A Simulation Study for Pairwise Multiple Comparisons with Heteroscedastic Variances

• Activity Number: 189
• Type: Contributed
• Date/Time: Monday, August 10, 2015 : 10:30 AM to 12:20 PM
• Sponsor: Section on Statistical Computing
• Author(s): Berna Yazici* and Evren Özkip and Ahmet Sezer
• Companies: Anadolu University and Ankara Police Collage and Anadolu University
• Keywords: heteroscedasticity ; generalized approach ; parametric bootstrap approach ; monte carlo method

Abstract

Generalized approach has been proved to be useful tools for making inferences in many practical problems. The parametric bootstrap approach is a type of Monte Carlo method applied on observed data. This approach can be applied in situations where samples or sample statistics are not easy to derive. In this paper, we consider simultaneous confidence intervals for one-way ANOVA under unequal variances. We compare two methods based on generalized approach and a parametric bootstrap approach. A Monte Carlo simulation study is conducted to evaluate type I error probabilities and powers of these methods under different scenarios.