Descripción
|
|
---|---|
Several meta-analysis methods can be used to quantitatively combine the results of a group of experiments, including weighted mean differences, statistical vote counting, parametric response ratio and non-parametric response ratio. Research on the quantitative combination of experimental results in software engineering has mainly focused on weighted mean differences. However, the other meta-analysis methods have their strengths. The software engineering community has not yet investigated decision-making on which meta-analysis method to use. In this talk, I will describe the experimental conditions under which each meta-analysis method should be applied, based on a recent research that we performed using Monte Carlo simulations. | |
Internacional
|
Si |
ISSN o ISBN
|
978-85-87191-87-8 |
Entidad relacionada
|
Brazilian Computer Society |
Nacionalidad Entidad
|
BRASIL |
Lugar del congreso
|
Goiânia, Brasil |