Evaluation of methods for comparing regression models by data simulation
Keywords:Models Identity, Dummy variables (binary), Variance analysis.
AbstractThe 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.
How to Cite
The Copyright Declaration for articles published in this journal is the author’s right. Since manuscripts are published in an open access Journal, they are free to use, with their own attributions, in educational and non-commercial applications. The Journal has the right to make, in the original document, changes regarding linguistic norms, orthography, and grammar, with the purpose of ensuring the standard norms of the language and the credibility of the Journal. It will, however, respect the writing style of the authors. When necessary, conceptual changes, corrections, or suggestions will be forwarded to the authors. In such cases, the manuscript shall be subjected to a new evaluation after revision. Responsibility for the opinions expressed in the manuscripts lies entirely with the authors.
This journal is licensed with a license Creative Commons Attribution-NonCommercial 4.0 International.