CAN MULTIPLE MODELS IMPROVE BAYESIAN'S PERFORMANCE? AN INVESTIGATION USING MCNEMAR'S TEST

Machine learning algorithms have been widely used for classification purposes in a number of research domains; however, very few researches paid any attention to statistically validate the performance these different data. This paper attempted study Naïve Bayes algorithm’s dataset sizes. Furthermore, known theory has also investigated, that building multiple models such as Bagging, Boosting and Stacking tend improve classifier’s performance. The analysis performed using McNemar’s test; well nonparametric statistical test medical domain. Results showed not all ensemble methods work expected therefore, needs be selected carefully. Moreover, use appeared simple, but gave valid results.