One of the common dilemmas in the teaching and learning of statistics is the (lack of) reasoning that students demonstrate to deal with data. It is indeed a major problem in Initial Data Analysis: there is not a clear understanding of the data in order to highlight useful information and suggest conclusions to support decision making. To better understand the types of problems involved in this dilemma we have made a survey, based on simple problems in which students are invited to interpret the original data as well as tables and graphics. The main results of this survey indicate that students have a need of creativity to interpret statistical data, particularly when the concepts are learned in previous levels. The consolidation of the statistical concepts is missing as there is not enough memorization by students in order to apply the descriptive facet of the statistical cognition.