Publications
2012
Billinger, Martin; Daly, Ian; Kaiser, Vera; Jin, Jing; Allison, Brendan Z.; Müller-Putz, Gernot R.; Brunner, Clemens
Is it Significant? Guidelines for Reporting BCI Performance Book Chapter
In: Stephen Dunne Brendan Z. Allison, Robert Leeb (Ed.): pp. 333-354, Springer, 2012, ISBN: 978-3-642-29745-8.
Abstract | Links | BibTeX | Tags: BCI, Classification, Information transfer rate, Significance testing
@inbook{Billinger2012,
title = {Is it Significant? Guidelines for Reporting BCI Performance},
author = {Martin Billinger and Ian Daly and Vera Kaiser and Jing Jin and Brendan Z. Allison and Gernot R. Müller-Putz and Clemens Brunner},
editor = {Brendan Z. Allison, Stephen Dunne, Robert Leeb, José Del R. Millán, Anton Nijholt},
url = {http://link.springer.com/chapter/10.1007%2F978-3-642-29746-5_17},
doi = {10.1007/978-3-642-29746-5_17},
isbn = {978-3-642-29745-8},
year = {2012},
date = {2012-07-07},
pages = {333-354},
publisher = {Springer},
abstract = {Recent growth in brain-computer interface (BCI) research has increased pressure to report improved performance. However, different research groups report performance in different ways. Hence, it is essential that evaluation procedures are valid and reported in sufficient detail. In this chapter we give an overview of available performance measures such as classification accuracy, cohen’s kappa, information transfer rate (ITR), and written symbol rate. We show how to distinguish results from chance level using confidence intervals for accuracy or kappa. Furthermore, we point out common pitfalls when moving from offline to online analysis and provide a guide on how to conduct statistical tests on (BCI) results.},
keywords = {BCI, Classification, Information transfer rate, Significance testing},
pubstate = {published},
tppubtype = {inbook}
}
Recent growth in brain-computer interface (BCI) research has increased pressure to report improved performance. However, different research groups report performance in different ways. Hence, it is essential that evaluation procedures are valid and reported in sufficient detail. In this chapter we give an overview of available performance measures such as classification accuracy, cohen’s kappa, information transfer rate (ITR), and written symbol rate. We show how to distinguish results from chance level using confidence intervals for accuracy or kappa. Furthermore, we point out common pitfalls when moving from offline to online analysis and provide a guide on how to conduct statistical tests on (BCI) results.