The present study was intended to evaluate the statistic methods of Models Identity, Dummy Variables (binary) and Variance Analysis, used for comparing regression models, by means of computer data simulation. Four linear regression cases and five cases of quadratic polynomial regression were considered. By utilizing the resources of the modulus of the Interactive Matrix Language (IML) of the Statistical Analysis System (SAS), appropriate routines were developed for the implementation of the methodology. A data simulation made up of 10.000 experiments was carried out, considering the different sample sizes (10, 50 and 100 observations) for each one of the nine cases reported. The results of all the situations simulated through the three methods were similar, presenting a low Type I Error and Type II Error percentage. The Dummy Variable Method proved to be the most efficient for the three sizes of samples, for it presented the lowest percentages of Type I Error and Type II Error. Key words: Models Identity. Dummy Variables (binary). Variance Analysis.