I am working on a dataset where I need to fit a non-linear model to observed data and perform a permutation test to check the significance of the fit. The dataset consists of measurements related to mean values (mean.val), variance (var.val), and a calculated variable (VR.val). The goal is to fit the model VR.val ~ (var.val / (mean.val^2)) - (1 / mean.val) and then perform a permutation test to determine if the observed relationship is significant.