Conversely, when searching for genes whose absolute LFC is significantly below a threshold, i.e., when testing the null hypothesis \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document} $\mathcal {H}_{0}: |\beta _{\textit {ir}}| \ge \theta $ \end{document}ℋ0:|βir|≥θ, the P value is constructed as the maximum of two one-sided tests of the simple null hypotheses: \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document} $\mathcal {H}_{0a}: \beta _{\textit {ir}} = \theta $ \end{document}ℋ0a:βir=θ and \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document} $\mathcal {H}_{0b}: \beta _{\textit {ir}} = -\theta $ \end{document}ℋ0b:βir=−θ. The one-sided P values are generated by integrating a normal distribution centered on θ with standard deviation SE(βir) from βir toward −∞, and integrating a normal distribution centered on −θ with standard deviation SE(βir) from βir toward ∞.
