Monti_CriticalGLM

Monti_CriticalGLM - Statistical Analysis of fMRI...

Info iconThis preview shows pages 1–4. Sign up to view the full content.

View Full Document Right Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: Statistical Analysis of fMRI Time-Series: A Critical Evaluation of the GLM Approach Martin M. Monti ] Princeton University, Dept. of Psychology April 18, 2006 NUMBER OF PAGES: 44 ABBREVIATED TITLE: Statistical Analysis of fMRI Time-Series. Acknowledgements : Id like to thank Damien Rice, Muse, Radiohead and Dolorean for the musical support throughout the redaction of this manuscript. ] Correspondence address: Martin M. Monti Princeton University Department of Psychology Green Hall, Princeton, NJ 08544. Tel. (609)258- 5679 email: mmonti@princeton.edu 1 Statistical Analysis of fMRI Time-Series 2 Abstract Functional Magnetic Resonance Imaging (fMRI) is currently one of the most widely used tools to study in vivo the neural underpinnings of human cognition. Analysis of fMRI data relies on a General Linear Model (GLM) approach to separate noise from the actual signal corvarying with some experimental task of interest. Validity of inferences drawn from such approach to data-analysis is secondary to the satisfaction of condition imposed by the statistical model. In the present paper we review the GLM approach to fMRI time- series analysis by considering the degree by which such data abides by the hypothesis of the model and by presenting the methodologies that have been put forward in order to correct for assumptions infringement. KEYWORDS: Functional Magnetic Resonance Imaging (fMRI), Blood Oxygenation Level- Dependent (BOLD), General Linear Model (GLM), Ordinary Least Squares (OLS), Auto- correlation, Heteroscedasticity, Multicollinearity, Fixed Effects, Random Effects, Conjunc- tion Analysis. Statistical Analysis of fMRI Time-Series 3 Contents 0.1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4 0.2 Single Subject Analysis (I): The General Linear Model Approach . . . . . . . 5 0.3 Single Subject Analysis (II): The GM Assumptions & fMRI Time-Series . . . 8 0.3.1 Autocorrelation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8 0.3.2 Heteroscedasticity . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15 0.3.3 Multicollinearity . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16 0.3.4 Linearity . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17 0.4 Multiple Subjects Analysis . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21 0.4.1 Fixed Effects. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 22 0.4.2 Random Effects. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 24 0.4.3 Conjunction Analysis. . . . . . . . . . . . . . . . . . . . . . . . . . . . 26 0.4.4 Mixed-Effects & Summary Statistics Hierarchical Approach . . . . . 31 0.4.5 ANOVA Approach. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 33 0.4.6 Variance Smoothing. . . . . . . . . . . . . . . . . . . . . . . . . . . . . 34 0.5 Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 35 Statistical Analysis of fMRI Time-Series...
View Full Document

Page1 / 45

Monti_CriticalGLM - Statistical Analysis of fMRI...

This preview shows document pages 1 - 4. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online