CoChat

An Empirical Comparison of Model Validation Techniques for Defect Prediction Models

Tantithamthavorn, Chakkrit, McIntosh, Shane, Hassan, Ahmed E., Matsumoto, Kenichi · 2017 · IEEE Transactions on Software Engineering

The DOI matches its Crossref record; 132 of the 132 references it cites were found in a registry or an index.

Abstract

Defect prediction models help software quality assurance teams to allocate their limited resources to the most defect-prone modules. Model validation techniques, such as$k$-fold cross-validation, use historical data to estimate how well a model will perform in the future. However, little is known about how accurate the estimates of model validation techniques tend to be. In this paper, we investigate the bias and variance of model validation techniques in the domain of defect prediction. Analysis of 101 public defect datasets suggests that 77 percent of them are highly susceptible to producing unstable results– - selecting an appropriate model validation technique is a critical experimental design choice. Based on an analysis of 256 studies in the defect prediction literature, we select the 12 most commonly adopted model validation techniques for evaluation. Through a case study of 18 systems, we find that single-repetition holdout validation tends to produce estimates with 46-229 percent more bias and 53-863 percent more variance than the top-ranked model validation techniques. On the other hand, out-of-sample bootstrap validation yields the best balance between the bias and variance of estimates in the context of our study. Therefore, we recommend that future defect prediction studies avoid single-repetition holdout validation, and instead, use out-of-sample bootstrap validation.

Overview

Integrity signals

Registry

Crossref · 10.1109/tse.2016.2584050

Cites

132 of 132 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Citations

Cites

Research works printed but not linked: 9

  1. 10.29172/7c2a6982-6d72-4cd8-bba6-2fccb06a7011 · DOI · Paper page
  2. 10.2307/2289236 · doi:10.2307/2289236 · Paper page
  3. Jelihovschi, 2014, The ScottKnott Clustering Algorithm
  4. 10.1067/mod.2000.109032 · DOI · Paper page
  5. Meyer, 2014, E1071: Misc functions of the department of statistics (E1071), TU Wien
  6. 10.1109/ICSE.2005.1553571 · DOI · Paper page
  7. 2013, R Core Team, R: A language and environment for statistical computing, R foundation for statistical computing, Vienna, Austria
  8. 10.1007/978-3-031-01899-2 · doi:10.1007/978-3-031-01899-2 · Paper page
  9. Tantithamthavorn, 2015, ScottKnottESD: An R package of the Scott-Knott effect size difference (ESD) test

Cited by

See all 575

Metadata

Authors
Tantithamthavorn, C., McIntosh, S., Hassan, A. E., & Matsumoto, K.
Affiliations
  • Nara Institute of Science and Technology (JP)
  • Queen's University (CA)
Venue
IEEE Transactions on Software Engineering
Published
2017-01-01
Volume
43
Issue
1
Pages
1-18
ISSN
  • 0098-5589 (ISSN-L)
  • 1939-3520
OpenAlex
W2474835145
Cited by
574
References
129
Citations by year
2026: 39 · 2025: 53 · 2024: 69 · 2023: 56 · 2022: 58 · 2021: 93 · 2020: 63 · 2019: 75 · 2018: 45 · 2017: 18
FWCI
106.29
Type
journal article
Language
en
Open access
closed
Locations
IEEE Transactions on Software Engineering (publishedVersion)
Funders
  • JSPS
  • Advancing Strategic International Networks to Accelerate the Circulation of Talented Researchers
  • Interdisciplinary Global Networks for Accelerating Theory and Practice in Software Ecosystem
  • JSPS Fellows (16J03360)
  • Natural Sciences and Engineering Research Council of Canada (NSERC)
Topics
  • Physical Sciences › Computer Science › Information Systems › Software Engineering Research
  • Physical Sciences › Computer Science › Software › Software Reliability and Analysis Research
  • Physical Sciences › Computer Science › Information Systems › Software Engineering Techniques and Practices
Keywords
fault prediction, model validation, k-fold cross-validation, software quality assurance, defect dataset

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.