The influence of em estimation of missing nodes in DCM on model ranking

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In Dynamic Causal Modeling (DCM) group analyses alternative model(s) are commonly specified and compared against each other. A model comparison problem is generally encountered by any kind of modeling approach where model selection is required given some observed data and several alternative models. The goal would be to select the optimal model by deciding between competing hypotheses represented by different DCMs. These hypotheses can involve any part of the structure of the modeled system, i.e. the pattern of intrinsic or extrinsic connections to the system. However, the underlying assumption is that the comparison is only valid if the data is the same in all models. In DCM for fMRI, where the data results from concatenation of all the time series of all areas in the model, the comparison requires that only models containing the same areas are included. In previous work, we have shown that Expectation Maximization can address this limitation by estimating time series in subjects with missing areas. This opposed the traditional approach of using a less conservative p-value which creates noisy time series to enforce topological comparability across models. Alternative methods for inference include the Fixed Effects (FFX) Analysis and the Random Effects (RFX) Analysis which can be used to rank prospective models in a model comparison/selection problem. Furthermore, Bayesian Model Averaging (BMA) can also be applied enabling subject specific mean parameters to represent summary statistics for a standard group analysis. Significant differences in a given parameter between a control group and a patient group, for instance, could then be calculated by computing the two-sample t-test on the average data from the two groups.

Original languageEnglish
Title of host publication2015 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages195-199
Number of pages5
ISBN (Electronic)9781479975914
DOIs
Publication statusPublished - 23 Feb 2016
Externally publishedYes
EventIEEE Global Conference on Signal and Information Processing, GlobalSIP 2015 - Orlando, United States
Duration: 13 Dec 201516 Dec 2015

Other

OtherIEEE Global Conference on Signal and Information Processing, GlobalSIP 2015
CountryUnited States
CityOrlando
Period13/12/1516/12/15

Fingerprint

Time series
Statistics
Magnetic Resonance Imaging

Keywords

  • Dynamic Causal Modeling
  • Expectation-Maximization
  • Model Comparison
  • Model Ranking
  • Model Selection

ASJC Scopus subject areas

  • Information Systems
  • Signal Processing

Cite this

Zaghlool, S. (2016). The influence of em estimation of missing nodes in DCM on model ranking. In 2015 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2015 (pp. 195-199). [7418184] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/GlobalSIP.2015.7418184

The influence of em estimation of missing nodes in DCM on model ranking. / Zaghlool, Shaza.

2015 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2015. Institute of Electrical and Electronics Engineers Inc., 2016. p. 195-199 7418184.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Zaghlool, S 2016, The influence of em estimation of missing nodes in DCM on model ranking. in 2015 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2015., 7418184, Institute of Electrical and Electronics Engineers Inc., pp. 195-199, IEEE Global Conference on Signal and Information Processing, GlobalSIP 2015, Orlando, United States, 13/12/15. https://doi.org/10.1109/GlobalSIP.2015.7418184
Zaghlool S. The influence of em estimation of missing nodes in DCM on model ranking. In 2015 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2015. Institute of Electrical and Electronics Engineers Inc. 2016. p. 195-199. 7418184 https://doi.org/10.1109/GlobalSIP.2015.7418184
Zaghlool, Shaza. / The influence of em estimation of missing nodes in DCM on model ranking. 2015 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2015. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 195-199
@inproceedings{72184957d9574bba967b6345b9c73e8f,
title = "The influence of em estimation of missing nodes in DCM on model ranking",
abstract = "In Dynamic Causal Modeling (DCM) group analyses alternative model(s) are commonly specified and compared against each other. A model comparison problem is generally encountered by any kind of modeling approach where model selection is required given some observed data and several alternative models. The goal would be to select the optimal model by deciding between competing hypotheses represented by different DCMs. These hypotheses can involve any part of the structure of the modeled system, i.e. the pattern of intrinsic or extrinsic connections to the system. However, the underlying assumption is that the comparison is only valid if the data is the same in all models. In DCM for fMRI, where the data results from concatenation of all the time series of all areas in the model, the comparison requires that only models containing the same areas are included. In previous work, we have shown that Expectation Maximization can address this limitation by estimating time series in subjects with missing areas. This opposed the traditional approach of using a less conservative p-value which creates noisy time series to enforce topological comparability across models. Alternative methods for inference include the Fixed Effects (FFX) Analysis and the Random Effects (RFX) Analysis which can be used to rank prospective models in a model comparison/selection problem. Furthermore, Bayesian Model Averaging (BMA) can also be applied enabling subject specific mean parameters to represent summary statistics for a standard group analysis. Significant differences in a given parameter between a control group and a patient group, for instance, could then be calculated by computing the two-sample t-test on the average data from the two groups.",
keywords = "Dynamic Causal Modeling, Expectation-Maximization, Model Comparison, Model Ranking, Model Selection",
author = "Shaza Zaghlool",
year = "2016",
month = "2",
day = "23",
doi = "10.1109/GlobalSIP.2015.7418184",
language = "English",
pages = "195--199",
booktitle = "2015 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2015",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - The influence of em estimation of missing nodes in DCM on model ranking

AU - Zaghlool, Shaza

PY - 2016/2/23

Y1 - 2016/2/23

N2 - In Dynamic Causal Modeling (DCM) group analyses alternative model(s) are commonly specified and compared against each other. A model comparison problem is generally encountered by any kind of modeling approach where model selection is required given some observed data and several alternative models. The goal would be to select the optimal model by deciding between competing hypotheses represented by different DCMs. These hypotheses can involve any part of the structure of the modeled system, i.e. the pattern of intrinsic or extrinsic connections to the system. However, the underlying assumption is that the comparison is only valid if the data is the same in all models. In DCM for fMRI, where the data results from concatenation of all the time series of all areas in the model, the comparison requires that only models containing the same areas are included. In previous work, we have shown that Expectation Maximization can address this limitation by estimating time series in subjects with missing areas. This opposed the traditional approach of using a less conservative p-value which creates noisy time series to enforce topological comparability across models. Alternative methods for inference include the Fixed Effects (FFX) Analysis and the Random Effects (RFX) Analysis which can be used to rank prospective models in a model comparison/selection problem. Furthermore, Bayesian Model Averaging (BMA) can also be applied enabling subject specific mean parameters to represent summary statistics for a standard group analysis. Significant differences in a given parameter between a control group and a patient group, for instance, could then be calculated by computing the two-sample t-test on the average data from the two groups.

AB - In Dynamic Causal Modeling (DCM) group analyses alternative model(s) are commonly specified and compared against each other. A model comparison problem is generally encountered by any kind of modeling approach where model selection is required given some observed data and several alternative models. The goal would be to select the optimal model by deciding between competing hypotheses represented by different DCMs. These hypotheses can involve any part of the structure of the modeled system, i.e. the pattern of intrinsic or extrinsic connections to the system. However, the underlying assumption is that the comparison is only valid if the data is the same in all models. In DCM for fMRI, where the data results from concatenation of all the time series of all areas in the model, the comparison requires that only models containing the same areas are included. In previous work, we have shown that Expectation Maximization can address this limitation by estimating time series in subjects with missing areas. This opposed the traditional approach of using a less conservative p-value which creates noisy time series to enforce topological comparability across models. Alternative methods for inference include the Fixed Effects (FFX) Analysis and the Random Effects (RFX) Analysis which can be used to rank prospective models in a model comparison/selection problem. Furthermore, Bayesian Model Averaging (BMA) can also be applied enabling subject specific mean parameters to represent summary statistics for a standard group analysis. Significant differences in a given parameter between a control group and a patient group, for instance, could then be calculated by computing the two-sample t-test on the average data from the two groups.

KW - Dynamic Causal Modeling

KW - Expectation-Maximization

KW - Model Comparison

KW - Model Ranking

KW - Model Selection

UR - http://www.scopus.com/inward/record.url?scp=84964712063&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84964712063&partnerID=8YFLogxK

U2 - 10.1109/GlobalSIP.2015.7418184

DO - 10.1109/GlobalSIP.2015.7418184

M3 - Conference contribution

SP - 195

EP - 199

BT - 2015 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2015

PB - Institute of Electrical and Electronics Engineers Inc.

ER -