A new approach for testing fuzzy hypotheses with fuzzy data based on fuzzy test statistic function is proposed. First, the authors present h-level (the end points are closed interval) for the fuzzy hypotheses parameter and the fuzzy data. Then, they construct the related fuzzy test statistic. Second, three different types of fuzzy hypotheses parameters are defined. Finally, a practical example for radar decision criteria is provided based on it to clarify the proposed approaching method. The advantages of the proposed method with respect to the three methods are shown and discussed.