On Graphically Checking Goodness-of-fit of Binary Logistic Regression Models

OBJECTIVES: This paper is concerned with checking goodness-of-fit of binary logistic regression models. For the practitioners of data analysis, the broad classes of procedures for checking goodness-of-fit available in the literature are described. The challenges of model checking in the context of binary logistic regression are reviewed. As a viable solution, a simple graphical procedure for checking goodness-of-fit is proposed. METHODS: The graphical procedure proposed relies on pieces of information available from any logistic analysis; the focus is on combining and presenting these in an informative way. RESULTS: The information gained using this approach is presented with three examples. In the discussion, the proposed method is put into context and compared with other graphical procedures for checking goodness-of-fit of binary logistic models available in the literature. CONCLUSION: A simple graphical method can significantly improve the understanding of any logistic regression analysis and help to prevent faulty conclusions.

Climate change and infectious diseases of wildlife: Altered interactions between pathogens, vectors and hosts

Infectious diseases result from the interactions of host, pathogens, and, in the case of vector-borne diseases, also vectors. The interactions involve physiological and ecological mechanisms and they have evolved under a given set of environmental conditions. Environmental change, therefore, will alter host-pathogen-vector interactions and, consequently, the distribution, intensity, and dynamics of infectious diseases. Here, we review how climate change may impact infectious diseases of aquatic and terrestrial wildlife. Climate change can have direct impacts on distribution, life cycle, and physiological status of hosts, pathogens and vectors. While a change in either host, pathogen or vector does not necessarily translate into an alteration of the disease, it is the impact of climate change on the interactions between the disease components which is particularly critical for altered disease risks. Finally, climate factors can modulate disease through modifying the ecological networks host-pathogen-vector systems are belonging to, and climate change can combine with other environmental stressors to induce cumulative effects on infectious diseases. Overall, the influence of climate change on infectious diseases involves different mechanisms, it can be modulated by phenotypic acclimation and/or genotypic adaptation, it depends on the ecological context of the host-pathogen-vector interactions, and it can be modulated by impacts of other stressors. As a consequence of this complexity, non-linear responses of disease systems under climate change are to be expected. To improve predictions on climate change impacts on infectious disease, we suggest that more emphasis should be given to the integration of biomedical and ecological research for studying both the physiological and ecological mechanisms which mediate climate change impacts on disease, and to the development of harmonized methods and approaches to obtain more comparable results, as this would support the discrimination of case-specific versus general mechanisms

Sparse computation for large-scale binary classification

Well-known data mining algorithms rely on inputs in the form of pairwise similarities between objects. For large datasets it is computationally impossible to perform all pairwise comparisons. We therefore propose a novel approach that uses approximate Principal Component Analysis to efficiently identify groups of similar objects. The effectiveness of the approach is demonstrated in the context of binary classification using the supervised normalized cut as a classifier. For large datasets from the UCI repository, the approach significantly improves run times with minimal loss in accuracy.

Index Tracking Using Data-Mining Techniques and Mixed-Binary Linear Programming

Index tracking has become one of the most common strategies in asset management. The index-tracking problem consists of constructing a portfolio that replicates the future performance of an index by including only a subset of the index constituents in the portfolio. Finding the most representative subset is challenging when the number of stocks in the index is large. We introduce a new three-stage approach that at first identifies promising subsets by employing data-mining techniques, then determines the stock weights in the subsets using mixed-binary linear programming, and finally evaluates the subsets based on cross validation. The best subset is returned as the tracking portfolio. Our approach outperforms state-of-the-art methods in terms of out-of-sample performance and running times.