sistema Estadual da An?lise de Dados - SEADE, e o ?ndice de Malmquist ? IM para avaliar o comportamento dos munic?pios no per?odo. Verificou-se que a maioria das pol?ticas municipais privilegiavam o PS em detrimento de melhores servi?os para a PU nos dois anos e que os munic?pios que atingiram o Equil?brio ?timo foram Engenheiro Coelho e Americana, em 2014 e 2015, e Cosm?polis em 2014. No sentido do PS, o avan?o ocorreu devido ao Deslocamento da Fronteira ? EFC e o retrocesso de Cosm?polis e Santo Ant?nio de Posse ocorreu devido ao Emparelhamento ? TEC. No sentido da PU, o avan?o ocorreu tanto por causa do TEC quanto do EFC. O retrocesso de Holambra ocorreu tanto por conta do TEC quanto do EFC. A Abrang?ncia do prestador de servi?o, se comparada ? Natureza Jur?dica e ao Direito, foi decisiva na vis?o do stakeholder, j? que os munic?pios operados pelo prestador regional foram ineficientes para a PU e eficientes para o PS, em 2014 e 2015.

The intense economic growth that Brazil has experienced in recent decades and its consequent explosive motorization process have resulted in an undesirable impact: the continuously increasing trend in traffic fatality numbers. This study presents a research on indicators and indexes with the objective of delivering both overall and disaggregated evidence about the road safety performance and targets in fatality reduction in Brazil at the state level taking the exposure into account. The intention is to support road safety strategic analysis in the country and to contribute to improve this critical scene. The methodological structure of this thesis consists of the following three main parts: (I) diagnosing the road safety situation at the state level using final outcome related information, in particular traffic fatality risk data; (II) setting a target number of traffic fatalities based on the relationship between the exposure level and the number of traffic fatalities in each state; and (III) suggesting domains for improvements based on the research of safety performance indicators representing three domains (road user, environment and vehicle) throughout the states. From a benchmarking point of view, we divided the Brazilian states into three separate clusters in order to provide more realistic state performance comparisons. After a data collection and indicators selection step, Data Envelopment Analysis (DEA) was the method used for executing the different steps, with the application of four different types of models specially developed for the identified research purposes. In addition, by means of bootstrapping the DEA scores we measured the sensitivity of the results to possible variations in the input data, for example concerning data quality and availability. As a result, we provided a road safety diagnosis per state as well as traffic fatality targets according to different perspectives: the entire group of road users (motorized and nonmotorized ones), motor vehicle occupants, and finally a disaggregated performance evaluation by running four separate DEA models (for motorcycle, car, truck and bus). Moreover, the SPI research including a hierarchy of 27 safety performance indicators expressed the states relative performance on the main road safety domains. Lastly, state profiles compiling all this information summarized the \"per state\" findings. / O intenso crescimento econômico que o Brasil tem experimentado nas últimas décadas e seu consequente explosivo processo de motorização resultaram em um impacto indesejado: a tendência contínua do aumento do número de mortes no trânsito. Este estudo apresenta uma pesquisa acerca de índices e indicadores com o objetivo de fornecer evidências gerais e desagregadas sobre o desempenho da segurança viária e metas de redução no número de mortes no Brasil no âmbito estadual, levando a exposição em consideração. A intenção é embasar uma análise estratégica da segurança viária no país e contribuir para melhorar este cenário crítico. A estrutura metodológica desta tese consiste das seguintes três partes principais: (I) diagnóstico da situação da segurança viária no nível estadual utilizando informações relacionadas ao resultado final, em particular dados de risco de morte no trânsito; (II) estabelecer uma meta para o número de mortes no trânsito para cada estado; e (III) sugerir domínios para melhorias baseado em pesquisa de indicadores de desempenho da segurança viária voltada a três domínios (usuário da via, ambiente e veículo). Sob a ótica do benchmarking, dividiram-se os estados brasileiros em três clusters para proporcionar comparações mais realistas dos desempenhos estaduais. Após uma etapa de coleta e seleção de indicadores, utilizou-se o método de Data Envelopment Analyis (DEA) para executar as diferentes etapas, com a aplicação de quatro tipos distintos de modelos especialmente desenvolvidos para os propósitos da pesquisa. Além disso, por meio de bootstrapping dos escores obtidos com a DEA, mediu-se a sensibilidade dos resultados a possíveis variações nos dados de entrada, no que diz respeito a, por exemplo, qualidade e disponibilidade dos dados. Como resultado, propicia-se, a partir de diferentes perspectivas, um diagnóstico da segurança viária por estado, assim como metas no número de mortes: para todo o grupo de usuários (motorizados e não-motorizados), ocupantes de veículos motorizados, e finalmente uma avaliação desagregada por meio de quatro modelos separados (para motocicletas, automóveis, caminhões e ônibus). Adicionalmente, a pesquisa de indicadores de desempenho da segurança considerando a hierarquia de 27 indicadores expressou os desempenhos relativos dos estados nos principais domínios da segurança viária. Por fim, perfis estaduais compilando todas estas informações resumem os resultados para os estados.

The intense economic growth that Brazil has experienced in recent decades and its consequent explosive motorization process have resulted in an undesirable impact: the continuously increasing trend in traffic fatality numbers. This study presents a research on indicators and indexes with the objective of delivering both overall and disaggregated evidence about the road safety performance and targets in fatality reduction in Brazil at the state level taking the exposure into account. The intention is to support road safety strategic analysis in the country and to contribute to improve this critical scene. The methodological structure of this thesis consists of the following three main parts: (I) diagnosing the road safety situation at the state level using final outcome related information, in particular traffic fatality risk data; (II) setting a target number of traffic fatalities based on the relationship between the exposure level and the number of traffic fatalities in each state; and (III) suggesting domains for improvements based on the research of safety performance indicators representing three domains (road user, environment and vehicle) throughout the states. From a benchmarking point of view, we divided the Brazilian states into three separate clusters in order to provide more realistic state performance comparisons. After a data collection and indicators selection step, Data Envelopment Analysis (DEA) was the method used for executing the different steps, with the application of four different types of models specially developed for the identified research purposes. In addition, by means of bootstrapping the DEA scores we measured the sensitivity of the results to possible variations in the input data, for example concerning data quality and availability. As a result, we provided a road safety diagnosis per state as well as traffic fatality targets according to different perspectives: the entire group of road users (motorized and nonmotorized ones), motor vehicle occupants, and finally a disaggregated performance evaluation by running four separate DEA models (for motorcycle, car, truck and bus). Moreover, the SPI research including a hierarchy of 27 safety performance indicators expressed the states relative performance on the main road safety domains. Lastly, state profiles compiling all this information summarized the \"per state\" findings. / O intenso crescimento econômico que o Brasil tem experimentado nas últimas décadas e seu consequente explosivo processo de motorização resultaram em um impacto indesejado: a tendência contínua do aumento do número de mortes no trânsito. Este estudo apresenta uma pesquisa acerca de índices e indicadores com o objetivo de fornecer evidências gerais e desagregadas sobre o desempenho da segurança viária e metas de redução no número de mortes no Brasil no âmbito estadual, levando a exposição em consideração. A intenção é embasar uma análise estratégica da segurança viária no país e contribuir para melhorar este cenário crítico. A estrutura metodológica desta tese consiste das seguintes três partes principais: (I) diagnóstico da situação da segurança viária no nível estadual utilizando informações relacionadas ao resultado final, em particular dados de risco de morte no trânsito; (II) estabelecer uma meta para o número de mortes no trânsito para cada estado; e (III) sugerir domínios para melhorias baseado em pesquisa de indicadores de desempenho da segurança viária voltada a três domínios (usuário da via, ambiente e veículo). Sob a ótica do benchmarking, dividiram-se os estados brasileiros em três clusters para proporcionar comparações mais realistas dos desempenhos estaduais. Após uma etapa de coleta e seleção de indicadores, utilizou-se o método de Data Envelopment Analyis (DEA) para executar as diferentes etapas, com a aplicação de quatro tipos distintos de modelos especialmente desenvolvidos para os propósitos da pesquisa. Além disso, por meio de bootstrapping dos escores obtidos com a DEA, mediu-se a sensibilidade dos resultados a possíveis variações nos dados de entrada, no que diz respeito a, por exemplo, qualidade e disponibilidade dos dados. Como resultado, propicia-se, a partir de diferentes perspectivas, um diagnóstico da segurança viária por estado, assim como metas no número de mortes: para todo o grupo de usuários (motorizados e não-motorizados), ocupantes de veículos motorizados, e finalmente uma avaliação desagregada por meio de quatro modelos separados (para motocicletas, automóveis, caminhões e ônibus). Adicionalmente, a pesquisa de indicadores de desempenho da segurança considerando a hierarquia de 27 indicadores expressou os desempenhos relativos dos estados nos principais domínios da segurança viária. Por fim, perfis estaduais compilando todas estas informações resumem os resultados para os estados.

Com o aumento da capacidade de processamento de dados dentro das empresas de todos os portes e da disponibilidade de informações cada vez maior nos tempos atuais, o uso de indicadores e ferramentas de análise quantitativa tornam-se cada vez mais comuns nas mais diversas áreas, buscando-se eficiência, uma correta alocação de recursos e na geração de expectativas mais realistas de vendas e resultados. Enquanto muitos mercados apresentam uma variedade de dados e de estudos para serem usados como bases de referência, existem outros que ainda são carentes de informações básicas para planejamento e análise. O mercado de materiais cirúrgicos é um destes, onde não estão disponíveis as demandas dos clientes, as projeções de mercado ou as estimativas de market share. Este estudo busca, através da análise das vendas em 43 territórios de empresas de dispositivos médicos com atuação no Brasil nas áreas de ortopedia traumatologia, neurocirurgia e buco-maxilo-facial, aplicar a técnica de Análise Envoltória de Dados (DEA, do inglês “Data Envelopment Analysis”) como um modelo de análise comparativa de eficiência que possa auxiliar nos processos de tomada de decisão, mesmo com uma base restrita e limitada de informações. A aplicação da técnica de DEA apresenta resultados que permitem [1] destacar os pontos de melhoria para os territórios ineficientes buscando [2] homogeneizar a eficiência de atendimento por meio do [3] benchmarking entre as regiões buscando [4] uma maior competitividade neste mercado. / With the increased capacity of data processing within companies of all sizes and the currently availability of all sort of informations, the use of indicators and tools for quantitative analysis become increasingly common in many areas, allowing companies to achieve better efficiency, proper resources allocation, and the settle of more realistic performance expectations. While many markets feature a variety of data and studies, others are deprived of basic information for planning and analysis. Among these, the medical devices market have almost unavailable informations of customers demands, markets forecasts or estimated market share at a regional level. Through the analysis of 43 sales territories of medical devices companies in Brazil, this study uses the technique of data envelopment analysis (DEA) as a model for comparative efficiency analysis that can assist the processes of decision making, even with a restricted and limited database. The application of DEA technique provide results that [1] highlight the points of improvement for inefficient territories [2] in order to homogenize the efficiency of regions through [3] benchmarking between them, [4] to improve overall competitive level.