Performance comparison of model selection criteria by generated experimental data

¹ Department of Electrical Engineering, Electronics and Automatics, Faculty of Engineering, University Center for Advanced Bioinformatics Research, South-West University “Neofit Rilski”, 66 Ivan Mihaylov Str., 2700 Blagoevgrad, Bulgaria
² Department of Informatics, Faculty of Mathematics and Natural Sciences, University Center for Advanced Bioinformatics Research, South-West University “Neofit Rilski”, 66 Ivan Mihaylov Str., 2700 Blagoevgrad, Bulgaria
³ Institute of Mathematics and Informatics, Bulgarian Academy of Sciences, Acad. Georgi Bonchev Str., Block 8, 1113 Sofia, Bulgaria
⁴ Department of Health Cares, Faculty of Public Health, Health Cares and Sports, University Center for Functional Research in Sports and Kinesitherapy, South-West University “Neofit Rilski”, 66 Ivan Mihaylov Str., 2700 Blagoevgrad, Bulgaria

^* Corresponding author: radoslav_sm@abv.bg

Abstract

In Bioinformatics and other areas the model selection is a process of choosing a model from set of candidate models of different classes which will provide the best balance between goodness of fitting of the data and complexity of the model. There are many criteria for evaluation of mathematical models for data fitting. The main objectives of this study are: (1) to fitting artificial experimental data with different models with increasing complexity; (2) to test whether two known criteria as Akaike’s information criterion (AIC) and Bayesian information criterion (BIC) can correctly identify the model, used to generate the artificial data and (3) to assess and compare empirically the performance of AIC and BIC.