Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

A Least Trimmed Square Regression Method for Second Level fMRI Effective Connectivity Analysis

A Least Trimmed Square Regression Method for Second Level fMRI Effective Connectivity Analysis We present a least trimmed square (LTS) robust regression method to combine different runs/subjects for second/high level effective connectivity analysis. The basic idea of this method is to treat the extreme nonlinear model variability as outliers if they exceed a certain threshold. A bootstrap method for the LTS estimation is employed to detect model outliers. We compared the LTS robust method with a non-robust method using simulated and real datasets. The difference between LTS and the non-robust method for second level effective connectivity analysis is significant, suggesting the conventional non-robust method is easily affected by the model variability from the first level analysis. In addition, after these outliers are detected and excluded for the high level analysis, the model coefficients of the second level are combined within the framework of a mixed model. The variance of the mixed model is estimated using the Newton–Raphson (NR) type Levenberg-Marquardt algorithm. Three sets of real data are adopted to compare conventional methods which do not include random effects in the analysis with a mixed model for second level effective connectivity analysis. The results show that the conventional method is significantly different from the mixed model when greater model variability exists, suggesting there is a strong random effect, and the mixed model should be employed for the second level effective connectivity analysis. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Neuroinformatics Springer Journals

A Least Trimmed Square Regression Method for Second Level fMRI Effective Connectivity Analysis

Download PDF
14 pages

Loading next page...
 
/lp/springer-journals/a-least-trimmed-square-regression-method-for-second-level-fmri-Q4DHB3KTPD
Publisher
Springer Journals
Copyright
Copyright © 2012 by Springer Science+Business Media New York
Subject
Biomedicine; Neurosciences; Bioinformatics; Computational Biology/Bioinformatics; Computer Appl. in Life Sciences; Neurology
ISSN
1539-2791
eISSN
1559-0089
DOI
10.1007/s12021-012-9168-8
pmid
23093379
Publisher site
See Article on Publisher Site

Abstract

We present a least trimmed square (LTS) robust regression method to combine different runs/subjects for second/high level effective connectivity analysis. The basic idea of this method is to treat the extreme nonlinear model variability as outliers if they exceed a certain threshold. A bootstrap method for the LTS estimation is employed to detect model outliers. We compared the LTS robust method with a non-robust method using simulated and real datasets. The difference between LTS and the non-robust method for second level effective connectivity analysis is significant, suggesting the conventional non-robust method is easily affected by the model variability from the first level analysis. In addition, after these outliers are detected and excluded for the high level analysis, the model coefficients of the second level are combined within the framework of a mixed model. The variance of the mixed model is estimated using the Newton–Raphson (NR) type Levenberg-Marquardt algorithm. Three sets of real data are adopted to compare conventional methods which do not include random effects in the analysis with a mixed model for second level effective connectivity analysis. The results show that the conventional method is significantly different from the mixed model when greater model variability exists, suggesting there is a strong random effect, and the mixed model should be employed for the second level effective connectivity analysis.

Journal

Neuroinformatics – Springer Journals

Published: Oct 24, 2012

References

  • The multivariate least-trimmed squares estimator
    Agulló, J; Croux, C; Aelst, S
  • A new look at the statistical model identification
    Akaike, H
  • Effect of hemodynamic variability on Granger analysis of fMRI
    Deshpande, G; Sathian, K; Hu, X
  • A new anatomical landmark for reliable identification of human area V5/MT: a quantitative analysis of sulcal patterning
    Dumoulin, S; Bitter, RG; Kabani, NJ; Baker, CL; Goualher, GL; Pike, GB; Evans, AC
  • Least angle regression
    Efron, B; Hastie, T; Johnstone, I; Tibshirani, R
  • Retinotopic organization in human visual cortex and the spatial precision of functional MRI
    Engel, S; Glover, GH; Wandell, BA
  • Assessment of Granger causality by nonlinear model identification: application to short-term cardiovascular variability
    Faes, L; Nollo, G; Chon, KH
  • Mixed-effects and fMRI studies
    Friston, KJ; Stephan, KE; Lund, TE; Morcom, A; Kiebel, S
  • Investigating causal relations by econometric models and cross-spectral methods
    Granger, C
  • Multivariate autoregressive modeling of fMRI time series
    Harrison, L; Penny, WD; Friston, KJ
  • Maximum likelihood approaches to variances component estimation and to related problems
    Harville, JA
  • Forward stagewise regression and the monotone lasso
    Hastie, T; Taylor, J; Tibshirani, R; Walther, G
  • Deficient responsed from the lateral geniculate nucleus in humans with amblyopia
    Hess, RF; Thompson, B; Gole, G; Mullen, KT
  • Robust regression: asymptotics, conjectures and Monte Carlo
    Huber, PJ
  • Minimum covariance determinant
    Hubert, M; Debruyne, M
  • High-breakdown robust multivariate methods
    Hubert, M; Rousseeuw, PJ; Aelst, SV
  • The singular value decomposition—Applied in the modelling and prediction of quasiperiodic processes
    Kanjilal, PP; Palit, S
  • Fast robust estimation of prediction error based on resampling
    Khan, JA; Aelst, S; Zamar, RH
  • Functional connectivity: study nonlinear delayed interactions between BOLD signals
    Lahaye, PJ; Poline, JB; Flandin, G; Dodel, S; Garneo, L
  • Cortical deficits in human amblyopia: their regional distribution and their relationship to the contrast detection deficit
    Li, X; Dumoulin, SO; Mansouri, B; Hess, RF
  • The fidelity of the cortical retinotopic map in human amblyopia
    Li, X; Dumoulin, SO; Mansouri, B; Hess, RF
  • A least angle regression method for fMRI activation detection for phase-encoded experimental designs
    Li, X; Coyle, D; Maguire, L; McGinnity, TM; Watson, DR; Benali, H
  • A nonlinear identification method to study effective connectivity in functional MRI
    Li, X; Marrelec, G; Hess, RF; Benali, H
  • A model selection method for nonlinear system identification based fMRI effective connectivity analysis
    Li, X; Coyle, D; Maguire, L; McGinnity, TM
  • An Algorithm for Least-Squares Estimation of Nonlinear Parameters
    Marquardt, D
  • Color responses of the human lateral geniculate nucleus: selective amplification of S-cone signals between the lateral geniculate nucleno and primary visual cortex measured with high-field fMRI
    Mullen, KT; Dumoulin, SO; Hess, RF
  • Nonlinear multivariate analysis of neurophysiological signals
    Pereda, E; Quiroga, RQ; Bhattacharya, J
  • Mapping directed influence over the brain using Ganger causality and fMRI
    Roebroeck, A; Formisano, E; Goebel, R
  • Least median of squares regression
    Rousseeuw, PJ
  • A fast algorithm for the minimum covariance determinant estimator
    Rousseeuw, PJ; Driessen, KV
  • Computing LTS Regression for Large Data Sets
    Rousseeuw, P; Driessen, K
  • Robust mutivariate regression
    Rousseeuw, PJ; Aelst, SV; Driessen, KV; Agulló, J
  • Variance components
    Searle, S; Casella, G; McCulloch, C
  • Linear regression analysis
    Seber, G; Lee, AJ
  • Borders of multiple visual areas in humans revealed by functional magnetic resonance imaging
    Sereno, M; Dale, AM; Reppas, JB; Kwong, KK; Belliveau, JW; Brady, TJ; Rosen, BR; Tootell, RB
  • Estimating brain functional connectivity with spare multivariate autoregression
    Valdes-Sosa, P; Sanchez-Bornot, JM; Lage-Castellanos, A; Vega-Hernandez, M; Bosch-Bayard, J; Melie-Carcia, L; Canales-Rodriguez, E
  • Effective connectivity: influence, causality and biophysical modeling
    Valdes-Sosa, P; Roebroeck, A; Daunizeau, J; Friston, K
  • fMRI retinotopic mapping-step by step
    Warnking, J; Dojat, M; Guérie-Dugué, A; Delon-Martin, C; Olympieff, S; Richard, N; Chehikian, A; Segebarth, C
  • Fast and robust bootstrap for LTS
    Willems, G; Aelst, S