The Wilcoxon statistic is often introduced from different points of view, and has been considered mainly as a linear rank statistic or as a U-statistic. For survival data analysis, it has also been considered as a weighted Mantel-Haenszel statistic. As a result, different approaches to censoring have led to different versions of generalized Wilcoxon statistics. The Gehan-Wilcoxon statistic has been widely used in practice and is available in many statistical software packages, even though it has been criticized as inappropriate for censored data and as inferior to Peto-Peto's generalization of the Wilcoxon statistic. A new and intuitive interpretation of Gehan's and Peto-Peto's generalized Wilcoxon statistic is presented here to illustrate their fundamental differences, and to show the possible hidden pitfalls of Gehan's generalization in the application of clinical trial data monitoring.