EUVIMEDEUVIMED entdecken
Crossref

Interaction Testing: Residuals-Based Permutations and Parametric Bootstrap in Continuous, Count, and Binary Data

Petra Buzkova

Epidemiologic Methods · 2016

DOI: 10.1515/em-2015-0010 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Epidemiologic Methods, 2016. Verfasst von Petra Buzkova. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 14 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To obtain statistical inference about interaction hypotheses without making strong distributional assumptions, permutation tests based on permuting the outcomes are often being used. It was shown that in continuous and binary data these tests might not be even approximately valid and parametric bootstrap was suggested as a viable alternative, outperforming such permutation tests. We describe an alternative permutation test, permuting the null hypothesis residuals rather than the outcome. Using simulations, we compare accuracy across the permutation tests and parametric bootstrap, studying continuous, binary, and additionally count data. Finally, we address power.

Zitieren

APA

Buzkova, P. (2016). Interaction Testing: Residuals-Based Permutations and Parametric Bootstrap in Continuous, Count, and Binary Data. Epidemiologic Methods. https://doi.org/10.1515/em-2015-0010

Vancouver

Buzkova P. Interaction Testing: Residuals-Based Permutations and Parametric Bootstrap in Continuous, Count, and Binary Data. Epidemiologic Methods. 2016. doi:10.1515/em-2015-0010

BibTeX
@article{Buzkova2016,
  author = {Buzkova, Petra},
  title = {Interaction Testing: Residuals-Based Permutations and Parametric Bootstrap in Continuous, Count, and Binary Data},
  journal = {Epidemiologic Methods},
  year = {2016},
  doi = {10.1515/em-2015-0010}
}
Kostenlos starten →