Root Cause Analysis by a Combined Sparse Classification and Monte Carlo Approach

Classification methods with embedded feature selection capability are very appealing for the analysis of complex processes since they allow the analysis of root causes even when the number of input variables is high. In this work, we investigate the performance of three techniques for classification within a Monte Carlo strategy with the aim of root cause analysis. We consider the naive bayes classifier and the logistic regression model with two different implementations for controlling model complexity, namely, a LASSO-like implementation with a L1 norm regularization and a fully Bayesian implementation of the logistic model, the so called relevance vector machine. Several challenges can arise when estimating such models mainly linked to the characteristics of the data: a large number of input variables, high correlation among subsets of variables, the situation where the number of variables is higher than the number of available data points and the case of unbalanced datasets. Using an ecological and a semiconductor manufacturing dataset, we show advantages and drawbacks of each method, highlighting the superior performance in term of classification accuracy for the relevance vector machine with respect to the other classifiers. Moreover, we show how the combination of the proposed techniques and the Monte Carlo approach can be used to get more robust insights into the problem under analysis when faced with challenging modelling conditions.

Antimicrobial Heteroresistance: an Emerging Field in Need of Clarity

SUMMARY: "Heteroresistance" describes a phenomenon where subpopulations of seemingly isogenic bacteria exhibit a range of susceptibilities to a particular antibiotic. Unfortunately, a lack of standard methods to determine heteroresistance has led to inappropriate use of this term. Heteroresistance has been recognized since at least 1947 and occurs in Gram-positive and Gram-negative bacteria. Its clinical relevance may be considerable, since more resistant subpopulations may be selected during antimicrobial therapy. However, the use of nonstandard methods to define heteroresistance, which are costly and involve considerable labor and resources, precludes evaluating the clinical magnitude and severity of this phenomenon. We review the available literature on antibiotic heteroresistance and propose recommendations for definitions and determination criteria for heteroresistant bacteria. This will help in assessing the global clinical impact of heteroresistance and developing uniform guidelines for improved therapeutic outcomes.

Contemporary and 'messy' rural in-migration processes: Comparing counterurban and lateral rural migration.

This paper questions the ongoing dominant coverage given to counterurbanisation in the rural population literature. It is argued that this provides only a partial account of the true diversity of contemporary migration processes operating in rural areas and has the potential to fuse together different in-migration processes. Specifically, lateral rural migration has been under-researched to date. Using empirical data from a survey of 260 migrant households to 3 UK case study areas (in Scotland, Wales, and Northern Ireland), the significance of lateral rural migration is revealed and compared with counterurban migration and migrants. The last change of address shows that 59% relocated from an urban area (participating in a counterurban flow) whilst 41% moved from another rural location (lateral rural flow). The boundary between migration processes can, however, be blurred: Some moves are an example of both counterurbanisation and lateral rural flows. Incorporating lifetime migration histories data demonstrates the contemporary complexity and messiness of rural in-migration processes. For example, 26% of these migrant households only ever undertook a lateral rural move during their lifetime. For others, the direction of migration has changed numerous times and intertwined with each move are aspects of life course, return, and inter-regional migration. Comparing the survey characteristics and motivations of counterurban and lateral rural migrants, alongside interview material, highlights important similarities and differences. The paper concludes by calling on rural population geographers to more fully engage with the complexity, totality, and indeed messiness of contemporary rural in-migration processes.