ScottKnott: A Package for Performing the Scott-Knott Clustering Algorithm in R

Jelihovschi, Enio Galinkin; Faria, José Cláudio; Allaman, Ivan Bezerra

doi:10.5540/tema.2014.015.01.0003

Cited by 122 publications

(82 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The Scott-Knott test will cluster the metrics according to statistically significant differences in their mean variable importance scores (α = 0.05). We use the implementation of the Scott-Knott test provided by the ScottKnott R package [21]. The Scott-Knott test ranks each metric exactly once, however several metrics may appear within one rank.…”

Section: Discussionmentioning

confidence: 99%

The Impact of Mislabelling on the Performance and Interpretation of Defect Prediction Models

Tantithamthavorn

McIntosh

Hassan

et al. 2015

2015 IEEE/ACM 37th IEEE International Conference on Software Engineering

View full text Add to dashboard Cite

Abstract-The reliability of a prediction model depends on the quality of the data from which it was trained. Therefore, defect prediction models may be unreliable if they are trained using noisy data. Recent research suggests that randomly-injected noise that changes the classification (label) of software modules from defective to clean (and vice versa) can impact the performance of defect models. Yet, in reality, incorrectly labelled (i.e., mislabelled) issue reports are likely non-random. In this paper, we study whether mislabelling is random, and the impact that realistic mislabelling has on the performance and interpretation of defect models. Through a case study of 3,931 manually-curated issue reports from the Apache Jackrabbit and Lucene systems, we find that: (1) issue report mislabelling is not random; (2) precision is rarely impacted by mislabelled issue reports, suggesting that practitioners can rely on the accuracy of modules labelled as defective by models that are trained using noisy data; (3) however, models trained on noisy data typically achieve 56%-68% of the recall of models trained on clean data; and (4) only the metrics in top influence rank of our defect models are robust to the noise introduced by mislabelling, suggesting that the less influential metrics of models that are trained on noisy data should not be interpreted or used to make decisions.

show abstract

Section: Discussionmentioning

confidence: 99%

The Impact of Mislabelling on the Performance and Interpretation of Defect Prediction Models

Tantithamthavorn

McIntosh

Hassan

et al. 2015

2015 IEEE/ACM 37th IEEE International Conference on Software Engineering

View full text Add to dashboard Cite

show abstract

“…To validate if the difference between various methods discussed above is significant, we conduct statistical test in this subsection. To overcome the confounding issue of overlapping groups that are produced by several other post hoc tests, such as Nemenyi's test, we conduct the Scott‐Knott test to partition 24 methods into different levels …”

Section: Empirical Studymentioning

confidence: 99%

Software change‐proneness prediction through combination of bagging and resampling methods

Zhu

Cheng

et al. 2018

J Software Evolu Process

View full text Add to dashboard Cite

Identifying the change‐prone parts of software could help managers and developers to effectively allocate maintenance resource and time during early phases of software life cycle. Change‐proneness prediction on file level with binary classification methods makes such identification possible. As the fact that change‐prone files frequently account for a small part of all the files, the prediction performance of standard classification methods is not satisfying. In this paper, we employ imbalanced learning methods, including bagging, resampling, and especially their combination to reduce the performance decrease of standard classifiers caused by the class imbalance problem in change‐proneness prediction. Besides, we propose a boxplot‐based partition method to provide more proper change‐proneness label designation for the training data. Eight open‐source Java projects are chosen in the empirical study to validate the effectiveness of the combination methods in change‐proneness prediction. The experimental results of the empirical study show that combining bagging with resampling can significantly improve the prediction performance of only bagging or resampling. Of all the combination methods employed, combination of bagging with undersampling performs better than others. And support vector machine is more effective as a base classifier than J48 and naive Bayes.

show abstract

“…Mortality of the insects was evaluated after 48 h. Insects were considered dead when they did not move when prodded with a fine brush. Rhyzopertha dominica mortality data were subjected to analysis of variance and the treatment means were grouped by the Scott–Knott test at the 5% level using the software R …”

Section: Methodsmentioning

confidence: 99%

Synthesis, insecticidal activity, and phytotoxicity of novel chiral amides

Aguiar

Alvarenga

Silva

et al. 2019

Pest Management Science

View full text Add to dashboard Cite

BACKGROUND The lesser grain borer, Rhyzopertha dominica (F.) (Coleoptera: Bostrychidae), is an important pest of stored grains worldwide. Chemical control is the main method used to manage this pest, but the continuous use of insecticides can lead to the selection of resistant R. dominica strains. Thus, there is a constant demand for the development of new insecticide molecules. This study describes the synthesis of 14 chiral amides and evaluation of their insecticidal activity against R. dominica. Their phytotoxicity to wheat (Triticum sativum) seeds is also evaluated. RESULTS In the screening assay, compounds 8i and 8j caused 100% and 87% mortality of R. dominica. These values did not differ from the mortality caused by Bifenthrin® (75%). Amide 8i presented similar toxicity (LD50 = 27.98 µmol g−1, CI95 = 25.14–30.71) and speed of action (LT50 = 22 h, CI95 = 19.34–24.66) to amide 8j (LD50 = 29.37 µmol g−1, CI95 = 27.43–31.09, and LT50 = 19 h, CI95 = 17.05–20.95) against the pest. Both amides inhibited less than 44% of wheat growth. CONCLUSION Among the tested amides, only 8i and 8j were effective in R. dominica control and presented no considerable phytotoxicity towards wheat seeds. Therefore, these amides are promising as insecticides for the management of R. dominica. © 2018 Society of Chemical Industry

show abstract

ScottKnott: A Package for Performing the Scott-Knott Clustering Algorithm in R

Cited by 122 publications

References 12 publications

The Impact of Mislabelling on the Performance and Interpretation of Defect Prediction Models

The Impact of Mislabelling on the Performance and Interpretation of Defect Prediction Models

Software change‐proneness prediction through combination of bagging and resampling methods

Synthesis, insecticidal activity, and phytotoxicity of novel chiral amides

Contact Info

Product

Resources

About