Non-parametric approaches provide inferential procedures to statistics based on some weak assumptions regarding the nature of the underlying population distributions. These procedures are commonly based on crisp information such as exact observations, crisp hypotheses, crisp categories, etc. But, in the real world, there are many situations in which, due to some practical limitations and/or human judgments, the available information is fuzzy rather than precise (crisp). To achieve suitable statistical methods in dealing with imprecise information, we first need to model such information and then extend the usual approaches to imprecise environments. Fuzzy set theory seems to have suitable tools for modeling this information and provide appropriate statistical methods based on such information. In this thesis , four subjects related to the testing non-parametric hypothesis are investigated in fuzzy environment, as follows: 1- Analysis of a two-way contingency table with imprecise information, 2- A generalization of the Wilcoxon signed-rank test and its applications, 3- Kolmogorov-Smirnov one-sample test in totally fuzzy environment, 4- Linear rank tests for two-sample fuzzy data; a p-value approach.