Conglomeration of General Linear Model for Epilepsy Clinical Neuroimaging

An innovative standard scheme was established aimed at developing inferences and interpretations statistically relative to clinical neuroimaging facts and figures. It involves as particular instances, SPMs, a standard methodology to clinical neuroimaging anatomy. Our developed model contributes and provides various educational and statistical benefits which begin from the anatomy of facts at group level before the level of the voxel, commencing by direct modelling of the location and shape of the modules. We set out a new general framework for making inferences from neuroimaging data, which includes a standard approach to neuroimaging analysis, statistical parametric mapping (SPM), as a particular case. The model offers numerous conceptual and statistical advantages that begin from analysis of the collected data at the group level somewhat than the voxel level, from explicit modelling of the shape and position of clusters of activation. It provides a natural and moral way to pool data from nearby voxels for parameter and variance-component estimation. The model can also be viewed as performing Spatio-temporal cluster analysis. The parameters of the model are estimated using an expectation-maximization (EM) algorithm.

Download Full-text

Modeling Group-Level Repeated Measurements of Neuroimaging Data Using the Univariate General Linear Model

Frontiers in Neuroscience ◽

10.3389/fnins.2019.00352 ◽

2019 ◽

Vol 13 ◽

Cited By ~ 7

Author(s):

Martyn McFarquhar

Keyword(s):

Linear Model ◽

General Linear Model ◽

Repeated Measurements ◽

General Linear ◽

Group Level ◽

Modeling Group ◽

Neuroimaging Data

Download Full-text

Non-negative variance component estimation for the partial EIV model by the expectation maximization algorithm

Geomatics Natural Hazards and Risk ◽

10.1080/19475705.2020.1785955 ◽

2020 ◽

Vol 11 (1) ◽

pp. 1278-1298

Author(s):

Leyang Wang ◽

Qiwen Wu

Keyword(s):

Expectation Maximization ◽

Variance Component ◽

Expectation Maximization Algorithm ◽

Variance Component Estimation ◽

Component Estimation

Download Full-text

Modelling group-level repeated measures of neuroimaging data using the univariate general linear model

10.31234/osf.io/a5469 ◽

2018 ◽

Author(s):

Martyn McFarquhar

Keyword(s):

Linear Model ◽

Repeated Measures ◽

General Linear Model ◽

Repeated Measurements ◽

General Linear ◽

Group Level ◽

Repeated Measures Anova ◽

Continuous Covariates ◽

Neuroimaging Data ◽

Model Approach

Group-level repeated measurements are common in neuroimaging, yet their analysis remains complex. Although a variety of specialised tools now exist, it is surprising that to-date there has been no clear discussion of how repeated-measurements can be analysed appropriately using the standard general linear model approach, as implemented in software such as SPM and FSL. This is particularly surprising given that these implementations necessitate the use of multiple models, even for seemingly conventional analyses, and that without care it is very easy to specify contrasts that do not correctly test the effects of interest. Despite this, interest in fitting these types of models using conventional tools has been growing in the neuroimaging community. As such it has become even more important to elucidate the correct means of doing so. To begin, this paper will discuss the key concept of the expected mean squares (EMS) for defining suitable F -ratios for testing hypotheses. Once this is understood, the logic of specifying correct repeated measurements models in the GLM should be clear. The ancilliary issue of specifying suitable contrast weights in these designs will also be discussed, providing a complimentary perspective on the EMS. A set of steps will then be given alongside an example of specifying a 3-way repeated-measures ANOVA in SPM. Equivalency of the results compared to other statistical software will be demonstrated. Additional issues, such as the inclusion of continuous covariates and the assumption of sphericity, will also be discussed. The hope is that this paper will provide some clarity on this confusing topic, giving researchers the confidence to correctly specify these forms of models within traditional neuroimaging analysis tools.

Download Full-text

Faculty Opinions recommendation of Modeling Group-Level Repeated Measurements of Neuroimaging Data Using the Univariate General Linear Model.

Faculty Opinions – Post-Publication Peer Review of the Biomedical Literature ◽

10.3410/f.735692004.793561798 ◽

2019 ◽

Author(s):

Lutz Jäncke

Keyword(s):

Linear Model ◽

General Linear Model ◽

Repeated Measurements ◽

General Linear ◽

Group Level ◽

Modeling Group ◽

Neuroimaging Data

Download Full-text

GPS-BDS-Galileo double-differenced stochastic model refinement based on least-squares variance component estimation

Journal of Navigation ◽

10.1017/s0373463321000564 ◽

2021 ◽

pp. 1-16

Author(s):

Hong Hu ◽

Xuefeng Xie ◽

Jingxiang Gao ◽

Shuanggen Jin ◽

Peng Jiang

Keyword(s):

Stochastic Model ◽

Least Squares ◽

Stochastic Models ◽

Variance Component ◽

Satellite System ◽

Variance Component Estimation ◽

Short Baseline ◽

Component Estimation ◽

Zero Baseline ◽

Global Navigation Satellite

Abstract Stochastic models are essential for precise navigation and positioning of the global navigation satellite system (GNSS). A stochastic model can influence the resolution of ambiguity, which is a key step in GNSS positioning. Most of the existing multi-GNSS stochastic models are based on the GPS empirical model, while differences in the precision of observations among different systems are not considered. In this paper, three refined stochastic models, namely the variance components between systems (RSM1), the variances of different types of observations (RSM2) and the variances of observations for each satellite (RSM3) are proposed based on the least-squares variance component estimation (LS-VCE). Zero-baseline and short-baseline GNSS experimental data were used to verify the proposed three refined stochastic models. The results show that, compared with the traditional elevation-dependent model (EDM), though the proposed models do not significantly improve the ambiguity resolution success rate, the positioning precision of the three proposed models has been improved. RSM3, which is more realistic for the data itself, performs the best, and the precision at elevation mask angles 20°, 30°, 40°, 50° can be improved by 4⋅6%, 7⋅6%, 13⋅2%, 73⋅0% for L1-B1-E1 and 1⋅1%, 4⋅8%, 16⋅3%, 64⋅5% for L2-B2-E5a, respectively.

Download Full-text