The response surface methodology plays an important role in the developing, improving and optimizing processes and products through the application of a collection of statistical and mathematical techniques. The main focus of this research is the last step of the methodology that is related to the study of the response surface in the region of interest. Thus, this dissertation aims to present a summarized methodology for ridge analysis in the fitted models of the second-order response surfaces that have a saddle point or a point out of the experimental region as a stationary point. This analysis looks for the optimum process and product conditions through planned experiments. Ridge analysis is particularly important when it is difficult to visualize the response surface due to the existence of four or more dimensions. In this work there are some examples that derive from literature, and an analysis of a real case study is also performed.