The danger of systematic bias in group-level FMRI-lag-based causality estimation.
Schippers, Renken and Keysers (NeuroImage, 2011) present a simulation of multi-subject lag-based causality estimation. We fully agree that single-subject evaluations (e.g., Smith et al., 2011) need to be revisited in the context of multi-subject studies, and Schippers' paper is a good example,...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Journal article |
| Language: | English |
| Published: |
2012
|
| _version_ | 1797078208158367744 |
|---|---|
| author | Smith, S Bandettini, P Miller, K Behrens, T Friston, K David, O Liu, T Woolrich, M Nichols, T |
| author_facet | Smith, S Bandettini, P Miller, K Behrens, T Friston, K David, O Liu, T Woolrich, M Nichols, T |
| author_sort | Smith, S |
| collection | OXFORD |
| description | Schippers, Renken and Keysers (NeuroImage, 2011) present a simulation of multi-subject lag-based causality estimation. We fully agree that single-subject evaluations (e.g., Smith et al., 2011) need to be revisited in the context of multi-subject studies, and Schippers' paper is a good example, including detailed multi-level simulation and cross-subject statistical modelling. The authors conclude that "the average chance to find a significant Granger causality effect when no actual influence is present in the data stays well below the p-level imposed on the second level statistics" and that "when the analyses reveal a significant directed influence, this direction was accurate in the vast majority of the cases". Unfortunately, we believe that the general meaning that may be taken from these statements is not supported by the paper's results, as there may in reality be a systematic (group-average) difference in haemodynamic delay between two brain areas. While many statements in the paper (e.g., the final two sentences) do refer to this problem, we fear that the overriding message that many readers may take from the paper could cause misunderstanding. |
| first_indexed | 2024-03-07T00:28:51Z |
| format | Journal article |
| id | oxford-uuid:7f12cf36-163d-4ade-97f2-e8ccd03e5244 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-07T00:28:51Z |
| publishDate | 2012 |
| record_format | dspace |
| spelling | oxford-uuid:7f12cf36-163d-4ade-97f2-e8ccd03e52442022-03-26T21:14:26ZThe danger of systematic bias in group-level FMRI-lag-based causality estimation.Journal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:7f12cf36-163d-4ade-97f2-e8ccd03e5244EnglishSymplectic Elements at Oxford2012Smith, SBandettini, PMiller, KBehrens, TFriston, KDavid, OLiu, TWoolrich, MNichols, TSchippers, Renken and Keysers (NeuroImage, 2011) present a simulation of multi-subject lag-based causality estimation. We fully agree that single-subject evaluations (e.g., Smith et al., 2011) need to be revisited in the context of multi-subject studies, and Schippers' paper is a good example, including detailed multi-level simulation and cross-subject statistical modelling. The authors conclude that "the average chance to find a significant Granger causality effect when no actual influence is present in the data stays well below the p-level imposed on the second level statistics" and that "when the analyses reveal a significant directed influence, this direction was accurate in the vast majority of the cases". Unfortunately, we believe that the general meaning that may be taken from these statements is not supported by the paper's results, as there may in reality be a systematic (group-average) difference in haemodynamic delay between two brain areas. While many statements in the paper (e.g., the final two sentences) do refer to this problem, we fear that the overriding message that many readers may take from the paper could cause misunderstanding. |
| spellingShingle | Smith, S Bandettini, P Miller, K Behrens, T Friston, K David, O Liu, T Woolrich, M Nichols, T The danger of systematic bias in group-level FMRI-lag-based causality estimation. |
| title | The danger of systematic bias in group-level FMRI-lag-based causality estimation. |
| title_full | The danger of systematic bias in group-level FMRI-lag-based causality estimation. |
| title_fullStr | The danger of systematic bias in group-level FMRI-lag-based causality estimation. |
| title_full_unstemmed | The danger of systematic bias in group-level FMRI-lag-based causality estimation. |
| title_short | The danger of systematic bias in group-level FMRI-lag-based causality estimation. |
| title_sort | danger of systematic bias in group level fmri lag based causality estimation |
| work_keys_str_mv | AT smiths thedangerofsystematicbiasingrouplevelfmrilagbasedcausalityestimation AT bandettinip thedangerofsystematicbiasingrouplevelfmrilagbasedcausalityestimation AT millerk thedangerofsystematicbiasingrouplevelfmrilagbasedcausalityestimation AT behrenst thedangerofsystematicbiasingrouplevelfmrilagbasedcausalityestimation AT fristonk thedangerofsystematicbiasingrouplevelfmrilagbasedcausalityestimation AT davido thedangerofsystematicbiasingrouplevelfmrilagbasedcausalityestimation AT liut thedangerofsystematicbiasingrouplevelfmrilagbasedcausalityestimation AT woolrichm thedangerofsystematicbiasingrouplevelfmrilagbasedcausalityestimation AT nicholst thedangerofsystematicbiasingrouplevelfmrilagbasedcausalityestimation AT smiths dangerofsystematicbiasingrouplevelfmrilagbasedcausalityestimation AT bandettinip dangerofsystematicbiasingrouplevelfmrilagbasedcausalityestimation AT millerk dangerofsystematicbiasingrouplevelfmrilagbasedcausalityestimation AT behrenst dangerofsystematicbiasingrouplevelfmrilagbasedcausalityestimation AT fristonk dangerofsystematicbiasingrouplevelfmrilagbasedcausalityestimation AT davido dangerofsystematicbiasingrouplevelfmrilagbasedcausalityestimation AT liut dangerofsystematicbiasingrouplevelfmrilagbasedcausalityestimation AT woolrichm dangerofsystematicbiasingrouplevelfmrilagbasedcausalityestimation AT nicholst dangerofsystematicbiasingrouplevelfmrilagbasedcausalityestimation |