Testing the Significance of Interactions in Genetic Studies Using Interaction Information and Resampling Technique

摘要: Interaction information is a model-free, non-parametric measure used for detection of interaction among variables. It frequently finds interactions which remain undetected by standard model-based methods. However in the previous studies application was limited lack appropriate statistical tests. We study challenging problem testing positiveness allows to confirm significance investigated interactions. turns out that commonly chi-squared test detects too many spurious when dependence between variables (e.g. two genetic markers) strong. To overcome this we consider permutation and also propose novel HYBRID method combines tests takes into account studied show numerical experiments that, contrast based test, proposed controls well actual level situations are Moreover outperforms with respect power computational efficiency. The applied find Single Nucleotide Polymorphisms as gene expression levels human immune cells.