Groupcompare: A holistic approach to two sample data analysis


CEBECİ Z., ÖZDEMİR A. F., YILDIZTEPE E., ÇELİK GÜNEY M.

SoftwareX, cilt.35, 2026 (SCI-Expanded, Scopus)

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 35
  • Basım Tarihi: 2026
  • Doi Numarası: 10.1016/j.softx.2026.102835
  • Dergi Adı: SoftwareX
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Compendex, INSPEC, Directory of Open Access Journals
  • Anahtar Kelimeler: Bootstrap, Permutation test, R package, Two-sample comparison
  • Dokuz Eylül Üniversitesi Adresli: Evet

Özet

The groupcompare R package provides a unified framework for two-sample statistical comparisons. It addresses critical limitations of traditional methods by integrating parametric, non-parametric, permutation, and bootstrap-based techniques within a single package. The package notably incorporates robust descriptive statistics such as Huber's M-estimator and the Harrell-Davis quantile estimator, enhancing reliability when dealing with non-normal data or outliers. Furthermore, groupcompare offers helpful bivariate plots and statistical inferences, simplifying interpretation and reporting.