Abstract
Permutation tests have extensively been used to estimate the significance of classification. Permutation tests usually use the test error as a dataset statistic to measure the difference between two or more populations. Then, to estimate the p-value(s), the test error is compared to a set of permuted test-error(s), which is usually obtained after permuting the labels of the populations. In this study, we investigate how several dataset factors, e.g., the number of samples, the number of classes, and the dimensionality size, may affect the p-value obtained via permutation tests. We performed the analysis using the standard permutation test procedure that uses the overall all test error dataset statistic and compared it to the permutation test procedure that uses per-class test error as a dataset statistic that we recently have proposed (doi:10.1016 /j.neucom.2011.11.007). We found that permutation tests that use a per-class test error as a dataset statistic are not only more reliable in addressing the null hypothesis but also are highly sensitive to changes in the dataset factors that we investigated in this work. An important finding of this study is that when the dimensionality is low and the number of classes is up to several, say ten, highly above chance accuracy would be required to state the significance. For the same low dimensionality, however, slightly above chance accuracy would be adequate to state significance in a two-class problem.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Al-Rawi, M.S., Cunha, J.P.S.: On using permutation tests to estimate the classification significance of functional magnetic resonance imaging. Neurocomputing 82, 224–233 (2012)
Al-Rawi, M.S., Cunha, J.P.S.: Using multivariate pattern analysis to study how specific brain regions respond to different visual stimulation. J. Neurol. 258, 167 (2011)
Detre, G.J., Polyn, S.M., Takerkart, S., Natu, V.S., Benharrosh, M.S., Singer, B.D., Cohen, J.D., Haxby, J.V., Norman, K.A.: The Multi-Voxel Pattern Analysis (MVPA). In: 12th Meeting of the Organization of Human Brain Mapping, Florence, Italy (2006)
Fisher, R.A.: Statistical methods for research workers. Oliver and Boyd (1954)
Golland, P., Fischl, B.: Permutation Tests for Classification: Towards Statistical Significance in Image-Based Studies. In: Taylor, C.J., Noble, J.A. (eds.) IPMI 2003. LNCS, vol. 2732, pp. 330–341. Springer, Heidelberg (2003)
Haxby, J.V., Gobbini, M.I., Furey, M.L., Ishai, A., Schouten, J.L., Pietrini, P.: Distributed and overlapping representations of faces and objects in ventral temporal cortex. Science 293, 2425–2430 (2001)
Maldjian, J.A., Laurienti, P.J., Kraft, R.A., Burdette, J.H.: An automated method for neuroanatomic and cytoarchitectonic atlas-based interrogation of fMRI datasets. NeuroImage 19, 1233–1239 (2003); WFU Pickatlas, version 2.4
Ojala, M., Garriga, G.C.: Permutation Tests for Studying Classifier Performance. J. Mach. Learn. Res. 11, 1833–1863 (2010)
Struyf, J., Dobrin, S., Page, D.: Combining gene expression, demographic and clinical data in modeling disease: a case study of bipolar disorder and schizophrenia. Bmc Genomics 9, 22 (2008)
Trautmann, E., Ray, L.: Mobility characterization for autonomous mobile robots using machine learning. Auton. Robot. 30, 369–383 (2011)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Al-Rawi, M.S., Cunha, J.P.S. (2012). Using Permutation Tests to Study How the Dimensionality, the Number of Classes, and the Number of Samples Affect Classification Analysis. In: Campilho, A., Kamel, M. (eds) Image Analysis and Recognition. ICIAR 2012. Lecture Notes in Computer Science, vol 7324. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-31295-3_5
Download citation
DOI: https://doi.org/10.1007/978-3-642-31295-3_5
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-31294-6
Online ISBN: 978-3-642-31295-3
eBook Packages: Computer ScienceComputer Science (R0)