Hence, based on Eqs. (3) and (4), the variance of T can be estimated as \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document} $$\sigma^{2} = \text{Var}(T) \doteq 4m + \sum_{j \ne k} \left(f(\hat{r}_{j,k}) - \frac{c_{1}}{n}\left(1-\hat{r}_{j,k}^{2} \right)^{2} \right). $$ \end{document}σ2=Var(T)≐4m+∑j≠kf(r^j,k)−c1n1−r^j,k22.
