The traditional time domain heart rate variability index pNN50 is a percentage scale-based measure of large beat-to-beat changes in heart period that may reflect parasympathetic neural activity impinging on the sino-atrial node. However, pNN50 exhibits nonlinear saturation effects near 0% and 100% that may adversely affect its statistical properties. The purpose of this paper is to propose a revision of pNN50, Logit50, that is the natural logarithm of the odds of the occurrence of large beat-to-beat differences in R-R interval. Using five clinical and normal sample data sets, the revised Logit50 index is shown to retain the computational simplicity and interpretability of the pNN50, but to have better metric properties in statistical and clinical applications. In particular, the Logit50 is demonstrated to be relatively unaffected by the positive distributional skew that is common in most statistical applications of pNN50.