Loading...
Research Project
Untitled
Funder
Authors
Publications
Optimization approaches to supervised classification
Publication . Silva, A. Pedro Duarte
The Supervised Classification problem, one of the oldest and most recurrent problems in applied data analysis, has always been analyzed from many different perspectives. When the emphasis is placed on its overall goal of developing classification rules with minimal classification cost, Supervised Classification can be understood as an optimization problem. On the other hand, when the focus is in modeling the uncertainty involved in the classification of future unknown entities, it can be formulated as a statistical problem. Other perspectives that pay particular attention to pattern recognition and machine learning aspects of Supervised Classification have also a long history that has lead to influential insights and dif- ferent methodologies. In this review, two approaches to Supervised Classification strongly related to optimization theory will be discussed and compared. In particular, we will review methodologies based on Mathematical Programming models that optimize observable criteria linked to the true objective of misclassification error (or cost) minimization, and approaches derived from the minimization of known bounds on the true misclassification error. The former approach is known as the Mathematical Programming approach to Supervised Classification, while the latter is in the origin of the well known Classification Support Vector Machines. Throughout the review two-group as well as general multi-group problems will be considered, and the review will conclude with a discussion of the most promising research directions in this area.
Hybrids and professional communities: comparing UK reforms in healthcare, broadcasting and postal services
Publication . Turner, Simon; Lourenço, Ana; Allen, Pauline
Many countries use state-owned, for-profit, and third sector organizations to provide public services,
generating ‘hybrid’ organizational forms. This article examines how the hybridization of organizations
in the public sector is influenced by interaction between regulatory change and professional
communities. It presents qualitative data on three areas of the UK public sector that have undergone
marketization: healthcare, broadcasting, and postal services. Implementation of market-based
reform in public sector organizations is shaped by sector-specific differences in professional communities,
as these groups interact with reform processes. Sectoral differences in communities include
their power to influence reform, their persistence despite reform, and their alignment with the direction
of change or innovation. Equally, the dynamics of professional communities can be affected
by reform. Policymakers need to take account of the ways that implementation of hybrid forms
interacts with professional communities, including risk of disrupting existing relationships based
on communities that contribute to learning.
Outlier detection in interval data
Publication . Silva, A. Pedro Duarte; Filzmoser, Peter; Brito, Paula
A multivariate outlier detection method for interval data is proposed that makes use of a parametric approach to model the interval data. The trimmed maximum likelihood principle is adapted in order to robustly estimate the model parameters. A simulation study demonstrates the usefulness of the robust estimates for outlier detection, and new diagnostic plots allow gaining deeper insight into the structure of real world interval data.
A note on the wallet game with discrete bid levels
Publication . Gonçalves, Ricardo; Ray, Indrajit
It is well-known that in the wallet game with two bidders, bidding twice the (individual) signal is an equilibrium. We prove that this strategy is never an equilibrium in a Japanese–English auction once discrete bid levels are introduced; we also discuss the implications of this result.
Can informal firms hurt registered SMEs’ access to credit?
Publication . Distinguin, Isabelle; Rugemintwaria, Clovis; Tacneng, Ruth
Using firm-level survey responses from 2009 to 2012, we examine whether competitors from the informal sector affect the credit constraints of registered SMEs in 86 countries worldwide. We also investigate the role played by the quality of institutional environment in exacerbating or in alleviating such effect. A weak quality of institutional environment strengthens inter-linkages between the formal and the informal sectors, increases the costs and decreases the benefits assumed by formal firms, and reduces the costs attributed to informality. Moreover, it also results in a large informal economy, which influences perceptions about the substitutability between formal and informal goods, and law evasion. Our findings indicate that registered SMEs facing competition from informal firms are more likely to be credit-constrained than other formal SMEs that are not confronted with such competition. This result is consistent with the “parasite” view and the entrepreneurial perspective of informality, which assert that informal firms are capable of competing against registered SMEs and hurting the latter’s profits. Further, we find that such adverse impact manifests only in countries with weak rule of law and high degree of corruption and bureaucracy. Our results also show that registered micro and small firms are more likely to be affected by the presence of informal firm competitors than medium-sized firms. This is because the benefits of formality that include access to credit from financial institutions, increase with firm size. On the whole, our findings suggest that governments must enhance their role in increasing access to credit to smaller firms and in providing incentives for informal firms to be integrated in the formal economy. Moreover, in order to achieve inclusive growth, our results highlight the importance of improving the business environment, which affects all entrepreneurs.
Organizational Units
Description
Keywords
Contributors
Funders
Funding agency
Fundação para a Ciência e a Tecnologia
Funding programme
5876
Funding Award Number
UID/GES/00731/2013