Search

Regression testing is the process of retesting a system after it or its environment has changed. Many techniques aim to find the cheapest subset of the regression test suite that achieves full coverage. More recently, it has been observed that the tester might want to have a range of solutions providing different trade-offs between cost and one or more forms of coverage, this being a multi-objective optimisation problem. This paper further develops the multi-objective agenda by adapting a decomposition-based multi-objective evolutionary algorithm (MOEA/D). Experiments evaluated four approaches: a classic greedy algorithm; non-dominated sorting genetic algorithm II (NSGA-II); MOEA/D with a fixed value for a parameter c ; and MOEA/D in which tuning was used to choose the value of c . These used six programs from the SIR repository and one larger program, VoidAuth. In all of the experiments MOEA/D with tuning was the most effective technique. The relative performance of the other techniques varied, although MOEA/D with fixed c outperformed NSGA-II on the larger programs (Space and VoidAuth).

This is the post-print version of the final paper published in Computational Statistics & Data Analysis. The published article is available from the link below. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. Copyright @ 2013 Elsevier B.V. Networks appear in many fields, from finance to medicine, engineering, biology and social science. They often comprise of a very large number of entities, the nodes, and the interest lies in inferring the interactions between these entities, the edges, from relatively limited data. If the underlying network of interactions is sparse, two main statistical approaches are used to retrieve such a structure: covariance modeling approaches with a penalty constraint that encourages sparsity of the network, and nodewise regression approaches with sparse regression methods applied at each node. In the presence of outliers or departures from normality, robust approaches have been developed which relax the assumption of normality. Robust covariance modeling approaches are reviewed and compared with novel nodewise approaches where robust methods are used at each node. For low-dimensional problems, classical deviance tests are also included and compared with penalized likelihood approaches. Overall, copula approaches are found to perform best: they are comparable to the other methods under an assumption of normality or mild departures from this, but they are superior to the other methods when the assumption of normality is strongly violated.

Supervised classification problems in which the class sizes are very different are common. In such cases, nearest neighbour classifiers exhibit a non-monotonic relationship between the number of nearest neighbours and misclassification rate of each of the two classes separately.