Reservoir studies commonly consider many scenarios, cases and realizations. However, reservoir simulation can be expensive. Statistical design has been used in reservoir engineering applications, including performance prediction, uncertainty modelling, sensitivity studies, upscaling, history matching and development optimization. If reservoir simulation studies are conducted with a statistical design, response surface models can estimate how the variation of input factors affects reservoir behaviour with a relatively small number of reservoir simulation models. In petroleum exploration and production, a decision has to consider the risk involved in the process which can be obtained by quantifying the impact of uncertainties on the performance of the petroleum field in question. The process is even more critical because most of the investments are realized during the phase in which the uncertainties are greater. The statistical design is efficient to quantify the impact of the uncertainties of the reservoirs in the production forecast and to reduce the number of simulations to obtain the risk curve. The main objective of this work is the application of the statistical design. Box-Behnken and Central Composite Design using different attributes ranges. To compare the precision of the results, different techniques are used. These are the Derivative Tree Technique by simulation flow, the Monte Carlo Technique and the Response Surface Methodology.